VOLUME 11, ISSUE 7, JULY 2024

Abstract: This survey delves into the critical domain of IoT device security and network protocols, examining prevailing challenges, vulnerabilities, and countermeasures. As IoT devices proliferate across diverse sectors, ensuring their security becomes paramount, necessitating a comprehensive exploration of existing challenges. The study scrutinizes the vulnerabilities associated with current IoT network protocols, shedding light on potential threats and weaknesses. By providing an in-depth analysis of countermeasures, the paper seeks to contribute valuable insights into fortifying the security posture of IoT devices and their underlying network infrastructure. This comprehensive survey serves as a useful resource for researchers, practitioners, and policymakers aiming to address the evolving landscape of IoT security.

Keywords: IoT device, network protocols, challenges, vulnerabilities, countermeasures.

Abstract: Leveraging a comprehensive dataset from DNB, Norway's largest bank, this study aims to design, detail, and assess a machine learning system tailored to prioritize financial transactions for manual review in the context of potential money laundering. The model employs supervised machine learning techniques and draws on three categories of historical data: transactions flagged as suspicious by the bank's internal alert system, routine legal transactions, and potential money laundering cases reported to authorities. By analyzing sender and recipient background information, historical behavior, and transaction history, the model is trained to predict the likelihood that a new transaction should be reported. The findings indicate that excluding unreported alarms and uninvestigated transactions from the training process can lead to suboptimal model performance.

Keywords: Supervised Learning, Machine Learning, Beneish Score, Hybrid Model, Suspicious Transactions, Financial Statement Fraud, Hidden Markov Model.

Abstract: Irrigation system is becoming smart by using modern technologies, which is more advantageous than traditional irrigation methods. In this work, a irrigation system is developed that automates the irrigation process powered by solar energy. This system operates by automatically turning the motor on or off to allow water to flow through the pump based on the needs of the soil, as determined by a soil moisture sensor. This not only minimizes water wastage but also ensures that crops receive the right amount of water at the right time. The soil moisture sensor detects the humidity levels in the soil and transmits this data to the control modules. The system then analyses this data and activates the water pump as needed. By using solar power, this irrigation system not only conserves water but also electricity, making it a cost-effective solution to our energy needs. Additionally, solar-powered smart irrigation systems are especially beneficial for Indian farmers, providing a reliable and sustainable solution. Although this system does not function at night, we can integrate rechargeable batteries to maintain operation, ensuring continuous irrigation. In conclusion, this smart irrigation system is highly recommended for farmers in areas with limited access to a constant water supply. It promotes sustainable agriculture by being economical, eco-friendly, and efficient.

Keywords: Soil moisture sensor, Arduino, IC 7812, LCD display module, Relay module, water pump, real-time data transmission, automatic moisture sensing and water pumping.

Abstract: The paper explores the integration of solar technology with UPS systems to provide sustainable and reliable power solutions, addressing energy needs. It discusses the benefits, challenges, and potential applications of this hybrid approach, emphasizing the importance of avoiding voltage fluctuations to protect mission-critical electrical loads. The design of the solar UPS includes two main components: a solar panel converting solar energy into electrical energy and a specially designed inverter circuit converting it into alternating current. The study aims to achieve high efficiency and offer a successful alternative to conventional electrical UPSs in the market, catering to the growing demand for both solar power and UPS technologies.

Keywords: Solar UPS, Realiability, Sustainability, integration.

Abstract: The review covers a spectrum of energy sources, like solar power, wind power. It also delves into aspects of energy prediction such as forecasting energy demand predicting energy production and estimating energy consumption. The review carefully analyses the machine learning algorithms employed in these applications the data sources utilized and the performance metrics used to assess their effectiveness. This analysis provides insights, into the strengths and limitations of these approaches.

Keywords: sustainable energy prediction, Machine Learning (ML), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), ensemble learning, deep learning, energy forecasting.

Abstract: Globally, healthcare systems are integrating artificial intelligence (AI) more and more, with the potential to significantly improve patient care, clinical decision-making, and operational efficiency. This abstract examines how AI is revolutionizing healthcare, emphasizing its main uses and difficulties. Diagnostic imaging: Artificial intelligence (AI) algorithms improve the precision and speed of medical image analysis, assisting in the early identification and diagnosis of illnesses like cancer and heart problems. Personalized medicine: Using patient data, AI-powered predictive algorithms create customized treatment regimens that maximize results based on each patient's unique genetic, lifestyle, and medical history characteristics. AI technologies facilitate remote patient monitoring, real-time health tracking, and virtual consultations, hence increasing access to healthcare services and enhancing care continuity. Drug Development and Discovery: AI uses massive dataset analysis to speed up drug discovery.

Keywords: water conservation, urban settings, innovative strategies, water scarcity, comprehensive framework, sustainable water management practices.

Abstract: In recent times, the world has been experiencing an increase in medical cases due to the inappropriate disposal of hospital waste. Hazardous wastes in medical facilities are not properly managed, leading to the spread of various viruses. Medical waste, generated in healthcare centers such as hospitals, clinics, and laboratories, can contain chemicals like mercury and lead that leach into the soil and water, causing environmental pollution. This pollution poses health problems for people living in surrounding areas. Medical waste may also contain infectious or hazardous materials that risk human health and environmental safety. Hazardous waste in hospitals includes: Chemical Waste: Expired or unused chemicals, such as laboratory reagents and solvents, pose risks to human health and the environment if not properly managed. Pharmaceutical Waste: Expired, unused, or contaminated medications, including chemotherapy drugs, are toxic and harmful if not properly disposed of. Radioactive Waste: Materials containing radioactive isotopes, such as medical equipment used in radiation therapy or nuclear medicine, require careful handling. Infectious Waste: Waste contaminated with infectious agents, such as blood-soaked bandages, used needles, and cultures from laboratory experiments, must be carefully managed. Sharps Waste: Used needles, syringes, and other sharp objects can cause injury or transmit infection if not properly disposed of. Proper management and disposal of hazardous waste in hospitals are critical to protect the health and safety of patients, healthcare workers, and the environment. This involves segregating hazardous waste from non-hazardous waste, using designated containers, appropriately labeling containers, and ensuring safe storage and transportation to prevent contamination. Specialized treatment methods, such as incineration or autoclaving, may be used by hospitals to treat hazardous waste before disposal. To address these challenges, a modified method for sorting medical waste in dustbins has been proposed. Smart hospital waste management dustbins have been designed using various sensors for different purposes. The bins are color-coded (Red, Blue, Yellow, and Black) to indicate different types of waste. Key components include: Ultrasonic Sensors: Measure the distance of waste within the bin, working with a servo motor to control the lid's opening and closing. Camera Module: Attached to an Arduino UNO for waste image recognition and classification according to the bin color. Gas Sensor: Monitors gas levels within the bin, triggering an alert via a buzzer if the gas exceeds a predefined threshold, indicating the presence of hazardous fumes. Buzzer: Alerts when the bin is filled to capacity.GSM Module: Sends SMS alerts to frontline workers when bins are full or emitting foul odors, prompting immediate action.This IoT-enabled system ensures proper waste segregation, treatment, and disposal, enhancing safety for healthcare employees, patients, and the environment. Proper waste management mitigates health risks and environmental damage, underscoring the importance of adopting advanced technologies in hospital waste management.

Keywords: Arduino UNO, Ultrasonic Sensor, GSM Module, Image Recognition, Smart Waste Management, Medical Waste Disposal,IoT-Based Waste Management, Hazardous Waste Segregation, Environmental Safety, HealthCare Waste Management

Abstract: Customer churn is one of the subscription-based business critical tasks that a company needs to make a decision about revenue stream management and to take care of their customers from churning. This research work is an introduction to a machine-learning method for customer churn analysis using predictive models. The process starts with a vast customer transaction dataset, which needs to be transformed into churn labels. Next, the system utilizes several machine learning algorithms, including logistic regression, decision tree, random forest, support vector machines (SVM), and gradient boosting, to process the input data and design predictive models. Carrying out feature selection and feature construction is part of the process. Feature selection is a method used to reduce the input of the dataset that might conflict with the output. Feature construction will unfortunately be a million-dollar question. Accuracy, precision, recall, and F1 scores measure model performances. In addition, the ROC curve can be obtained for a designed model.The findings demonstrate how accurate and efficient the proposed method can be for a customer churn problem. An organization gets an early warning about a customer churn problem using this method. It will put a customer in the retention consideration set. In addition, a design model gives an organization a reason behind a customer churn. This analysis will help organizations understand the cause of Churn and decide what they will do before a customer leaves.

Keywords: Customer Churn Prediction, Machine Learning, Predictive Modeling.

Abstract: This paper explores how Reinforcement Learning (RL) can be a valuable tool for enhancing decision-making in autonomous driving systems when integrated with autonomous vehicle control. Stakeholders in the autonomous driving industry share a sense of both anticipation and necessity when it comes to incorporating RL into self-driving technologies. In this examination of RL applied to autonomous driving, we delve into the comparative analysis of various RL-driven applications within the context of autonomous vehicle control.

Keywords: Autonomous Driving, Reinforcement Learning, Self Driving Cars, Vehicle Control, Traffic Management, Traffic Optimization.

Abstract: The key to making any system intelligent is the internet of things. The requirements of the modern systems are met by using recent operating systems. Numerous platforms have been created for the Internet of Things. The majority of them, meanwhile, are designed for certain implementations and are unable to handle the present constraints of more modern systems. We will cover a broad overview of the Internet of Things, its working mechanism, resource constraints, node attributes, and mixed traffic communications in our research. We will also talk about newer technologies that make use of an Internet of things platform that has numerous uses. Current developments necessitate that modern gadgets be connected to the internet, which builds the modern Internet of things and improves user experience by ensuring a strong connection and efficient use of the devices belonging to the next generation. However, the increased connectedness of the Internet of Things has made it a target for attackers in recent times. We'll talk about common assaults, security risks, and modern Internet of things strategies.

Keywords: Internet of Things, Real-Time Systems

Abstract: Phishing is a fraud attempt in which a scammer acts as a trusted person or reality to gain sensitive information from an internet user. In this Methodical Literature check (SLR), different phishing discovery approaches, videlicet Lists Grounded, Visual Similarity, Heuristic, Machine Learning, and Deep Learning grounded ways, are studied and compared. For this purpose, several algorithms, data sets, and ways for phishing website discovery are revealed with the proposed exploration questions. A methodical Literature check was conducted on 80 scientific papers published in the last five times in exploration journals, conferences, leading shops, the thesis of experimenters, book chapters, and from high- rank websites. The work carried out in this study is an update in the former methodical literature checks with further focus on the rearmost trends in phishing discovery ways. This study enhances compendiums' understanding of different types of phishing website discovery ways, the data sets used, and the relative performance of algorithms used. Machine literacy ways have been applied the most, i.e., 57 as per studies, according to the SLR. In addition, the check revealed that while gathering the data sets, explorationers primarily penetrated two sources 53 studies penetrated the PhishTank website (53 for the phishing data set) and 29 studies used Alexa's website for downloading licit data sets. Also, as per the literature check, utmost studies used Machine literacy ways; 31 used Random Forest Classifier, which, as per different studies, achieved the loftiest Accuracy, 99.98, for detecting phishing websites.

Keywords: Phishing, URL, Hyperlinks, Machine Learning, Random Forest, K-means, SVM.

Abstract: Soil is the most diverse, nutrient-rich loose surface material that covers most of our land. Soil contains both organic and inorganic matter. The presence of soil is necessary to prevent direct leaching of the inorganic pollutants in the groundwater. Color, texture, structure, porosity, density, consistency, temperature, and air are the physical properties of soil. Suitability of soil for agriculture is determined by the physical properties. There are different properties for different soils. Soil is the source of the water and provide mechanical stability to the plants. There are various types of soil in the environment for example - loamy soil, sandy soil, chalk, peat, silt, and clay soil. Soil analysis refers to a set of various chemical processes which help us determine the available plant nutrients which are either in micronutrient or macronutrient form. In this study, various physiochemical parameters (pH, electrical conductivity, organic carbon, nitrogen, potassium, phosphorus) were analyzed. physio-chemical Parameters of soil are conducted in the study area based on various parameters are as pH, (6.91 - 8.56) electrical conductivity, (0.085 - 0.432) nitrogen, (100 - 200) potassium, (114 - 408) and phosphorus, (14 - 24) soil organic matter (0.72 - 0.98) contents in the study area. A soil analysis is used to determine the level of nutrients found in soil. As such, it can only be as accurate as the sample taken in a particular field. The results of a soil analysis provide the agricultural producer with an estimate of the number of fertilizer nutrients needed to supplement those in the soil. In modern agriculture, excess use of chemical fertilizers affects the pH, EC, Organic carbon, N, P, and K, which are within the permissible limit. and Electrical conductivity which is harmful to germination. Due to overdose of chemical fertilizers its affects soil fertility resulting to decreases crop yield production.

