VOLUME 11, ISSUE 9, SEPTEMBER 2024

Abstract: The leading cause of death that halts socioeconomic advancement in society is a traffic accident. Nigeria is one of the nations that has experienced a rise in road accidents as a result of a number of contributing factors. In order to predict the severity of road crashes in Sokoto and identify the factors that produce accurate predictions, a comparative analysis will be done using four machine learning techniques, including Decision Tree (DT), Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Nave Bayes (NB). This study will employ data from the Federal Road Safety Corps (FRSCN), Sokoto command. Using the Waikato Environment for Knowledge Analysis (WEKA), the experiment will be carried out. The final result for the experiments shows that Random forest (RF) has the highest accuracy score with 98.11% followed by Support Vector Machine (SVM) with the accuracy score of 94.33%, followed by K Nearest Neighbour (KNN) with the accuracy of 92.45% and the last model with the lowest score is Naïve Bayes with accuracy score of 84.90%.

Keywords: Accident Severity, Machine Learning, Naïve Bayes, Weka, Data mining.

Abstract: In this research paper, we have investigated the thermoelectric effect in energy-converting materials at the nanoscale, using the characteristics of density of states, power factor(PF), thermal conductivity, figure of merit(ZT) and carrier mobility also with focusing on their potential for enhancing energy efficiency. The thermoelectric effect, which involves the direct conversion of temperature differences into electrical voltage, offers a promising approach for sustainable energy harvesting. At the nanoscale, materials exhibit unique properties that can significantly improve thermoelectric performance, including increased electrical conductivity and reduced thermal conductivity. This research explores various nanoscale materials, such as nanowires, quantum dots, and thin films, analyzing their Seebeck coefficient, electrical conductivity, and thermal conductivity. By optimizing these parameters, the study aims to enhance the figure of merit (ZT) of thermoelectric materials, making them more viable for applications in energy conversion devices, such as power generators and waste heat recovery systems. It is found that the higher mobility (µ= 0.1 m2/Vs) lies higher than those with lower mobilities (µ= 0.01 m2/Vs). Materials with high mobility are often more conductive and better for applications requiring high electrical transport properties. It has also been observe that the materials with lower thermal conductivity at nanoscale might be preferred for insulating applications, while materials with higher conductivity might be chosen for heat dissipation For thermoelectrics, high mobility is essential to ensure good electrical conductivity without too much degradation of the Seebeck coefficientThe findings contribute to the development of next-generation thermoelectric technologies.

Keywords: Thermoelectric Effect, Nanoscale Materials, Energy Conversion, Seebeck Coefficient, Figure of Merit (ZT).

Abstract: Anomaly detection is a critical aspect of cybersecurity aimed at identifying unusual patterns that may signify potential security threats. This paper investigates various data science methodologies for anomaly detection, including statistical methods, machine learning algorithms, and hybrid approaches. We delve into the challenges faced in these methodologies, such as data quality issues, high false positive rates, and the evolving nature of threats. Furthermore, the paper proposes solutions to these challenges, including advanced preprocessing techniques, model optimization, and adaptive models.

Keywords: Data Science, Anomaly Detection, Cybersecurity, Statistical Methods, Predictive Analytics, Threat Detection.

Abstract: This paper deals with studying about impact of LLM and its application on the agriculture operation (smart farm 4.0). To study the influence of LLM, Firstly, this paper reviews several LLMs on how LLM gives an influence in many areas because its area is so wide such as normal editing works, speak, many advises, and code development by using huge data. Secondly, this paper studies on how we have to introduce into agriculture area, especially vegetable harvest among all agriculture's current issues. Finally, this study focuses on how to design mobile robot and gripper for the effective harvest of vegetable of perilla. Currently, in farm site (country site), there are many problems because almost farmers are old age and young generations are not coming into agriculture site. However, they have to work and farming is important not give up to survive for food. Government is trying to innovate with many ways but it is too far from farmer. Vegetable agriculture is important but no technology because of complex process. This paper study for this issue and simulate before design mobile robot and gripper for perilla harvest in Korean country site. After simulation, we will design and produce mobile robot with H/W and S/W.

Keywords: ChatGPT, LLM, Perilla, Vegetable robot, Smart farm.

Abstract: The agricultural industry faces significant challenges in maintaining crop health and productivity due to plant diseases. Traditional methods of plant disease detection are labor-intensive, time-consuming, and often prone to human error. With advancements in artificial intelligence (AI), particularly deep learning (DL) algorithms, automated plant disease detection has emerged as a powerful tool for precision agriculture. This paper explores the application of deep learning techniques, such as convolutional neural networks (CNNs), for detecting plant diseases through image analysis, highlighting the efficiency, accuracy, and scalability of these methods in real-time agricultural scenarios. We also discuss the integration of deep learning models with smart farming technologies, offering a comprehensive solution for early disease detection and intervention.