Keywords: Physico-chemical Analysis, soil Parameters, Soil health

Abstract: Nowadays lots of multistory buildings are constructed with floating columns for aesthetic point of view and for getting more space in parking areas for movement. However, such buildings are highly damaged during earthquakes in highly seismic zones as compared to normal buildings. In urban areas, multi-story buildings are constructed by providing floating columns on the ground floor for the various purposes which are stated above. The motive is to compare the response of RC frame buildings with and without floating columns under earthquake loading and under normal loading. The effect of earthquake forces on various building models for various parameters is proposed to be carried out with the help of response spectrum analysis. In this study, it was found that the story displacement, story drift, and story shear of a building without a floating column was more efficient than that of a building with a floating column. On comparing it has been concluded that the maximum story displacement obtained for Cases 1 & 15 with a minimum value of 11.158 mm & 14.8 mm respectively. Comparing the Story drift for all cases, Cases 1, 5, 7 & 15 are observed as most efficient. On analyzing story shear values, Cases 1, 5, and 10 are found to be optimum for both X & Z direction among all cases.

Keywords: Floating column, Story Drift, Base shear, Story Displacement.

Abstract: The Agriculture Portal is an innovative platform that improves crop yields by providing farmers with easy access to agricultural information, resources and tools. The portal offers a wide array of features such as weather predictions, crop planning tools and real time market prices. This technical paper describes the development and implementation of the Agriculture Portal, focusing on its features and functionality. The paper also discusses the benefits of the portal for farmers, including increased productivity, improved decision-making, and increased profitability. The portal is based on a robust technology platform that is scalable and adaptable to the needs of farmers of different sizes and geographical locations. It is designed to be user-friendly and accessible on multiple devices including mobile phones and tablets. Agriculture portals represent a major advancement in the use of technology in agriculture and have the potential to transform agriculture and increase crop yields around the world by giving farmers easy access to information and resources.

Keywords: Agriculture portal, Crop yield, Farmer, User friendly.

Abstract: The integration of artificial intelligence (AI) in the beverage industry represents a transformative approach to optimizing production, distribution, and consumer engagement. AI technologies, including machine learning, predictive analytics, and natural language processing, are being harnessed to enhance various facets of the industry. This paper explores the applications of AI in beverage production, such as quality control and inventory management, and its role in streamlining supply chains through predictive maintenance and demand forecasting. Additionally, the impact of AI on personalized marketing and customer service is examined, highlighting the potential for AI-driven chatbots and recommendation systems to revolutionize consumer interactions. The ethical considerations and challenges associated with the adoption of AI in the beverage sector are also discussed, providing a comprehensive overview of the current and future landscape of AI implementation in this industry. Through a detailed analysis, this study underscores the significant benefits AI can bring to the beverage industry, from improving operational efficiency to enhancing customer experiences.

Keywords: AI, Beverage

Abstract: Ensuring accurate blood classification is imperative prior to administering a transfer of blood from one individual to another during emergency scenarios. Currently,performing these assessments conducted conducting this task laboratory specialists, and when handling a large volume of tests, it becomes tedious and mayresult in errors attributable to humans. This paper proposes the replacement of manual labor in clinical laboratories for the identification of blood groups . The proposed system aims to develop an embedded system utilizing image processing algorithms to conduct blood tests based on blood typing systems. Through a review of various existing methods and their performance evaluation, this paper aims to assist researchers in their endeavors

Keywords: Antigen, Blood Samples, GPU, Histogram, LBP (nearby paired example),Nearest Neighbor Classifier, Image Processing, Pattern Matching.

Abstract: The functioning of a currency is essential for the economy of a country, and banknotes are a major component of the Indian economy. Counterfeiting currency is an attempt to imitate a real currency with the intention of deception. Most of the methods used to detect counterfeit currency are based on hardware or image processing techniques, which are less efficient and time- consuming. As technology advances, the methods used to counterfeit currency have become more sophisticated, and the circulation of such notes has a significant impact on the economy. Therefore, the detection of counterfeit notes is of paramount importance. There are numerous commercial methods for detecting fake notes, however, they are not accessible to the general public. People who acquire counterfeit currency are often victims, and there is usually no government policy to reimburse them for the counterfeit notes that are confiscated. To design an automated system, it is necessary to develop an efficient algorithm that can accurately predict whether the banknotes are genuine or forged, as counterfeit notes are designed with great accuracy.

Keywords: Banknote Authentication, Fake-notes, Skewness, Logistic regression , XG boost, Decision tree classifier, Pre- processing.

Abstract: This study examines the differences in e-learning infrastructure between federal and state tertiary institutions in Kebbi State, Nigeria. A structured questionnaire, distributed to 180 respondents across nine institutions, gathered data on the availability, accessibility and utilization of e-learning tools. SPSS was used for data analysis, employing simple frequency counts and a 4-point Likert scale to answer research questions. Results indicate that federal institutions have significantly better e-learning infrastructure compared to state institutions. Federal institutions reported higher availability and accessibility of internet services, digital resources and computers. They also had better-equipped virtual learning facilities and superior technical support. In contrast, state institutions showed lower and more inconsistent usage of e-learning tools among lecturers and students. Resource availability and ease of access were key factors influencing e-learning adoption. Positive perceptions of e-learning effectiveness were noted, but infrastructure limitations and funding constraints were major barriers. Recommendations for improvement included increased investment and faculty development programs. Independent samples t-tests confirmed a significant difference in the mean availability of e-learning infrastructure between federal and state institutions, with federal institutions having a clear advantage. This study underscores the need for enhanced e-learning infrastructure in state institutions to improve adoption and effectiveness.

Keywords: Availability, Accessibility, Usage, E-learning infrastructure, Tertiary institutions

Abstract: A huge step in the field of precision farming has been made with the creation of this soil moisture detection system, which enables farmers to maximize water use, decrease resource waste, and boost yields of crops. Additionally, it promotes environmentally friendly farming methods by lowering water use. The use of this sort of equipment is anticipated to increase agriculture's productivity and profitability while fostering sustainable management of resources. Soil moisture sensors, a data processing unit, and a user-friendly interface accessible through mobile or online platforms are key components of the system. Soil moisture sensors are carefully positioned across the field to collect data on soil moisture content at various depths.

Keywords: smart irrigation; Soil health; soil moisture sensor; machine learning; Soil properties; Data analytics; Crop management; Smart farming

Abstract: Electric vehicles (EVs) have been widely regarded as the most promising solutions to replace conventional integrated engine-based vehicles. The control system works by selecting the right energy source to supply voltage to the output load and also this control system can regulate the charging and discharge of the battery automatically based reservation algorithm. The voltage source consists of two energy, from the battery or other external sources. The control application or switch is control system of motor (ON and OFF) condition through a relay when the battery capacity has been widely applied as the power supply for EVs. Hence, for the owner, it is important to know all the information regarding battery operation like percentage charging and also the improper operations like motor control to operate a smooth and efficient operation. In this method, Battery Management System (BMS) will continuously monitor the key operational parameters such as voltage, current, and temperature of the battery and ensures its safe operation. Based on this data, it calculates the State of Charge and informs the owner of the vehicle by using an LCD on the output.

Keywords: Monitoring, Electric Vehicle.

Abstract: Reliable and discrete authentication techniques are essential for security surveillance systems that protect public and private spaces. The inherent limits of conventional identity methods, such passwords and ID cards, are driving demand for more resilient solutions. The study of human walking patterns via the lens of gait analysis has become a popular biometric technique in security. It is especially desirable for a variety of surveillance applications due to its nonintrusive design and capacity for continuous authentication. Even with obstacles such fluctuating walking circumstances and privacy issues, research is still being done to improve gait analysis's accuracy and dependability. Gait analysis is a particularly useful tool for improving safety and protection in a variety of settings as security demands rise. The history of security authentication is examined in this review study, which also emphasises the potential of gait analysis as a biometric security frontier.

Keywords: Segmentation, Erosion, Dilation, Silhouette, Feature Extraction, Gait Analysis

Abstract: A three years old Goat was presented to the Block Veterinary Dispensary, Srijangram with a history of haemogalactia for 4 days after parturition. Clinical examination revealed that all the vital parameters were within the normal limits. California mastitis test (CMT) was found to be negative. On the basis of history and clinical examination, the case was diagnosed to be of haemogalactia. The Goat was treated with Inj. Ceftriaxone @ 10 mg/kg BW IM for 5 days, Inj. Tranexamic acid @ 5 mg/kg BW, IV, SID along with adrenaline (intramammary), serratiopeptidase (PO) for 5 days. Improvement in condition was observed after three days of treatment and completely recovered after five days of treatment.

Keywords: adrenaline, CMT, goat, haemogalactia, tranexamic acid.

Abstract: The number of fatalities from breast cancer is rising dramatically every year. It is the most common kind of cancer overall and the leading cause of death for women globally. Any advancement in the identification and prognosis of cancer is crucial to a long and healthy life. Therefore, it's critical to have a high level of accuracy in cancer prognosis in order to update patient survival standards and treatment aspects. Machine learning approaches have shown to be a powerful method, have become a research hotspot, and may significantly contribute to the process of early detection and prediction of breast cancer. Using the Breast Cancer Wisconsin Diagnostic dataset, we ran five machine learning algorithms through this study: Support Vector Machine (SVM), Classification and Regression Tree (CART), Navi Bayes, and K-Nearest Neighbors (KNN). Once the results were in, we compared and evaluated the performance of each classifier. This study paper's primary goal is to identify the most efficient machine-learning algorithms in terms of confusion matrix, accuracy, and precision for the detection and prediction of breast cancer. The Support Vector Machine is shown to have attained the maximum accuracy of 97.2%, outperforming all other classifiers. All of the work is completed in the Anaconda environment using the Scikit-learn package and the Python programming language.

Abstract: Water is crucial for public health and environmental management. T his study looks into the prediction of water quality using machine learning algorithms based on different physical and chemical factors. We implemented several algorithms, including Gradient Boosting, Random Forest, and Support Vector Machines, to identify the most precise model. The Gradient Boosting model achieved the highest accuracy of 85%. This paper presents the methodology, results, and implications of using machine learning for water quality prediction, providing a scalable and efficient solution for real-time water quality assessment.

Keywords: Water quality, Machine Learning, Gradient Boosting, Prediction Model, Environment Monitoring

+91-7667918914 iarjset@gmail.com 0 Items International Advanced Research Journal in Science, Engineering and Technology A Monthly Peer-Reviewed Multidisciplinary Journal ISSN Online 2393-8021 ISSN Print 2394-1588 Since 2014 Home About About IARJSET Aims and Scope Editorial Board Editorial Policies Publication Ethics Publication Policies Indexing and Abstracting Citation Index License Information Authors How can I publish my paper? Instructions to Authors Benefits to Authors Why Publish in IARJSET Call for Papers Check my Paper status Publication Fee Details Publication Fee Mode FAQs Author Testimonials Reviewers Topics Peer Review Current Issue & Archives Indexing FAQ’s Contact Select Page Electronic Forensics-Based Fronesis Technique for Earlier Discovery of in progress Attacks by hackers Ranjitha N , Swetha CS Abstract Traditional methods for detecting cyber attacks rely on predefined databases of known signatures and machine learning models to identify abnormal behavior. However, the increasing sophistication and diversity of cyber threats highlight the limitations of these approaches. This paper introduces Fronesis, an innovative method for early detection of ongoing cyber attacks based on digital forensics. Fronesis integrates ontological reasoning with frameworks such as MITRE ATT&CK and the Cyber Kill Chain model, utilizing continuously gathered digital artifacts from monitored systems. By applying rule-based reasoning on the Fronesis cyber-attack detection ontology, the approach identifies adversarial techniques present in the collected data. These techniques are then correlated with tactics mapped to specific phases of the Cyber Kill Chain model, enabling the early detection of cyber attacks in progress. The effectiveness of Fronesis is illustrated through a practical scenario involving an email phishing attack.

Keywords: MITRE ATT&CK framework, the Cyber Kill Chain model Downloads: | DOI: 10.17148/IARJSET.2024.11725 How to Cite: [1] Ranjitha N , Swetha CS, "Electronic Forensics-Based Fronesis Technique for Earlier Discovery of in progress Attacks by hackers," International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2024.11725 Copy Citation Call for Papers Rapid Publication 24/7 April 2026 Submission: eMail paper now Notification: Immediate Publication: Immediately with eCertificates Frequency: Monthly Downloads Paper Format Copyright Form   Submit to iarjset@gmail.com or editor@iarjset.com   Submit My Paper Author CenterHow can I publish my paper? Publication Fee Why Publish in IARJSET Benefits to Authors Guidelines to Authors FAQs (Frequently Asked Questions) Author Testimonials IARJSET ManagementAims and Scope Call for Papers Editorial Board DOI and Crossref Publication Ethics Editorial Policies Publication Policies Subscription / Librarian Conference Special Issue Info ArchivesCurrent Issue & Archives Conference Special Issue Copyright © 2026 IARJSET This work is licensed under a Creative Commons Attribution 4.0 International License. Open chat

Abstract: This paper tackles the challenge of identifying diseases in cotton plants using deep-learning techniques. The aim of using convolutional neural networks (CNNs) is to categorize five photos of cotton leaves into groups, such as healthy and unhealthy. Implemented with Keras and TensorFlow frameworks, the paper offers a detailed workflow from data collection and pre-processing to model training and evaluation. The dataset includes images of cotton leaves, with data augmentation techniques enhancing the training process to guarantee precise categorization, the CNN architecture takes significant elements out of the pictures. Another strategy being investigated to boost performance with little data is transfer learning. Transfer learning is also explored to improve performance with limited data. Evaluation metrics like accuracy, precision, recall, and F1-score are used to assess the model. This project serves as both an educational resource and a practical tool for agricultural stakeholders, promoting early disease detection, better crop management, and improved yield through the application of AI in agriculture.

Keywords: Deep learning, Convolutional Neural Networks (CNNs), Image classification, Keras, TensorFlow, Data augmentation, Transfer learning

Abstract: Forecasting stock market prices remains a very major concern to economists, financial analysts, and data scientists for the past decades. This paper investigates the application of several machine learning algorithms for stock market price prediction and compares their performance. The algorithms used in this research are the Support Vector Regressor, Random Forest, K-nearest Neighbor, Logistic Regression, Decision Tree, Long Short-Term Memory Networks, Gated Recurrent Units, and a mixture of LSTM and GRU networks. These models are tested on some historical datasets of Reliance stock prices, which are subjected to extensive preprocessing, which includes dealing with missing values and feature engineering. The predictive accuracy of each model is taken as the mean. absolute error and root mean-squared error. In this respect, the paper provides the most in-depth comparison of predictive capabilities of these models available to date and offers potential empirical evidence to benefit researchers and practitioners in the area of financial forecasting.

Keywords: Stock Market Prediction, LSTM, Random Forest, Decision Tree, Financial. Forecasting, Machine Learning, Time. Series Forecasting, GRU, Logistic Regression, K-nearest Neighbor, Support Vector Regressor.

Abstract: Embryonic development is a highly regulated process driven by intricate molecular signals, cellular activities, and tissue formations. Understanding this process is fundamental for advancing fields such as regenerative medicine and developmental disorder research. Advanced imaging techniques, such as confocal and light sheet microscopy, have transformed our ability to observe these dynamic processes within developing embryos. However, the vast and complex data generated by these techniques pose significant challenges for analysis and interpretation. Cell Suite is a sophisticated software tool designed to address these challenges by enabling the segmentation, tracking, and visualization of cells and tissues in developing embryos. Its user-friendly interface and robust algorithms allow researchers to extract quantitative measurements and analyze spatial-temporal dynamics from 4D imaging data with remarkable precision and efficiency. A key feature of Cell Suite is its ability to segment individual cells or tissues within an embryo and track their movements and interactions over time. This functionality is crucial for studying dynamic cellular behaviors such as division, migration, and differentiation. By analyzing these datasets, researchers can identify critical factors and signaling pathways involved in tissue and organ formation.

Keywords: Embryonic development, Advanced imaging techniques, Cell Suite, Segmentation and tracking, Spatial-temporal dynamics

Abstract: Suicide is a serious global issue requiring timely interventions. Developing an accurate prediction system using available data can help identify at-risk individuals and provide timely support. This study analyzes suicide data to pinpoint key attributes contributing to suicide attempts, aiming to predict future attempts with high precision using machine learning techniques. We evaluated three algorithms-Logistic Regression, Random Forest, and Naïve Bayes-finding Random Forest to be the most accurate. The dataset was preprocessed and important features, such as age, gender, mental health history, and socio-economic status, were identified. Stratified k-fold cross-validation ensured robust model evaluation. Results indicate that ensemble methods like Random Forest significantly improve suicide attempt predictions, aiding mental health professionals in early intervention. Future research should incorporate diverse data sources, such as social media and electronic health records, while addressing ethical concerns about privacy and deployment.

Keywords: Suicide, prediction system, machine learning, Random Forest, Logistic Regression, Naïve Bayes, data analysis, mental health, intervention, ethical concerns.

Abstract: This study investigates the creation and deployment of a serverless chatbot for restaurant websites utilizing Google Dialogflow for natural language processing, FastAPI as the backend framework, and ngrok for secure and straightforward local development and testing. The paper emphasizes the advantages of serverless architecture, Dialogflow's natural language understanding capabilities, and its easy interaction with FastAPI for effective backend administration. Additionally, the integration of MySQL as a database solution is explored, highlighting its role in managing user data and order information efficiently. The study also covers how ngrok makes development easier by offering a secure tunnel that allows local servers to be accessed over the internet, allowing for real-time debugging and testing. By promptly and accurately responding to questions and delivering menu specifics, this solution seeks to improve customer experience and streamline the development process.

Keywords: Restaurant Chatbot, Google Dialogflow, Serverless Architecture, FastAPI, MySQL, Natural Language Processing (NLP), Ngrok, Secure tunnel.

Abstract: The increasing workload and pressure in the IT industry often lead to elevated stress levels among professionals, affecting their health and productivity. This research proposes a novel approach to detect stress in IT professionals using face recognition technology focusing on the forehead region. By analyzing images and incorporating additional inputs like body temperature, oxygen levels, and sleep hours, we employ logistic regression Artificial intelligence algorithms to predict stress levels. The proposed system aims to offer an efficient and non-intrusive method for early stress detection, facilitating timely interventions to improve employee well-being. The methodology involves preprocessing the images to enhance feature extraction, followed by the application of convolutional neural networks (CNN) to identify stress-related patterns. The system is trained to recognize these patterns and classify the stress levels accurately. To validate the effectiveness of the approach, the model's performance is evaluated using metrics such as accuracy, precision, recall, and F1 score, and compared with existing stress detection methods.

Keywords: Artificial intelligence, logistic regression, CNN, ROI algorithms.

Abstract: This project aims to develop a predictive maintenance system for aircraft engines using machine learning techniques. Leveraging historical maintenance records and real-time sensor data, the system will predict engine failures and maintenance requirements, optimizing maintenance schedules and reducing downtime. Key steps include data collection, preprocessing, feature engineering, model selection, training, and deployment. The project seeks to improve aircraft safety, operational efficiency, and cost-effectiveness by enabling proactive maintenance interventions based on predictive insights. Through continuous monitoring and updating, the system will adapt to evolving operational conditions, ensuring reliable performance and minimizing the risk of unexpected engine failures.

Keywords: Predictive maintenance, Aircraft engines, Machine learning, Engine failure prediction Real-time sensor data Maintenance schedules Operational efficiency, Proactive maintenance

Abstract: Fake job postings as a important threat in the electronic job market, exploiting job seekers and compromising sensitive information. This comparative study aims to discover various machine learning algorithms and practices to find and predict fake job posts. The research involves analyzing a dataset of job postings, identifying features that distinguish legitimate from fraudulent job ads, and evaluating the efficiency of different classification models. In the end, this study offers a solid answer for boosting the security of online job marketplaces by shedding light on how well systems like Conclusion Trees, Haphazard Forest, Support Vector Machine (SVM), and Neural Networks perform in identifying false job posts.

Keywords: • Fake job postings • Job fraud detection • Machine learning • Classification models • Online job market • Data analysis • Feature extraction • Model evaluation

Abstract: The prevalence of Disease recognition in rice leaves poses a significant challenge to agricultural productivity and food security globally. Traditional methods of disease recognition in rice leaves, which depend heavily on manual inspection and expert knowledge, are increasingly inadequate for modern agricultural needs. These methods are labor-intensive, time-consuming, and often prone to human error. This research aims to leverage the advancements in deep learning to develop an automated system for rice leaf disease identification. By employing convolutional neural networks (CNNs), DenseNet, and ResNet architectures, this study seeks to classify images of rice leaves into various disease categories accurately. The high performance of these models underscores their capability to capture intricate patterns and features essential for disease identification. In addition to accuracy. The system is designed to run on a local server, ensuring accessibility and reliability for farmers and agricultural experts. Key components include user authentication, image upload, preprocessing, disease classification, and result visualization. The results demonstrate the system's effectiveness in early disease detection, which can significantly improve crop management and yield. Future enhancements include integrating IoT devices, expanding to multiple crops, and developing a mobile application for greater accessibility.

Keywords: Rice leaves disease recognition, Deep Learning, Convolutional Neural Networks, Automated Disease Classification, Agricultural Technology, Image Processing, Local Server

Abstract: Detection and Prevention of Cyberbullying is a natural language processing task, which aims to detect cyberbullying content in tweets which contain text and this text also contains emojis, and also detect the cyberbullying content in images. This has become increasingly important in recent times due to increase in social media activity and as the users increase the misusing of the content also increases. So, the cyberbullying content also has increased a lot in the recent times. To solve this problem, we propose a machine learning model which is trained on various social media content which has been marked manually by annotators as cyberbullying content. We aim to detect cyberbullying content and achieve state of the art performance on a variety of benchmark datasets.

Abstract: Friendship inference in social networks has become a significant research area because of the proliferation of social media platforms and the valuable insights they offer. This study proposes a novel approach to infer friendships by exploiting multi-source information using a two-stage deep learning framework. The first stage several data sources, such as user interactions, profile information, and shared content, to generate comprehensive feature representations. The second stage employs a deep learning model to analyze these representations and predict friendship links with high accuracy. Results from experiments show that our approach outperforms traditional approaches, offering improved precision and recall in friendship inference. This research offers a strong basics for enhancing social network analysis and may leveraged for various applications like recommendation systems, targeted advertising, and community detection.

Abstract: Falls are important concern among elderly individuals, often leading to severe injuries or fatalities. Prompt detection of fall can significantly mitigate these risks by enabling timely medical intervention. This paper presents an advanced fall detect system that utilizes convolutional nueral network (CNNs) and multi-sensor fusion to accurately detect falls in real-time. The system operates on a local server, capturing video data via a web camera and integrating continuous wave radar data to enhance detection accuracy. Through extensive testing, the system demonstrated high accuracy, reliability, and user-friendliness, making it a valuable tool for improving the safety and well-being of elderly individuals.

Keywords: ● Fall Detection ● Elderly Safety ● Convolutional Nueral Networks (CNNs) ● Multi-Sensor Fusion ● Real-Time Monitoring ● Machine Learning ● Continuous Wave Radar

Abstract: In recent years, emotion-based music recommendation systems have gained considerable attention due to their potential to enhance user experiences by personalizing music selection based on the user's emotional condition. This project aims to develop an innovative Emotion Echoes system utilizing advanced deep learning and computer vision techniques. The system employs a convolutional neural network (CNN) to detect seven types of emotions from facial expressions captured through a webcam. By analyzing sequences of video frames in real-time, the system accurately interprets the user's emotional mood and recommends music that aligns with the detected emotion. The Emotion Echoes system is designed to offer a seamless and immersive experience by continuously analyzing a sequence of 50 consecutive frames to capture the user's emotional dynamics. The system's architecture includes capturing real-time video frames, preprocessing them for optimal attribute extraction, and feeding them into the trained CNN model for sentiment detection.

Keywords: ● Emotion-Based Music Recommendation ● Deep Learning ● Computer Vision ● Convolutional Neural Network (CNN) ● Real-Time Processing ● Facial Emotion Recognition ● Personalized Music Experience

Abstract: There is a growing need to have effective surveillance systems that can identify and flag alarming behaviour instantly in the current era. In this study, we propose a new method of recognizing suspicious activities of video data using deep learning algorithms. We employed the DCSASS Dataset which contained videos from thirteen categories of suspicious activity, like abuse, arson, assault, robbery and so on. A mixed architecture involving both ResNet50 and I3D was used because it could handle the temporal and spatial complexities that come with video data. The model is trained to recognize subtle cues concerning suspicious behaviour as it exhibits remarkable training accuracy. By subjecting our model to rigorous evaluation on a separate validation set, it shows encouraging results at about 85% accuracy. To improve the performance of the model further, we consider various strategies such as data augmentation, fine-tuning of hyper parameters as well as ensemble methods. We also try to make our models interpretable by employing techniques such as class activation mapping for better understanding of decision making process.

Keywords: DCSASS Dataset, Deep learning algorithms, ResNet50, I3D.

Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by challenges in interaction, communication, and repetitive behaviors. Early and accurate diagnosis is crucial for effective intervention. This paper presents a novel ASD Detection System using deep learning techniques, specifically CNNs, to analyze brain MR images and classify them as either ASD or typical control. The system achieves high accuracy, providing a reliable tool for early ASD diagnosis. Comprehensive testing ensures robustness, performance, and security, making it suitable for clinical use. The system's deployment on a local server enhances data privacy and accessibility for healthcare professionals.

Keywords: Autism Spectrum Disorder, Deep Learning, Convolutional Neural Networks, Medical Imaging, Early Diagnosis, Neurodevelopmental Disorders, Machine Learning, Brain MR Images.