Keywords: Automated Plant Disease Detection, Precision Agriculture, Deep Learning, Image Classification, Convolutional Neural Networks (CNNs), Transfer Learning, Data Augmentation, Model Training and Evaluation, Real-Time Detection.

Abstract: The exponential growth of Android-based devices has resulted in a worrying rise in the spread of malware through mobile applications. The surge in Android malware highlights the crucial need for strong security measures. Machine learning, focusing on APK permission analysis, offers a promising solution to detect harmful apps and protect users from security threats and privacy breaches. The model classifies the APK files as benign or malicious based on the permissions used by the model. Our paper, primarily research-based, focuses on comparing various available options for detecting malware to identify the most suitable real-time solution. We propose a malware detection system that assesses an app's maliciousness by analyzing its permission usage. This study presents an innovative method for detecting Android malware, employing Support Vector Machines (SVM), as the machine learning model of choice after evaluating other models. In addition to comparing various models, we incorporated feature reduction techniques during the assessment process. After a comprehensive comparison of various parameters among different models, Support Vector Machines (SVM) emerged as the most suitable choice for our research. The feasibility of SVM was determined through measures such as ROC-AUC, recall, precision, accuracy, and F1-score.

Keywords: Machine learning, APK, Malware, Android, permissions.

Abstract: This paper mainly focuses on the face recognition using edge information and principle component analysis. The edge information is extracted using canny edge detector and further this edge information is used to obtain principle components. This method is innovative as combination of edge information and Eigen images are used for face recognition. The results of this experimentation are evaluated using distance classifiers and are encouraging and will provide guidance for future research work in the field of image processing.

Keywords: Principal Component Analysis, Canny Edge Detector, Distance Classifiers

Abstract: Artificial intelligence (AI) is crucial in benefiting businesses worldwide. Generative AI, in particular, has the potential to revolutionize a variety of businesses by automating tasks, improving project efficiency, improving accuracy, and enabling new capabilities. Two positives of generative AI in business operations are labor productivity and increased profits. Generative AI algorithms can analyze data and make effective business decisions. It has applications in numerous fields, including healthcare, logistics, and social media. Its use in these fields can lead to cost savings and improved business project outcomes. Furthermore, recent advancements in generative AI models, such as ChatGPT, have greatly improved the quality of generated content. This has resulted in a significant improvement in human-like capabilities, such as reasoning. Generative AI has helped leading businesses in various industries, such as Google and Amazon, by driving innovation, improving customer experience, and creating new business opportunities. The continued use of generative AI by businesses in the future would significantly improve business operations and boost the global economy.

Keywords: Generative AI, Human-like abilities, Productivity

Abstract: This study explores the multifaceted challenges posed by deepfake videos, drawing insights from case studies and interviews with journalists, cybersecurity experts, and victimized employees. It highlights the profound impact of deepfakes on journalism, where media professionals face increased responsibilities for verifying content authenticity. The findings reveal that current detection and mitigation methods are largely reactive, underscoring the need for proactive approaches involving AI, biometric analysis, and industry collaboration. The study also examines the organizational and personal impacts, emphasizing the psychological toll on individuals targeted by deepfakes and the varying levels of organizational preparedness. The urgent need for stronger regulatory measures is underscored, with experts calling for clearer legal frameworks to address the misuse of deepfake technology. Socio-cultural and ethical implications, such as the erosion of public trust and identity theft, highlight the broader societal impacts of deepfakes. The study concludes that a proactive, multi-layered response encompassing technological innovation, regulatory action, and public awareness is crucial to effectively mitigate the evolving threats posed by deepfake technology.

Keywords: Deepfake Technology; Journalism Integrity; Content Verification; Cybersecurity Threats; Digital Literacy; AI and Machine Learning; Identity Theft; Cross-Border Cooperation.

Abstract: The focus of this paper is to obtain patterns of integer solutions to homogeneous ternary quadratic diophantine equation given by .The process of obtaining Pythagorean triples from the integer solutions of the considered equation is exhibited.

Keywords: Homogeneous quadratic, Ternary quadratic , Integer solutions, Pythagorean triples , Substitution technique, Factorization method.

Abstract: The increasing complexity of modern power systems, driven by the integration of interconnected technologies, has given rise to smart grids. These grids promise enhanced efficiency, reliability, and sustainability, but they are also vulnerable to cyber threats due to their intricate architecture. This paper addresses the cybersecurity challenges of smart grids by analyzing their components, potential cyberattacks, and the short- and long-term impacts of these attacks. The research explores advanced techniques like anomaly detection, intrusion detection systems (IDS), and AI-driven approaches to enhance the security of smart grids. Additionally, it employs the Analytical Hierarchy Process (AHP) to evaluate various cybersecurity options. The study also examines real-world case studies, assesses cascading impacts of cyberattacks, and develops a situational awareness tool for incident response. The results contribute valuable insights for researchers, policymakers, and practitioners, emphasizing the importance of robust cybersecurity frameworks for protecting smart grid infrastructure.