Abstract: The inspiration is gathered for this project to relieve the burden of multiple diseases and shift the negatives into proactive healthcare strategies. Leaving in the edge of evolved technologies utilizing the advantages of health system that may help many people to reduce cost and increase their health profiles. The project's scope is extensive, focusing on predicting the likelihood of various diseases in individuals based on patients unique health profiles. At the heart of this initiative are machine learning models, specifically assemblage technique such as Random Forests and Gradient Boosting, which utilize diverse data sources to provide precise and personalized risk assessments.

Abstract: Finding brain tumors and improving patient care are the driving forces behind this research. Tumors are unpredictable cell enlargements in a person's brain, and the phrase "cancer," for refers to benign tumors. Brain tumors can also be detected by DNA testing, spine poke, retinal arteryogram, and A positron Field Spectroscopy. MRI scan pictures are acquired for this examination in order to analyze the illness state. The goals of this investigation are to:i) recognize abnormalities in images; and ii) section the tumor region. The segmental mask can be used to evaluate the tumor's density, which will aid in treatment. The algorithm for deep learning is used to look for anomalies in MRI pictures. The tumor region is divided using complex thresholding. The average density pf the impacted area is indicated by the proportion of cancerous pixels.

Keywords: CT or MRI scans, Malignant tumours.

Abstract: In smart grids, electricity theft is still a major problem that causes large financial losses and inefficiencies in operations. Because of their complexity and size, traditional theft detection techniques like manual inspections and rule-based algorithms are unable to handle the complexity and size of contemporary smart grids. In order to detect electricity theft, this research explores the use of deep neural networks (DNNs), which are able to evaluate massive datasets and recognize complex patterns linked to fraudulent activity. We provide a thorough process that covers data preparation, feature extraction, model architecture design, training, and evaluation for creating a DNN-based theft detection system. The suggested approach outperforms traditional techniques, giving utilities a reliable tool to improve theft detection and preserve grid integrity.

Abstract: There is a perception that Bitcoin is utilized for illicit purposes like dark web trading, money laundering, and purchasing ransomware linked to smart city systems. While it cannot identify illicit transactions, blockchain technology stops them. One of the most important methods for spotting possible fraud is anomaly detection. Sadly, the heuristic and signature-based approaches that underpinned earlier detection techniques were insufficient to fully explore the complexity of anomaly detection. Machine learning (ML) is a potential tool for anomaly detection because it can be taught on vast datasets of known malware samples to find patterns and features of events. The goal of research is to develop a fraud and security threat detection model that is more effective than current approaches. Consequently, ensemble learning can be used to identify anomalies in Bitcoin by combining multiple ML classifiers. The data balancing method in the suggested model is called ADASYN-TL (Adaptive Synthetic + Tomek Link). Hyperparameter tuning involves the use of Bayesian optimization, grid search, and random search techniques. The model's performance is significantly impacted by the hyperparameters. We combined K-Nearest Neighbors, Random Forest, Decision Tree, and Naive Bayes to create the stacking model, which we used for classification. Shapley Additive ex-Planation (SHAP) was utilized to analyze and interpret the stacking model's predictions. Additionally, the model investigates how well various classifiers perform using accuracy, F1-score, and Area Under Curve-Receiver Operating. In the end, it chooses the best model based on characteristics (AUC-ROC), precision, recall, False Positive Rate (FPR), and execution time. The suggested model aids in the creation of efficient fraud detection models that overcome the shortcomings of the current algorithms. We achieved the highest F1-score of 97%, precision of 96%, recall of 98%, accuracy of 97%, AUC-ROC of 99%, and FPR of 3% with our stacking model, which combines the prediction of multiple classifiers.

Abstract: The early detection of fetal brain abnormalities is critical for prompt intervention and better management of neonatal health. This project leverages the You Only Look Once (YOLO) algorithm, a state-of-the-art object detection technique, to achieve accurate and efficient detection of fetal brain anomalies from ultrasound images. Traditional methods of fetal brain analysis are often time-consuming and require specialized expertise, leading to potential delays in diagnosis. The YOLO algorithm, with its real-time processing capabilities, offers a promising solution by detecting multiple abnormalities in a single forward pass through the network.In this project, a comprehensive dataset of fetal ultrasound images is curated, encompassing a wide range of brain anomalies. The YOLO model is trained and fine-tuned to recognize specific patterns indicative of various conditions such as ventriculomegaly, holoprosencephaly, and others. The model's performance is evaluated based on metrics such as precision, recall, and mean Average Precision (mAP), ensuring robustness and reliability.

Keywords: YOLO algorithm , Mean Average Precision (mAP) Object detection, Dataset, Training, Fine-tuning, Ultrasound images

Abstract: With the ease with which images may be altered using advanced software, digital image fraud has become a widespread problem in the modern digital era. To maintain the integrity and authenticity of digital photographs, the detection of such forgeries is essential in a number of sectors, including journalism, forensics, and legal investigations. The intricacy and subtlety of contemporary forgeries can provide a challenge to conventional image forgery detection techniques. In this study, we provide a deep learning-based method for efficiently identifying digital image forgeries. Using convolutional neural networks (CNNs), our approach automatically learns and extracts information from photos, making it possible to identify many kinds of forgeries, including copy-move, slicing, and image retouching to improve its accuracy and robusteness. suggested system is trained on a variety of forged and actual images. Our deep learning-based methodology works better than conventional methods, as evidenced by experimental results that show lower false positive rates and higher detection rates. By offering a potent tool for the automatic detection of image forgeries, this research advances the field of digital image forensics and ensures the authenticity and dependability of digital visual content.

Keywords: CNN, Forgery, ELA

Abstract: The rapid proliferation of cloud-based services has transformed data storage, management, and sharing methods. Cloud computing offers significant advantages such as scalability, cost efficiency, and accessibility, making it a preferred choice for businesses and individuals. However, these benefits come with critical challenges, particularly in ensuring the security and accessibility of data stored in public cloud environments. As organizations increasingly rely on cloud services to manage their data, the need for robust data security mechanisms has become paramount. The project introduces a novel approach to enhancing data security and accessibility in public cloud environments. It addresses the challenge of efficiently delegating decryption rights for subsets of encrypted data without requiring large decryption key sizes. The proposed system leverages a keyaggregate cryptosystem, termed DATA SHARING which integrates Triple DES (Data Encryption Standard) as the underlying encryption algorithm. The system aims to provide a comprehensive solution that combines robust encryption standards with efficient key management, ensuring data confidentiality and integrity while facilitating secure data sharing and access control.

Abstract: Reducing fraud and maintaining the integrity of the insurance sector depend heavily on the detection and evaluation of dishonesty in insurance claims through machine learning. This study makes use of cutting-edge machine learning methods to identify and evaluate insurance claim fraud. The system's objective is to effectively discriminate between genuine and fraudulent claims by evaluating past data, seeing trends, and putting prediction models into practice. The suggested system is made to be accurate, scalable, and able to learn continuously, all of which will increase its efficacy over time. This study showcases the system's potential to improve fraud detection in the insurance industry by outlining its design, methodology, and implementation details.

Abstract: Unmanned Aerial Vehicles (UAVs), colloquially referred to as drones, have witnessed exponential growth in their usage across diverse domains, ranging from agriculture and infrastructure inspection to surveillance and cinematography. This surge in popularity has been facilitated by advancements in drone technology, making them more accessible, affordable, and versatile. However, along with their myriad benefits, drones also pose challenges, particularly in areas such as privacy, security, and safety. As such, the development of robust drone detection systems becomes imperative to address these concerns and ensure responsible drone usage.

Keywords: DCSASS Dataset, Deep learning algorithms, ResNet50, I3D.

Abstract: The objective of analyzing Sales Insights data within Power BI is to achieve a thorough comprehension of sales performance by examining the data through the lens of Power BI's extensive analytical and graphical capabilities. This initiative seeks to identify critical sales metrics and patterns, offering valuable insights for strategic planning. The process employs a systematic methodology to ensure a thorough collection, examination, cleansing, transformation, and visualization of data, leading to the identification of meaningful indicators. Marketing is experiencing significant growth, and there's a challenge in accurately tracking sales. This necessitates precise information on the company's sales figures to facilitate informed decision-making. The Power BI Quick Insights feature, with its array of sophisticated analytics algorithms, is a cutting-edge tool for this purpose. By analyzing sales data, it reveals the products customers are buying and the reasons behind their purchasing behaviors. This understanding can guide strategic choices and enhance the overall sales efficiency. The project aims to showcase how to leverage Power BI for sales analytics data, utilizing SQL queries for data cleansing and DAX query language, and its effectiveness in delivering dashboards to users. Thus, I developed a dashboard to monitor trends and business performance, including market fluctuations, identify top-selling products, regional sales variations, and product market performance. The dashboard presents a comprehensive data visualization that aids in making business decisions. The project's goal is to provide businesses with a deeper insight into their sales operations, enabling them to refine their strategies and boost sales effectiveness.

Keywords: Data Analytics, Business Intelligence, Sales, Visualization.

Abstract: This study presents the application of machine learning techniques to the prediction of real estate/house prices on two real datasets that were obtained from Kaggle, one from Melbourne developed by Anthony Pino and the other from Boston created by D. Harrison and D.L. Rubinfeld. There is a dearth of literature regarding machine learning research on housing price prediction in India. This work attempts to develop this prediction engine for user use in the real world by reviewing the use of current machine learning methods on two radically dissimilar datasets. The results show that altering the algorithms can have a significant impact on accuracy. Furthermore, a subpar dataset may have a detrimental impact on the predictions. It also offers enough evidence to determine which algorithm is most appropriate for this task.

Keywords: Machine Learning, Real Estate, House Price, Price Prediction, Algorithm.

Abstract: Our work combines real observation data with synthetic data in exoplanet detection by deep learning. We collate datasets from space-based telescopes, like Kepler and TESS, from ground-based observatories for light curves, and spectral data. To further enrich the dataset, we produce synthetic data simulating a collection of astrophysical scenarios. Convolutional and recurrent neural networks enable model robustness and generalization. Accuracy and reliability of exoplanet detection will increase with training using the total dataset. Such integration will not only extend the scope of the training dataset to probe a far greater variety of astrophysical conditions but also speed up the discovery and characterization of exoplanets.

Abstract: The data from the tap-on shrewd cards is a useful tool for analyzing passenger boarding patterns and forecasting imminent foldaway petition. On the other hand, positive instances-that is, embarkment at a certain bus break at a detailed time-are rare in comparison to undesirable occurrences when looking at the smart-card archives (or illustrations) by boarding stops and by time of day. It has been publicized that machine learning processes used to forecast hourly lodging records from a certain site are far less accurate when the data is imbalanced. This study tackles the problem of data imbalance in smart-card data before using it to forecast demand for bus boarding. In order to augment a copied keeping fit dataset with added evenly distributed traveling and non-traveling cases, we suggest using subterranean procreative adversarial nets (Deep-GAN) to create dummy traveling instances. A deep neural network (DNN) is then trained on the copied dataset to predict which illustrations from a given stop would travel and which will not during a specified period opening. The findings demonstrate that resolving the data disproportion question can greatly enhance the prediction model's functionality and more closely match the real profile of ridership. When comparing the Deep-GAN's performance to that of other conventional resampling techniques, it becomes clear that the suggested approach is capable of creating artificial training datasets with greater diversity and similarity, and thus, higher prediction power.The study emphasizes the importance of enhancing figures superiority and typical presentation for individual travel behavior analysis and travel behavior prediction. It also offers helpful recommendations.

Keywords: Predictive models, Machine learning,Data models,Training, Generative adversarial networks, Ensemble learning, Biological system modeling

Abstract: Electronic Health Record EHR might be a system that gathers digital health information from patients and exchanges it via the cloud with other providers of healthcare services. Given that EHRs include a large amount of sensitive and important patient data, the framework must ensure accuracy and capacity in responses and astuteness . In interim , because of the rise of IoT, more low performance terminals are sent for accepting and uploading quiet info to the server, which increments the computational and communication burden of the EHR frameworks . The unquestionable database VDB , where a client outsources his huge database to a cloud server and queries it whenever he wants certain data; this is suggested as a useful updatable cloud capacity demonstrate for resource constrained clients . To move forward productivity, the majority of current VDB designs use verification upgrade and reuse strategies to show that the question is correct. It ignores the real-time proof era, resulting in an overhead where the customer must carry out extra preparation work, such as reviewing blueprints to verify capacity judgement. We provide a freely verifiable shared updatable EHR database plot in this work that supports privacy-preserving and bunch judgment checking with least client communication fetched . We adjust the existing utilitarian commitment FC plot for the VDB plan and develop a concrete FC beneath the computational l BDHE suspicion . In expansion , the utilize of an productive verifier local denial bunch signature plot makes our conspire back energetic bunch part operations, and gives pleasant highlights , such as traceability and non frameability.

Keywords: VDB, FC, EHR FRAMEWORK

Abstract: This paper embarks upon an exhaustive exploration of the intricate historical narrative and progressive evolution of artificial intelligence (AI), meticulously tracing its lineage from nascent conceptual constructs to its myriad manifestations in the contemporary contexts. Through a rigorous analysis od critical milestones, seminal achievements and the contributions of emblematic pioneers, the document elucidates the defining moments that have sculpted the trajectory of AI. The study traverses the conceptual landscape from the foundational epochs of theoretical paradigms and symbolic computation strategies to the realms of machine learning, deep learning and neural architectures. These paradigmatic shifts have engendered profound transformations in a plethora of fields, including but not limited to robotics, natural language processing, computer vision, healthcare, and autonomous systems. By juxtaposing historical perspectives with modern advancements, this scholarly endeavour aims to provide a comprehensive understanding of the vector AI development, its societal implications and the perpetual pursuit of machines endowed with intelligence.

Keywords: Pioneer, paradigm , autonomous , Natural Language Processing and epoch.

Abstract: The availability of public auditing facilitates efficient integrity checks for data stored on cloud servers. This paper reexamines public auditing for encrypted data, emphasizing the management of data dynamics such as modifications, insertions, and deletions. Initially, we identify the component in current auditing methods that most significantly limits data dynamics in terms of cost. Subsequently, we introduce a groundbreaking public auditing technique that delivers significantly faster data dynamics compared to previous methods. Our auditing challenge-response protocol significantly reduces the computational burden on the third-party auditor (TPA), enhancing the speed of verification for auditing results. Effectiveness and security analyses demonstrate that the suggested method minimizes computational costs while ensuring data integrity and privacy against an untrusted cloud.

Keywords: Public Auditing, Cloud Services, Data Mobility, Encrypted Data, Data Dynamics, Third-Party Auditor (TPA)

Abstract: The healthcare industry is increasingly leveraging artificial intelligence (AI) to enhance patient outcomes, particularly in Intensive Care Units (ICUs) where timely and accurate predictions can save lives.[1] Personalized Federated Learning (PFL) offers a novel approach to this challenge by enabling collaborative learning across multiple centers while preserving patient privacy.[2] This research focuses on developing a PFL framework tailored for multi-center ICU prediction. The framework aims to integrate diverse patient data from various hospitals to predict critical outcomes, such as patient deterioration and mortality, without sharing sensitive data.[3] By personalizing models to local data characteristics while benefiting from the collective knowledge of all participating centers, the PFL approach is expected to improve prediction accuracy and patient care in ICUs.[4][5]

Keywords: Personalized Federated Learning, In-Hospital Mortality Prediction, Multi-Center ICU, Machine Learning, Healthcare Analytics, Federated Learning, ICU Patient Data, Mortality Risk Assessment

Abstract: Nowadays, credit cards are the most common method of payment both offline and online purchases due to advancements in electronic commerce and communication technology. Thusly, the gamble of misrepresentation related with these exchanges has expanded. Each year, fraudulent credit card activities lead to significant losses for businesses finances and individuals, with fraudsters continually devising new schemes. Detecting credit card theft remains a difficult task for researchers because of the complexity and creativity of fraudsters. The imbalance in datasets used for fraud detection algorithms further complicates this task. Therefore, There are pressing need for efficient and effective methods to identify fraudulent credit card transactions. This paper makes a new approach to tackle this issue: the Gradient Boosting Classifier, a machine learning tool. Experimental results, demonstrating 100% training accuracy and 91% test accuracy, indicate that Other machine learning methods are inferior to the proposed method techniques.

Keywords: innovative approach, Gradient Boosting, machine learning

Abstract: In e-learning, tracking and classification of on-screen endeavors are fundamental for identifying learner engagement and optimizing content delivery. However, traditional methods often compromise user privacy by centralizing sensitive data. In classify to improve privacy preservation, this research suggests a novel method for tracking and classifying on-screen activities using Federated Learning (FL). Our method allows data to remain decentralized on users' devices while leveraging aggregated models for analysis. We evaluate the performance of the FL-based system against traditional centralized methods, highlighting improvements in both privacy and accuracy.

Abstract: Technology regarding shaded printing has grown lately the rate of notes being copied for fake cash on a big scale. Despite the rise in popularity of electronic financial transactions and the recent decline in utilizing paper money, banknotes continue to be widely used because of their dependability and simplicity of operation. Printing was only available to print business entities years ago, but as of late anyone can use an average laser printer to print money paper with the highest accuracy achievable. In light of this, phony currency has grown to hold the position of bigger issue than real money. Phoney money is a significant issue for India, which has lamented concerns like abomination and hidden money. This problem is addressed by proposing a deep learning-based method to identify the fake Indian rupee. The Utilizing MATLAB, a tool has been locate the fake cash. As a result, the legitimacy of the Indian currency note will be determined. Counterfeiting is the practise of making copies of legitimate currency. Hence, the Indian government forbids the use of fraudulent currency. In India, the only authority in charge of printing money is the RBI. As soon as they've been accepted and released onto the market, counterfeit banknotes present an annual the difficulty for the RBI. The printing and scanning companies have seen major advances in technology, which have led to an upsurge in counterfeiting issue. Therefore, counterfeit money affects the economy and devalues legitimate currency. The need to spot counterfeit money is consequently greatest. The vast majority of older systems relied on hardware and techniques for image processing. Finding phoney currency requires more work and is less efficient using these methods. To ensure that tackle the aforementioned issue, which involves we suggested the Identification of Fake Indian Currency Using Xception Architecture. By evaluating the images of the currency, our system can recognize counterfeit money.

Keywords: MAATLAB, Machine learning, counterfeiting, Quillbot

Abstract: The integration of voice recognition technology in digital whiteboards represents a significant advancement in interactive learning and collaborative environments. This research explores the development and implementation of a voice-integrated digital whiteboard system, designed to enhance user interaction, accessibility, and overall usability. Traditional digital whiteboards, while effective in many ways, often require manual operation, which can be limiting for users with physical disabilities or those seeking more seamless interaction. Our proposed system leverages cutting-edge voice recognition technology to allow users to perform a variety of actions through simple voice commands, such as drawing, erasing, and navigating through the whiteboard. This paper details the design and implementation process, including system architecture, user interface design, and integration of voice commands. The system was developed using React.js for the front- end and Python for backend processing, incorporating voice recognition libraries to facilitate the voice command functionality. Comprehensive testing was conducted to evaluate the system's performance, usability, and accuracy of voice commands. Results indicate that the voice-integrated digital whiteboard significantly improves user experience and accessibility compared to traditional systems. The research concludes with a discussion of the implications of this technology in educational and professional settings, highlighting potential areas for future enhancement and research. This work demonstrates the potential of voice integration to transform interactive digital tools, making them more inclusive and efficient.

Keywords: Voice recognition technology, System architecture, User interface design, Voice commands, Usability

Abstract: This project tries to take the existing methods of patient administrative data security to another level by securing such data through the use of advanced steganographic techniques of data incorporation. The following report also contains a fully working the system's implementation providing for better management with enhanced security and more access to data in health care facilities through Python application and libraries. The principal facets data generation is one of this system's functions., well- known as data gen. py, total administration of the patient files at the clinic patient File management. txt, Steganography application-secret pixel. py files and the main application which is being referred to as 'app'. py. For encryption it uses AES while for hash, it uses SHA- 256; hence, the security aspect is done quite well.

Abstract: This concept which is of Fingerprint door locker is related to the security issues in the day today life, the physical key can be made as duplicate in very cheap cost and the key can lost somewhere or the key can steal, to overcome these issues we can use biometric security gadgets and try improvise the security much more because it can never be stolen it cannot be lost and the stealing chance of duplication are very low to break the security. Here we will use fingerprint for biometric verification as it is one such thing which is unique to every individual.

Keywords: Biometric, Arduino, Sensor, Identification, Locking system.

Abstract: Humanity's presence has been aided by innovation in terms of personal happiness. We are always striving to create something new and unique. We have machines to assist us in our lives and make us pretty complete in the financial field, the up-and-comer receives confirmations/reinforcement prior to endorsement of the credit sum. The framework's decision to support or reject an application is based on the verified information provided by the up-and-comer. There are always a large number of people seeking for credit in the financial sector, but the bank's reserves are limited. Using a few classes-work calculations, the proper expectation would be quite beneficial in this circumstance.A relapsing model, an arbitrary timberland classifier, a support vector machine classifier, and so on. The success or failure of a bank is determined by the amount of credits, or whether the client or client is returning the advance. Credit recovery is the most important aspect of the financial sector. In the financial sector, the improvement cycle plays a key role. Using credible data from up-and-comers, an AI model based on distinct order computations was created. The main goal of this work is to predict whether another candidate will allow the advancement by using AI models based on the real informational index.

Keywords: Machine learning, Data, Loan, Training, Testing, Prediction

Abstract: RTAs are a major global health issue, resulting in significant injury, death, and economic costs. The goal of this research is to develop a prediction model to assess the risk associated with various accident scenarios by investigating the numerous elements that impact the severity of RTAs. The study analyzes data from police-reported traffic accidents over a five-year period, considering variables such as driver demographics, vehicle type, environmental conditions, and road characteristics. The findings indicate that accident severity is strongly affected by factors like the age and gender of the driver, time of day, weather conditions, and the type of road. Accidents involving young drivers, male drivers, and those occurring at night or in bad weather are more severe. Additionally, crashes on RR and those involving heavy vehicles tend to be more serious. To determine the probability of a serious injury or death in a rear-end collision, a predictive model employing ML and LR approaches was created. This model, which showed high accuracy, can help policymakers and traffic safety officials identify high-risk situations and implement specific preventive measures. The study highlights the need for comprehensive road safety strategies that include enforcement, education, and engineering improvements.

Keywords: RTAs-Road Traffic Accidents, ML-Machine Learning, LR-Logistic Regression, RR-Rural Roads.

Abstract: In recent years, the prevalence of stress has become a significant public health concern, influencing both physical and mental well-being. This study examines the possibilities of applying techniques for ML to detect human stress based on sleeping habits. By leveraging data on sleep patterns, such as duration, quality, interruptions, and variability, we aim to develop a forecasting model that can precisely determine stress levels. We collected sleep data from a diverse group of participants using wearable devices and self-reported surveys over several weeks. A number of ML techniques, such as SVM, RF, and NNs, to create predictive models. The models' performance was assessed utilizing measures such as F1-score, recall, accuracy, and precision. Our findings demonstrate that Random Forests and Neural Networks outperform other algorithms in detecting stress from sleep data.

Keywords: SVM- Support Vector Machine, RF-Random Forest, NN-Neural Network, ML-Machine Learning

Abstract: Predicting used car prices is a complex task that involves considering several key factors, such as the year, make, model, mileage, condition, and market trends. Accurate prediction models are essential for dealerships, sellers, and consumers to make informed decisions. This study aims to explore how artificial intelligence (AI) and neural networks can be utilized to forecast the prices of secondhand cars. Our goal is to develop a practical model for used car valuation using machine learning techniques. Our methodology includes data collection, preprocessing, feature selection, and training using advanced neural network architectures. The model's accuracy will be evaluated using metrics such as mean absolute error (MAE) and root mean square error (RMSE). Ultimately, the aim is to showcase the capabilities of AI in this domain.

Keywords: Artificial Intelligence, Neural Networks, Machine Learning, Old Car Price Forecasting Predictive Modeling, Data Preprocessing Feature Engineering, Mean Absolute Error, Automotive Market.

Abstract: SecureTransferX is an innovative system for transferring and storing files, specifically designed to meet the high security requirements of contemporary businesses. In a time characterized by increasing cyber dangers and data breaches, organizations need strong platforms to protect their confidential information. SecureTransferX provides a wide range of advanced cybersecurity features to guarantee the privacy, accuracy, and accessibility of data both during transportation and storage. The main characteristics of SecureTransferX consist of encryption from end to end, authentication with multiple factors, precise access controls, and continuous monitoring of potential threats. These technologies collaborate to strengthen the processes of transfer and storage, reducing the risks linked to unauthorized entry, data interception, and harmful assaults. Additionally, SecureTransferX is crafted with scalability and adaptability in consideration, catering to the varied requirements of businesses in diverse sectors. Whether transmitting large files among distant teams or securely archiving confidential documents, SecureTransferX offers a smooth and user-friendly experience. Through the utilization of cutting-edge encryption techniques and adherence to the finest practices in the industry, SecureTransferX enables organizations to exchange and store data confidently, improving their cybersecurity stance and protecting against possible threats. By utilizing SecureTransferX, companies can streamline their activities, promote collaboration, and maintain the trust of their stakeholders in an increasingly digital environment.