Keywords: Smart grid, cybersecurity, cyberattacks, intrusion detection systems, anomaly detection, AI in cybersecurity, Analytical Hierarchy Process (AHP), situational awareness, incident response, risk assessment, Internet of Things (IoT).

Abstract: Essbase-driven multidimensional Data warehouses have integrated themselves into the systems of enterprise decision-making and have the possibility of dealing with massive amounts of data while providing analytical values. However, the management and the tuning of these data cubes to serve the given aim and perform well present many difficulties. This article takes a closer look into issues relating to data cube management and performance tuning in systems driven by Essbase. A number of underlying concepts are explained, including cube structuring, indexing, calculation scripts, data loading and partitioning. In addition, we describe the consideration of various tuning techniques such as dimension optimization, management of aggregate storage, use of cache and parallelism in an attempt to fine-tune the cube. This work uses real-world case studies and performance evaluation; it provides useful information on enhancing the quality of responses to queries, decreasing processing loads, and increasing the scalability of enterprise DWs. Else additionally it does consider the key innovations such as hybrid aggregation as well as dynamic calculations. The approach for testing consists of a blend of business response percentages and/or qualitative assessments derived from installations. At the end of the chapter, the reader will understand how to work with Essbase data cubes for optimal business performance management.

Keywords: Essbase, Data cube management, Multidimensional data warehouse, Performance tuning, Dimension structuring, Aggregate storage, Query performance, Partitioning, Dynamic calculations.

Abstract: Mathematics in basic education contributes to the development of critical and reflective thinking that allows students to make a hypothesis before solving a mathematical enigma, as well as to pose and solve challenges using procedures for their solution. Considering that technology has impacted the education of children and adolescents, providing online educational resources, learning platforms and interactive tools, the work presented here aims to develop an educational software to provide a tool for students in the area of fractions. As a result, it was developed in the Visual Basic programming language the Fractions and Conquest software, which provides an interactive learning environment where students can practice and reinforce their knowledge about fractions through playful activities. During the tests conducted on the software, users expressed their satisfaction with its ease of use, as well as indicated that it is very useful for understanding concepts related to fractions. In conclusion, it can be said that it is important to have this type of educational software because it helps the teaching-learning process in the search for the understanding of topics that some students consider abstract, such as fractions. It is intended in the medium term to implement additional features to the software, such as a system to track student progress and personalized evaluation modules, making the learning process more attractive and motivating.

Keywords: educational software, fractions, basic education, mathematics.

Abstract: The Internet of Things (IoT) has generated excitement for a few years now, with start-ups and established businesses placing bets on the industry's growth. Along with the business solutions, IoT has been very vital in connecting things to the internet. There by achieving a communication among the connected devices. The Internet of things (IoT) is getting more traction in recent years. One of the usage scenarios of IoT is smart home. Smart home basically provides home automation for installed devices at home such as thermostat, lighting, air conditioning, etc and allows devices connected to the Internet to be monitored and controlled remotely by user. They still lack of important usage of IoT i.e. providing monitoring, dealing with security, and managing privacy. This paper proposes a smart home system with microcontroller as the backend that not only serves as home automation and merely a switch replacement, but to also record and report important things to the owner of the house e.g. when someone trespasses the house (security perimeter), cctv monitoring, etc, AC Loads can be controlled via Electromagnetic relays. The communication between user and the system is done using Telegram Bot.

Keywords: Telegram Bot,Real-Time Control, Home Appliances, Cloud Integration, Device Monitoring

Abstract: Periods, also known as menstruation, are regular episodes of vaginal bleeding that occur during a woman's monthly cycle. Dysmenorrhea, another name for painful periods, affects a lot of women. During the menstrual cycle, lower abdomen pain is a characteristic of dysmenorrhea. Other symptoms that you can have include headaches, nausea, diarrhea, mood swings, lower back and leg pain, and headaches. This work's primary goal is to develop and assess a herbal pain reliever. The purpose of the herbal roll is to provide relief from menstrual cramps, which can occur before, during, or after the menstrual cycle. Volatile oils found in herbal roll-ons are used to cure a variety of symptoms, including headaches, joint discomfort, lower back pain, and so on. The roller bottles are simple to handle and convenient to use. A blend of volatile oils, including asafoetida, thymol, camphor, and clove oil, are present in this herbal roll-on.

Keywords: Herbal Roll on, Dysmenorrhoea, cramps, Menstrual cycle.

Abstract: The primary objective of the study was to compare Extraversion, Neuroticism and Psychoticism between Softball and Baseball players Total 50 softball 50 baseball players were selected as a subject for the present study. Their age ranged from 21 to 28 years. Data was collected individually through a Eysenck personality inventory from Softball and Baseball Players. To analyze the data mean scores, standard deviation and t-ratio were used to Extraversion, Neuroticism and Psychoticism between Softball and Baseball players. The Results shows No Significant differences between Extraversion, Neuroticism and Psychoticism between Softball and Baseball players