Keywords: Encryption, Cybersecurity, Data Protection, Scalability, Secure File Transfer

Abstract: Efficient cloud resource management is vital for optimizing system performance and ensuring balanced workloads across servers. Effective load balancing not only improves resource utilization but also enhances throughput and reduces response times, which are critical for achieving high availability and fault tolerance in cloud environments. Traditional job scheduling strategies often struggle to prioritize tasks with the same priority and to allocate jobs to virtual machines optimally, leading to performance inefficiencies. Despite extensive research, many existing scheduling algorithms fail to provide optimal solutions consistently. This study proposes a Bio-Inspired Cat Swarm Optimization (CSO) approach integrated with a modified K-means clustering technique to address the shortcomings of current load balancing methods. The CSO method mimics the natural behavior of cats to search for optimal solutions, while the modified K-means clustering ensures efficient grouping and prioritization of tasks. The new priority-based scheduling algorithm introduced in this research aims to eliminate the drawbacks of existing systems, thereby enhancing the overall performance and efficiency of cloud computing. This approach not only improves resource allocation but also ensures a more balanced and resilient cloud infrastructure, capable of meeting the increasing demands of users and applications.

Keywords: Cloud computing, load balancing, resource management, Cat Swarm Optimization, K-means clustering, job scheduling, high availability, performance optimization.

Abstract: Cyber-physical system security for electric distribution systems is critical. In direct switching attacks, often coordinated, attackers seek to toggle remote-controlled switches in the distribution network. Due to the typically radial operation, certain configurations may lead to outages and/or voltage violations. Existing optimization methods that model the interactions between the attacker and the power system operator (defender) assume knowledge of the attacker's parameters. This reduces their usability. Furthermore, the trend with coordinated cyberattack detection has been the use of centralized mechanisms, correlating data from dispersed security systems. This can be prone to single point failures. In this, novel mathematical models are presented for the attacker and the defender. The models do not assume any knowledge of the attacker's parameters by the defender. Instead, a machine learning (ML) technique implemented by a multi-agent system correlates detected attacks in a decentralized manner, predicting the targets of the attacker

Keywords: Cybrt attack, Cyber attack Status,Cyber attack Ratio, prediction of cyber attack

Abstract: The paper explains the end-to-end master data management framework provided by Informatica based on its sophisticated capabilities in the line of data discovery, modeling, cleansing, enrichment, matching, merging, relationship management, and governance. The MDM solutions from Informatica, through MDM Multi-Domain Edition and Customer360 SaaS, are equipped with utilities that permit profiling and analysis of source data, construction of flexible and custom data models, and high-quality data through sophisticated cleansing and enrichment. It uses advanced matching engines, including machine learning-based ones, for the correct identification and merging of duplicates; the Trust Framework ensures the creation of reliable golden records. The platform can also maintain complex relationships and hierarchies of entities, thus providing end-to-end governance of data through automated workflows. This consolidates all procedures and tools for businesses to ensure high-quality and uniform master data across all systems and applications.

Keywords: Data Profiling, Data Cleansing, Data Matching, Data Governance.

Abstract: Monitoring environmental conditions in storage facilities, especially for crops like ragi and wheat, is crucial for maintaining their quality and safety. Traditionally, manual methods for tracking temperature, humidity, air quality, and fire risks are labor- intensive and prone to errors. Our prototype offers a modern, automated solution using an ESP32 microcontroller integrated with various sensors. This system ensures reliable and continuous monitoring, with data logged to ThingSpeak and alerts sent via Pushbullet for immediate response, providing a cost-effective and efficient approach to managing storage environments.

Keywords: Environmental monitoring, ESP32, temperature and humidity, air quality, fire detection, automated alerts, data logging, cost-effective.

Abstract: This project develops an ECG monitoring system using an ESP32 microcontroller and an ECG sensor for continuous heart rate tracking. The system transmits real-time data to ThingSpeak for visualization and sends SMS alerts to a designated guardian if an abnormal heart rate is detected. Designed to enhance patient safety and monitoring efficiency, it is particularly beneficial for individuals with chronic heart conditions, elderly patients, and those in post-operative care.

Keywords: Continuous heart rate monitoring, Real-time data visualization on ThingSpeak ,SMS alerts for abnormal heart rates, Enhanced patient safety, Integration of IoT technologies

Abstract: India, with its burgeoning population and rapidly developing economy, faces significant challenges in managing its natural fuel resources. The efficient utilization of natural fuels like coal, oil, and natural gas is crucial for sustainable development. This study aims to predict natural fuel consumption using advanced machine learning techniques, aiding policymakers and industry leaders in making informed decisions. The project involves collecting historical data on natural fuel consumption in India, preprocessing this data, and employing linear regression and K-Means clustering algorithms to predict future consumption and identify consumption patterns. This research is significant as it addresses the critical issue of energy management in India. By accurately predicting future fuel consumption and understanding consumption patterns this study can guide strategic planning and policy formulation, contributing to efficient resource allocation, energy security, and sustainable economic growth.

Abstract: In order to automate the cleaning of wall- and ceiling-mounted fans, this project proposes a novel fan cleaning machine. Conventional fan cleaning techniques can be dangerous, labor-intensive, and time-consuming, especially in high or difficult-to-reach areas. The suggested device provides an effective, user-friendly solution to these problems. The revolving brush system and movable arm mechanism of the fan cleaning machine allow it to accommodate different fan shapes and sizes. The brushes are made to remove dirt and dust off fan blades in a gentle yet efficient manner, protecting them from injury and guaranteeing a deep clean. A suction system on the machine collects loosened particles, reducing the amount of dust that spreads while it is in use.

Keywords: Arduino, Fan Cleaning, Brushes

Abstract: Railway accidents in India have been a significant concern, impacting lives, infrastructure, and the economy. This research paper aims to analyze railway accident data in India using Python to uncover patterns, trends, and potential causes. By leveraging data analytics techniques, we can provide insights that may help in reducing the frequency and severity of such incidents. The study uses a comprehensive dataset of railway accidents in India, employing Python libraries for data cleaning, analysis, and visualization. The findings highlight key factors contributing to railway accidents and suggest measures for improving railway safety.

Abstract: The smart medicine box is a microcontroller-based device designed to address medication non-adherence. It not only dispenses medicines at prescribed schedules but also incorporates a basic health monitoring system. The system sends SMS notifications to users once their medicine has been dispensed. The proposed medicine box helps the patient to take the right medicine at the right time along with an SMS which will help the patient to take the medicine. The basic ideology is integrating the principle of Alarm clock.

Keywords: microcontroller, Health monitoring, Sensor, alarm clock, SMS notification

Abstract: In this study, we present a novel approach for recognizing bird species using Fast Fourier Transform (FFT) analysis of audio spectra. Traditional bird recognition methods often rely on complex feature extraction techniques and machine learning algorithms. Our method simplifies this process by leveraging the FFT to convert audio signals into frequency domain representations, which are then analyzed to identify distinct spectral patterns associated with different bird species. We employ FFT to transform recorded bird songs into frequency spectra, which are then used to generate a comprehensive audio fingerprint for each species. This approach enables us to capture the unique frequency characteristics and temporal variations of bird calls with high precision. By comparing these fingerprints with a pre-established database of known bird calls, we are able to classify and recognize bird species with high accuracy. Our system is tested across various environments and recording conditions, demonstrating robustness and reliability. The results indicate that FFT-based audio spectrum analysis is a powerful tool for avian acoustic monitoring and can be integrated into real-time bird recognition applications. This method not only streamlines the recognition process but also enhances the scalability and accessibility of avian monitoring systems, making it a valuable contribution to ornithology and bioacoustics research.

Keywords: Fast Fourier Transform (FFT), audio spectrum analysis, bird recognition, acoustic monitoring, avian bioacoustics.

Abstract: The aim of this project is to create an intelligent spraying robot that will decrease pesticide use and human health damage, allowing farmers to be protected and labour intensity can be reduced. The robot will have full route planning and navigation systems, as well as driving control, spraying mechanism and system construction and obstacle avoidance with multi-sensor module integration. The spray robot will be designed, including spraying and sensor integration simulations and analyses. It is used not only to track motion and monitor orientation, but also to compensate for path errors in order to achieve good stability and reliability. Meanwhile, the spraying system will be improved to eliminate leaks and prevent repeated spraying, with automatic sprays varying according to the target. This project proposes a pesticide spraying system which will help farmers in field of agriculture.

Keywords: DC Motor, Arduino UNO, Bluetooth Module, Pesticide sprayer, Android App.

Abstract: This paper gives a brief idea about the historical background about the development of bridges. Bridges are the foundation of a country's transport network but they are expensive to build and maintain. So, care should be taken for the bridges. For that purpose, sensors are used. The idea of controlling different parameters through proper functioning, monitoring and analysis of data is effective for preventing the bridge from damages. This project predominantly focuses about monitoring and evaluation of bridge condition through various sensors used. Advancement in sensor technology have brought the automated real-time bridge health monitoring system

Keywords: Arduino Uno, Servo motor, Smart Bridge, Automation, Sensors, User Interface

Abstract: This paper presents a study on a GPS-based vehicle location monitoring system with geo-fencing capabilities. The system provides high-security message against their ward's vehicle movement and issues alerts to users based on location boundaries using Internet of Things (IoT) technology. The system can easily monitor and track a ward's vehicle's location and issue alerts when the vehicle exits the geo-fenced area. The system has two main components: hardware and software. The hardware includes an Arduino nano, NodeMCU and GPS module. The software uses Google Maps and an IoT platform. The parent can monitor the vehicle via mobile phone. Registered phone number alerts are sent to the parent when the vehicle exits or enters the geo-fenced area. The prototype system was tested by moving the vehicle around the geo-fenced area. Results showed correct location tracking of the vehicle and phone number notifications upon exiting or entering boundaries.

Keywords: GPS location monitoring, geo- fencing, internet of things, vehicle tracking

Abstract: In today's ubiquitous IT environment, even non-living objects interact with one another and intelligently respond to changing circumstances. The Internet of Things (IoT) is a technology that recognizes and conceptualizes the essence of computer. Fluid intake is important to prevent dehydration and reduce recurrent kidney stones. There has been a trend in recent years to develop tools to monitor fluid intake using "smart" productions such as smart bottles. The article provides a short overview on IoT-enabled water bottles. The quality of water is influenced by a number of factors. The smart water bottle uses input sensors to continuously evaluate temperature, water level, pH level in real time. This method is beneficial to health-conscious people and may also be very useful in the health care industry where additional caution is required in all areas.

Keywords: Health Care, IoT sensors, Water bottle

Abstract: The Coin-Based Mobile Charger System is an innovative solution for public mobile charging, allowing users to charge their devices by inserting coins. This literature survey provides an overview of existing research and developments in coin-based mobile charging systems, focusing on their design, implementation, and security features. The survey covers various aspects, including coin detection mechanisms, solar tracking systems, and user interface designs. It also discusses the benefits and limitations of these systems, as well as their potential applications in rural and urban areas. The survey aims to provide a comprehensive understanding of the current state of coin-based mobile charger systems, identifying areas for future research and development. By exploring the existing literature, this survey contributes to the advancement of secure, efficient, and user-friendly public mobile charging solutions.

Keywords: Mobile charging, coin-operated system, portable charger, user convenience, public spaces,, security measures.

Abstract: This research explores the transition from traditional fan to manual and automatic electronically sweeping fan. This electronic control has revolutionized fan operation, convenience, energy efficiency, and functionality. This paper examines the technological advancements enabling electronic fan control for traditional fans and smart phone integration. By comparing traditional methods with electronic control system, this abstract highlights the evolution and benefits of electronically sweeping fan, paving the way for innovations in household appliances.

Keywords: electical, fan,speed,

Abstract: The dual-axis solar tracker represents a significant advancement in solar energy technology, designed to optimize the solar energy capture by dynamically adjusting the position of photovoltaic (PV) panels. This system utilizes two degrees of freedom: azimuthal (horizontal) and elevational (vertical) adjustments, allowing the solar panels to follow the sun's trajectory across the sky. By aligning the panels perpendicular to the sun's rays throughout the day, the tracker can increase energy absorption by up to 25-45% compared to fixed installations. This technology is particularly advantageous for applications requiring high energy yield and space efficiency, such as in residential solar power systems and large-scale solar farms. However, the complexity and cost of dual-axis trackers can be a consideration, as they involve more sophisticated mechanisms and maintenance compared to single-axis or fixed systems.

Keywords: Microcontroller, Solar Energy Systems, Tracking Mechanism, Energy Efficiency, Sun Tracking System

Abstract: The integration of biometric technologies into voting systems represents a significant advancement in ensuring electoral integrity and enhancing voter authentication. This paper explores the design and implementation of an electronic voting machine (EVM) that leverages fingerprint recognition for secure and efficient voter identification. The proposed system incorporates a fingerprint scanner to authenticate voter identity, reducing the risk of fraud and errors associated with traditional voting methods. Key features of the EVM include real-time fingerprint matching, an encrypted data storage mechanism, and a user-friendly interface to streamline the voting process. The system's robustness is evaluated through simulated voting scenarios and real-world testing, demonstrating its capability to enhance security, increase voter confidence, and improve overall election administration. This approach not only addresses challenges related to voter fraud and identity verification but also represents a step forward in modernizing electoral processes through biometric innovation.

Keywords: Electronic Voting Machine, Fingerprint Recognition, Biometric Authentication

Abstract: Transmission line is the most important part of the power system. Transmission lines a principal amount of power. The requirement of power and its allegiance has grown up exponentially over the modern era, and the major role of a transmission line is to transmit electric power from the source area to the distribution network. In essentially, fault analysis is a very focusing issue in power system engineering to clear fault in short time and re-establish power system as quickly as possible on very minimum interruption. The power theft detection which aims to detect any theft related to electricity. Electrical energy is very important for everyday life. The objective of this project is to design a system to avoid the theft. This model reduces the manual manipulation work and theft control. We must first properly understand the working of different parts that is to be combined together. The technology which we are going to use in our project and the implementation of this system will save a large amount of electricity.

Keywords: Transmission line, distribution network, fault analysis, theft control.

Abstract: An element generating electric energy by vibration when an impact is applied, as can be described a piezoelectric sensors device. Presently, these piezoelectric sensors devices are used to power station equipment and LED lamps on bridges, where they are installed at the floor around ticket gates and bridge decks. However, one disadvantage of these piezoelectric sensors devices is that the generated electricity is too low because of little present current. Experimentally, the developed power generating shoes have been evaluated for their validity under various types of piezoelectric sensors devices, shoes and secondary batteries. Currently, it is found out that only up to 1.5% mobile phones can be charged which is indeed very low. So, we take piezoelectric sensors and after placing them in the soles of shoes, we run or walk. The energy produced by the sensors passes through bridge rectifier and gets converted to DC. The DC is stored in rechargeable battery which in turn charges the phone. To increase energy production, shoe designs should be improved and charge/discharge circuits created for them. Every day we all walk around going from one place to another. When we walk, we move forward by pushing the ground backward with our feet. Our project aims at utilizing this energy to generate electricity thus providing us with an opportunity to utilize wasted energy in earlier days hence bringing forth a 'smart shoe' as a step towards a modernized future.

Keywords: Piezoelectric sensors, rechargeable battery, smart shoes, energy saving, phone charging

Abstract: The Bidirectional Visitor Counter System is an innovative solution for accurately tracking the number of visitors entering and exiting a premises. Utilizing advanced sensors and algorithms, this system provides real-time data on visitor traffic, enabling businesses and organizations to optimize their operations, improve customer experience, and enhance security. The system's bidirectional capability ensures accurate counting in both directions, eliminating errors and providing reliable data. With its user-friendly interface and remote monitoring capabilities, this system is ideal for various applications, including retail, hospitality, and public venues. By providing actionable insights into visitor behavior, the Bidirectional Visitor Counter System helps organizations make data-driven decisions to drive growth and success.

Keywords: Bidirectional Visitor Counter, Visitors, Entry, Exit, IR sensor, Arduino, LED, OLED

Abstract: This project explores the design and development of a geometric shape drawing robot, leveraging the capabilities of stepper and servo motors for precise movement and control. The objective of the project is to create an educational tool that can draw various geometric shapes, demonstrating principles of robotics, mechanics, and programming. The project involves designing the mechanical structure, selecting appropriate hardware components, and developing software to control the robot's movements

Keywords: Geometric,Shapes,Arduino Nano, Stepper Motor, Servo Motor,Chassis, Stepper bracket, Pencollor, Servo holder, ULN2003 driver,O rings, Ball bearings.

Abstract: Skinput represents a groundbreaking technology leveraging. The human body can transmit sounds, which allows our skin to work like a touchscreen. This innovative method lets us use our arms and hands as interactive surfaces by detecting unique, low-frequency sounds when we tap different areas. It's a highly useful way to input commands and interact with devices, turning our skin into a natural interface. Researchers clarify that alterations in bone density, mass, and size, coupled with the filtering effects caused by joints and soft tissues, result in distinct acoustic properties across different areas of the skin. The software correlates sound frequencies with specific skin locations, enabling the system to determine which skin area the user has pressed. Subsequently, the prototype system employs wireless technology, such as Bluetooth, to transmit commands to the controlled device (e.g., iPod, phone, or computer).

Keywords: Bio-Acoustic, Buttons, Acoustic Detector, Body Interaction, Pico Projector, Armband Prototype, Bluetooth.

Abstract: This collection of studies explores advancements in drone technology and its applications across various domains. The first study introduces a novel algorithm for generating aerobatic trajectories for VTOL fixed-wing aircraft using differential flatness, enhancing maneuverability and computational efficiency. Another study focuses on drone detection through ISAR imaging with a millimeter-wave MIMO radar, employing a backprojection algorithm to achieve high-resolution images and improved object distinction. The development of a hybrid VTOL-UAV for surveillance applications is detailed in a third study, which highlights design, testing, and performance evaluations. The Node and Edge Drone Surveillance Problem (NEDSP) is addressed in another paper, optimizing surveillance routes and battery management using mixed-integer linear programming. RF-UAVNet, an advanced CNN for RF-based drone surveillance systems, is introduced, demonstrating high accuracy and efficiency in detection and classification. The security of IoD communications is enhanced through an identity-based proxy signcryption scheme, simplifying key management while ensuring confidentiality and authenticity. A real-time homomorphic authenticated encryption scheme is proposed to secure drone communications, balancing privacy and operational efficiency. The application of Transformer-based models for Named Entity Recognition in drone flight logs is explored to support forensic investigations by improving data extraction accuracy. Finally, a data-driven simulator using a Genetic Algorithm optimizes the positioning of aerial ambulance drones for emergency response, potentially transforming emergency medical services with improved response times. Together, these studies contribute significantly to the advancement of drone technology, addressing challenges in trajectory planning, detection, security, and emergency response.

Keywords: Aerial Ambulance Drones, Out-of-Hospital Cardiac Arrests, Genetic Algorithm, Emergency Response, Simulation, Optimized Deployment, Medical Services

Abstract: With growing, car parking increases with the number of car users. With the increased use of smartphones and their applications, users prefer mobile phone-based solutions. This paper proposes the Smart Parking System that depends on Arduino parts, Android applications, and based on IoT. This gave the client the ability to check available parking spaces and reserve a parking spot. IR sensors are utilized to know if a car park space is allowed. Its area data are transmitted using the WI-FI module to the server and are recovered by the mobile application which offers many options attractively and with no cost to users and lets the user check reservation details. With IoT technology, the smart parking system can be connected wirelessly to easily track available locations

Keywords: Internet of Things, Cloud Computing, Smart Parking, Smart City, Mobile Application.

Abstract: Breast cancer is a prevalent and life-threatening disease affecting millions of women globally. Early and accurate diagnosis is crucial for successful treatment and improved patient outcomes. In recent years, machine learning has emerged as a powerful tool in the field of medical imaging and diagnostics, offering potential advancements in breast cancer detection and classification. Several machine learning algorithms, including support vector machines (SVM), artificial neural networks (ANN), random forests, and convolutional neural networks (CNN), are employed to build predictive models based on the extracted features. The models are trained and evaluated using a comprehensive dataset comprising a diverse range of breast images, annotated by experienced radiologists.

Keywords: Breast Cancer, convolutional neural networks (CNNs)

Abstract: Steganography, the ancient practice of concealing messages within other messages or media to avoid detection, has evolved significantly with advancements in technology. This paper explores the social and ethical implications of steganography, particularly in the digital age. Historically, steganography has been used for covert communication, from ancient Greece to World War II. In modern times, it has found applications in digital media, including images, audio files, and even software, raising concerns among governments and law enforcement agencies. The main ethical issue is to balance personal privacy and national security. While steganography can protect personal as well as sensitive information from being accessed illegally, malicious entities such as terrorists can also exploit it by trying to communicate undetected. This dual-use nature has led to debates on whether its use should be regulated or restricted. The paper also discusses the technical aspects of steganography, including various methods and tools used to embed and extract hidden information. Furthermore, it examines the potential consequences of misusing steganographic techniques, and the challenges faced by authorities in detecting and also preventing such misuse. Through a detailed analysis of historical and contemporary examples, the paper highlights the ongoing discussion on the benefits of steganography for personal privacy and the risks it poses to public safety. A case study on financial institution's client details is considered for the detailed analysis. The procedure follows a nuanced approach to regulation that considers both the ethical implications and practical challenges associated with steganography, advocating for continued research and development in detection/prevention techniques.

Keywords: Steganography, Ancient practice, Concealing messages, Covert communication, Digital age, Digital media, Personal privacy, Malicious entities, Embedding, Dual-use nature, Public safety, Nuanced regulation.

Abstract: Our project's major goal is to protect marine life without causing pollution. It is a very straightforward but crucial idea. Oil rises on top of water because water has a higher density than oil. This feature of an oil separator is based on how oil and water interact. The viscosity difference idea underlies the majority of this endeavor . Because oil has a higher viscosity than water, it flows over the aluminium discover a much slower rate than water does while the project is being worked on. Because of this, separating oil from water is simple. The four metal discs in this project are connected to a motor shaft to speed up the separation of oil from water. The engine is powered.

Abstract: This paper presents the design and implementation of an elevator model utilizing ARM CORTEX M3 microcontroller and pulley mechanism. The system aims to provide efficient and cost effective system for multi floor elevators. The ARM CORTEX M3 is known for its high performance and low power consumption. The pulley mechanism is employed to achieve smooth and vertical operation of the elevator car. A program was written in arm assembly and dumped to the arm microcontroller. And a stepper motor is used for operating the elevator.

Keywords: Arm cortex based elevator, arm assembly, stepper motor.

Abstract: This project presents the design and implementation of a single cycle RISC-V RV32I processor on FPGA using Xilinx ISE Design Suite. RISC-V is an open standard instruction set architecture that provides flexibility, scalability and privilege from proprietary constraints, making it an excellent choice for educational purposes. The processor is designed using Verilog HDL, includes essential components such as the instruction fetch, decode, execute, memory access and write-back stages. The entire design is synthesized and implemented on a Spartan-6 FPGA board. This project demonstrates the feasibility and effectiveness of implementing a single cycle RISC-V processor on FPGA, providing valuable insights into processor design and hardware implementation.

Keywords: RISC-V single cycle processor design, RV32I Instruction Set, Spartan 6 FPGA, Xilinx ISE Design Suite.

Abstract: Air pollution poses a significant threat to the ecosystems. Accurate prediction of pollutant levels is essential for informed decision-making and effective conservation policies. This paper explores the application of linear regression as a predictive tool to estimate air pollutant levels, emphasizing its utility in environmental management. By leveraging historical data and identifying key influencing factors, linear regression can provide transparent, interpretable predictions that aid in setting realistic norms and conservation goals. The study utilizes the "Air Quality Index - New Delhi" dataset to illustrate the application of linear regression in forecasting air quality, demonstrating its potential in proactive environmental monitoring and policy-making.

Keywords: Air Pollution, Linear Regression, Predictive Analysis, Air Quality Index (AQI).

Abstract: This paper presents the design and implementation of an integrated multifunctional system using an Arduino microcontroller. The system integrates load cell, gas sensor, buzzer, OLED display, 12V DC fan, servo motor for a complete solution for environmental monitoring and responsive operation The main goal is to create a system that more work for real-time data acquisition, processing and appropriate response action capabilities does so. The load cell is used to measure loads, providing critical data for applications that require precise load control. The gas sensor is designed to detect the presence of hazardous gases, keeping the environment safe. Data from these sensors are sent to the Arduino, which processes the information and triggers the necessary responses. When a certain limit is exceeded, the system activates a buzzer to alert users to potential hazards. Real-time data from the sensors are also displayed on the OLED screen, giving users an immediate visual picture of the monitored parameters. In addition to power monitoring, the system has a 12V DC fan and a servo motor, both controlled by an Arduino. A 12V DC fan is used for ventilation, and automatically activates when the gas sensor detects harmful gases, thus helping to reduce potential hazards The servo motor is used for controlling machinery, such as air conditioners or other control devices based on sensor data. This combination ensures a robust response to the changing environment. Overall, this Arduino-based system exhibits a robust environmental monitoring and automation system. The modular design allows for easy expansion and customization, making it suitable for a wide range of applications. The paper details the design, components, and operational performance of the system, and provides insights into design considerations and practical implementation challenges The results show the real-time effectiveness of the system research and practice in practice, and emphasizes the potential for widespread application across sectors.

Keywords: Arduino microcontroller, Environmental monitoring, Load cell, Gas sensor, Real-time data acquisition, Responsive actuation, Automation, Safety monitoring.

Abstract: The Contactless Switch Using Arduino is designed to enhance convenience and hygiene in controlling electrical devices by utilizing gesture detection technology. The system employs an APDS-9960 sensor connected to an Arduino for detecting hand gestures, which then trigger a relay to switch devices on or off without physical contact. This report details the system's design, working principles, advantages, applications, results, and future scope, providing a comprehensive overview of its functionality and potential benefits in various environments.

Abstract: Technologies and services geared towards smart vehicles and Intelligent Transportation Systems (ITS) continue to revolutionize many aspects of human life. This paper provides a comprehensive overview of the latest techniques and progress in Automatic Number Plate Recognition (ANPR) systems, offering a comprehensive performance comparison of various real-time tested and simulated algorithms, including those involving computer vision (CV). ANPR technology can detect and recognize vehicles by their number plates using recognition techniques. Even with the best algorithms, successful ANPR system deployment may require additional hardware to maximize accuracy Performance can be undermined by various factors, including the condition of the number plate, nonstandardized formats, complex scenes, camera quality and mount position, tolerance to distortion, motion blur, contrast issues, reflections, processing and memory limitations, environmental conditions, indoor/outdoor or day/night shots, software tools, and other hardware-based constraints.

Keywords: automatic number plate recognition, image processing, computer vision, machine learning, vehicle identification, neural networks, intelligent transportation system, smart vehicle technologies, object detection and tracking, recognition

Abstract: Traditional Library -Digital resources have increased the efficiency of managing a library; however, books are still impossible to find in physical libraries. This paper presents the design of a new smart library system that uses Light Emitting Diodes (LED) for accurate book tracking and positioning Touch Listener Circuits. The system is supported by a network of LED-based markers tiling the library, assisting users in real-time navigation accurately. An individual LED beacon is attached to each book, allowing it to communicate with a central control unit that can locate where the e-book resides. The system can be operated with a mobile application or interactive kiosks, wherein owners just get visual and directional cues to find their books faster. By significantly reducing the time it takes for a user to find an item within a library, this LED-based approach is not only improving navigation through physical collections but also making libraries easier and more efficient places to work.

Abstract: Rechargeable batteries in modern applications like electric vehicles and renewable energy storage systems are critically dependent on Battery Management Systems (BMS) to operate properly as well as make them long-lasting. This paper discusses the implementation of a BMS using an Arduino, which is practically feasible being one of the inexpensive and reprogrammable microcontroller platforms. The battery management system is designed to monitor a 3p (3.7V) lithium-ion battery pack, tracking the state of charge and slowly balancing cells that have drifted beyond sensible limits between factory-calibrated values. It is designed to perform many key functions that include monitoring the battery parameters such as voltage and State of Charge (SoC), and protection against abnormal conditions such as over-charging and over-discharging for increased performance from the battery pack. To better manage all of these tasks, an Arduino-based BMS with little cost and just making it easier to customize. In this study, we described the development and implementation of an Arduino-based BMS. The battery pack status is monitored continuously in real-time using a Voltage sensor. Voltage sensors track the voltage levels of cells. Finally, the Arduino processes this data and applies algorithms to calculate the State of Charge (SoC), and based on these values it gives us immediate actions that need to be taken so as we can maintain our battery safe in working conditions So, we say that the design and construction of a Battery Management System is an easy and economical way to take care of safety, reliability & long-life cycle for high voltage rechargeable batteries. The paper offers a complete walkthrough to ensure that every component of the system is built and written properly, as well as showing off its top-level functionality benefits. This makes the Arduino-based BMS a significant stepping stone in battery tech and its use cases across an ever-changing-energy focus landscape.

Keywords: Battery Management System (BMS), State of Charge (SoC), Cell Balancing.

Abstract: Biometric technology, encompassing methods like fingerprint, facial ID, iris scan, and voice recognition, has revolutionized security and identification across sectors, offering unprecedented accuracy and convenience. It promises enhanced security and streamlined processes in fields such as law enforcement, banking, and personal device security. However, it also raises significant ethical and social concerns. The integration of biometrics systems has undeniably improved security, helping combat fraud and enhance public safety by securing borders and identifying criminals. Yet, the centralization and storage of biometric system data in vast databases present attractive targets for cybercriminals. Unlike passwords, biometric traits are immutable, making data breaches particularly concerning. Privacy issues are critical, as biometric data involves capturing highly personal and immutable characteristics, leading to potential privacy violations if mishandled. Unauthorized access or misuse of such data leads to invasive surveillance and tracking, necessitating stringent privacy regulations. Additionally, biometric systems can exhibit biases based on race, gender, and other demographic factors, resulting in unfair treatment and discrimination, and exacerbating social inequalities. Accessibility concerns must also be addressed to ensure these systems do not exclude individuals with disabilities. Establishing comprehensive legal frameworks and ethical guidelines is crucial to mitigate these challenges, including stringent data protection measures, transparency, and accountability to ensure equitable performance across diverse populations and safeguard individual rights.

Keywords: Biometrics, Privacy, Security, Ethical Concerns, Data Protection, Facial Recognition, Fingerprint, Iris Scan, Voice Recognition, Personal Data, Identity Verification, Public Safety, Societal Impact.

Abstract: This paper describes a smart cart robot that can move and avoid obstacles on its own. The robot is built using an ultrasonic sensor to detect obstacles, DC motors for movement, a Bluetooth module for wireless control, and a motor driver to manage the motors. An Arduino UNO board is used to process all the information and control the robot, while the chassis and wheels form the robot's body. The Arduino IDE is used for programming the robot. The ultrasonic sensor helps the robot "see" and avoid obstacles, while the Bluetooth module allows users to control it remotely. This smart cart robot can be used in various applications like automated shopping carts or warehouse automation, showing how different hardware and software components can work together to create intelligent machines.

Keywords: Autonomous Navigation, Obstacle Detection, Path Planning, Distance Avoidance, Ultrasonic Sensing Real-time Data.

Abstract: Residential and industrial power systems are essential in the modern world, but traditional solutions often end up being expensive and cumbersome to manage. Given below is a project that shows how to monitor and balance power using Arduino for managing electrical load. The push buttons-based interface provides quick command and parameter input for real-time monitoring, and control of the system. A voltage regulator and current sensors measure the power that is consumed, with data being read by an Arduino Small Computer System Interface (SCSI) which displays it on a LCD. This flexible and cost-effective system achieves balanced power distribution, prevents overloads, and maximizes energy utilization with the ultimate objective of improving efficiency and availability in many types of applications.

Keywords: Arduino Nano, Energy Monitoring, Current Transformer, LCD Display, Step-Down Transformer

Abstract: Effective management of exam halls and seating arrangements is crucial for ensuring a smooth and fair examination process. This abstract discusses the key aspects involved in the allocation of seats in exam halls, focusing on principles such as fairness, transparency, and efficiency. It highlights various methods used to allocate seats, including manual, semi-automated, and fully automated systems, and examines their advantages and disadvantages. The abstract also addresses common challenges faced in the seating allotment process, such as avoiding cheating, ensuring comfort, and accommodating special needs students. Furthermore, it presents case studies and examples from institutions that have successfully implemented innovative seating allotment strategies, demonstrating the impact on exam integrity and student satisfaction. Finally, the abstract underscores the importance of continuous improvement and the adoption of best practices to enhance the overall examination experience.

Abstract: This paper presents the development and implementation of a car cockpit automation system utilizing face recognition technology. The primary goal of this project is to enhance user comfort and convenience by automating the adjustment of car settings, including rearview mirrors, steering wheel position, and seat height, based on the identified user. The system integrates a face recognition algorithm implemented in Python using the OpenCV library, with adjustments controlled by an Arduino through serial communication.

Keywords: Car Cockpit, Automation Face Recognition, User Personalization, Automated Adjustments Comfort and Convenience Serial Communication, Vehicle Settings Image Processing System Integration.

Abstract: The objective of the study was to assess the impact of Pradhan Mantri Ujjwala Yojana (PMMY) on promoting gender equality in the rural part of Kandhar taluka in Nanded district of Maharashtra. The present study was conducted in the rural part of Kandhar Taluka during the year 2023-24. Gender equality means that the rights, responsibilities and opportunities of individuals do not depend on whether they are male or female or from rural or urban environments. Women deserve to live with dignity, safety and security. Pradhan Mantri Ujjwala Yojana (PMMY) was launched in May 2016 by the Ministry of Petroleum and Natural Gas with the objective of ensuring availability of clean cooking fuels like LPG to rural and underprivileged households, who are otherwise using traditional cooking fuels. These were firewood, cow dung cakes, and coal etc. The scheme aims to empower women and protect their health by providing them free LPG cylinders. Survey was conducted from 150 beneficiaries of PMUY. Gender equality variables for the study includes Increase the Access to education, Increase the opportunity in decision-making, Increase the Participation in social events, Increase the Participation in social events, Freedom from social bounding , Self-respect, Political participation .The data was collected through demographic information and interview schedule from women residing in the rural sector in Kandhar Taluka . Descriptive statistics (By using SPSS) was used for data processing. In this study , results found that there is positive Impact of Pradhan Mantri Ujjwala Yojana (PMUY)on gender equality by increasing opportunity in decision-making, Participation in social events ,Participation in social events, Freedom from social bounding , Self-respect and Political participation

Keywords: PMUY, Rural, Gender, Equity, decision making.

Abstract: Recent developments in artificial intelligence and natural language processing have transformed human-computer interaction and paved the way for the creation of voice-activated devices in a variety of fields. This paper describes the development and deployment of a voice-activated vehicle, a novel application meant to improve accessibility, safety, and driving pleasure. By fusing voice recognition technology with an automotive control interface, the system enables drivers to carry out a number of tasks with voice commands. These features include multimedia operation, climate control, navigation, and car diagnostics. The system can comprehend and execute natural language instructions by utilizing machine learning techniques, resulting in a smooth and user-friendly interface. Furthermore, the integration of cutting-edge safety technologies guarantees that voice commands won't jeopardize driving security. Results from experiments show how accurate the system is in identifying and carrying out instructions in a variety of settings. A major step towards the future of smart cars, this voice-activated automobile prototype shows how artificial intelligence (AI) might change transportation and make it more accessible for those with impairments.

Abstract: The project design and implementation of a GPS (Global Positioning System) tracking system with Arduino Uno, GSM SIM900A module,GPS L89 Module were meant to send Location information in form real-time or short alerts SMSs via a pre-registered mobile number. The Arduino is the master which commands the GSM module to send SMS messages, and also communicates with GPS device for getting geographical coordinates. When started, the GPS is constantly reporting where you are-this information is sent as a Google Maps link through the GSM. The system may send regular updates, or return answers to GPS commands requesting the location details of individual units-solving their communication reliability issues plus optimizing for power and signal quality. It can be used to personal safety and asset tracking for a very low price.

Abstract: "Emoji Pairs Challenge" is a captivating web-based memory game that aims to test and enhance players' cognitive abilities through an enjoyable and interactive experience. The game presents a grid of concealed emojis, where players must uncover and match pairs by flipping the tiles. Featuring multiple difficulty levels, players can select from various grid sizes to customize the challenge according to their skill level. The game keeps track of the number of moves and the time taken to complete each level, motivating players to boost their memory and speed. The vibrant and expressive emoji graphics infuse a playful element, making the game ideal for players of all ages.

Keywords: Memory Enhancement, Cognitive Development, Emoji Pairing, Interactive Gameplay, Brain Workout, Matching Game, Educational Fun.

Abstract: Weather data takes center stage as a crucial element in technological enhancements and rapidly changing environmental patterns, serving applications that span from agriculture to disaster management and surveillance. Though, these classic weather stations are affected by several disadvantages as they still depend upon data transmission all the time. This inevitably leads to a high power consumption loads of data which it costs as well time and money even after by the efforts.

Abstract: The project aims at designing, modelling and analysis of a fixed wing vertical take of landing (VTOL) UAV (Transitional aircraft), (Hybrid drone) and evaluate its performance of airfoil at different angle of attacks. The aircraft possess the merits of fixed wing aircraft which includes high speed, endurance and range and (VTOL) which includes hovering capability and precise low speed flight response which is extremely helpful in remote areas. The CAD modelling of the UAV is done with help of CATIA software The mathematical modelling is done using MATLAB & SIMULINK analysis of the airfoil using ANSYS (CFD simulation). Ultimately the project aims to develop a high-performance UAV that can take off and land vertically while providing efficient forward flight capabilities where the UAV is required to operate in harsh and extreme environmental conditions.

Keywords: Fixed wing, performance, low speed flight, endurance & range.

Abstract: Traditional methods may not be successful in meeting the evolving demands of modern agriculture, always striving for increased productivity and sustainability. The proposed architecture works as a system on top of comprehensive interfacing with the sensors and also in real time protecting crops through IoT cloud. Soil Moisture Sensor, PIR Motion Sensor, DHT11 are interfaced with microcontroller to send the moisture level and turn off the pump automatically and notify that on Telegram Bot. The DHT11 sensor data are transmitted on to the LCD. PIR Motion Sensor senses the passive infrared rays and notify the invasion activity on LCD and Telegram Bot. Hence with the above working the agriculture production leads to a better living and yield of the crops.

Keywords: AUTOMATION, ESP32, IOT, SENSOR, WFI, TELEGRAM BOT.

Abstract: Flow shop scheduling refers to the execution of jobs in a pre-defined order. The set up time of machines is an important parameter while studying the waiting time of jobs. The presented model is a flow shop scheduling model in two stage where the processing times are designed in a specially structured manner. The machine set up time has also been considered separately. The algorithm has also been applied to a numerical example.

Keywords: Waiting time of jobs, Set up time, Flow shop Scheduling, Processing time.