DEPARTMENT OF COMPUTER SCIENCE

**Abstract** The manual calculation of Grade Point Average (GPA) and Cumulative Grade Point Average (CGPA) is often time-consuming, prone to computational errors, and may lead to inaccurate academic records. This project, titled **"Design and Implementation of a CGPA/GPA Calculator,"** was undertaken to develop a computerized system that automates the computation of students' academic performance with improved accuracy, speed, and reliability. The system was designed to calculate semester GPA and cumulative CGPA based on approved grading policies, taking into account course credit units, grades obtained, quality points, and cumulative academic records. The development of the application followed the Software Development Life Cycle (SDLC), which included requirements analysis, system design, implementation, testing, and evaluation. The system was developed using appropriate programming tools and technologies, with a user-friendly interface that allows users to input course details, credit units, and grades, after which the application automatically computes the corresponding GPA and CGPA. The calculator also provides features for validating user input, minimizing calculation errors, and displaying results in an easily understandable format. System testing was carried out using various datasets to evaluate the accuracy, efficiency, and reliability of the application. The results showed that the developed system accurately computed GPA and CGPA values within a short processing time while eliminating the errors commonly associated with manual calculations. Furthermore, the application enhanced record management, improved user convenience, and provided a dependable tool for students and academic institutions to monitor academic performance. The study concludes that the implementation of a CGPA/GPA Calculator significantly improves the efficiency and accuracy of academic result computation. It is therefore recommended that educational institutions adopt automated GPA/CGPA calculation systems to reduce computational errors, improve transparency, and facilitate effective academic performance monitoring.

In the current fast-changing agricultural environment, farmers need to have access to timely and relevant information to make well-informed choices. This initiative seeks to create and implement a comprehensive Information System specifically designed for farmers, especially in rural and semi-urban areas. The system will utilize modern technology to deliver vital information regarding weather forecasts, crop management, pest control, market prices, and optimal agricultural practices. By integrating mobile and web platforms, the system guarantees easy access and real-time updates. The main goals include enhancing the knowledge base of farmers, boosting crop yields, minimizing losses, and promoting sustainable agricultural methods. The project will entail a thorough needs assessment, system design, development, and intensive field testing in partnership with local farming communities. Additionally, the system will incorporate user-friendly interfaces, multilingual support, and offline functionalities to accommodate diverse user requirements. In the end, this Information System aims to equip farmers with the knowledge and resources needed to enhance productivity and profitability, thus aiding in food security and economic development in the region.

Cardiovascular Diseases (CVDs) remain the paramount global health challenge, responsible for approximately 17.9 million deaths annually, with cardiac arrest representing a particularly critical and sudden event. Despite advancements in machine learning, accurate prediction is often hindered by highdimensional clinical data ("the curse of dimensionality") and the performance limitations of standalone classifiers. Consequently, this study aimed to develop a framework that integrates a novel Hybrid Recursive Feature Elimination-Firefly (RFE-Firefly) feature selection technique with a stacked ensemble classifier to enhance predictive accuracy. The study utilized a structured heart disease dataset from the Kaggle repository, subjecting it to rigorous pre-processing, including normalization and class balancing via the Synthetic Minority Over-sampling Technique (SMOTE). The proposed Hybrid RFEFirefly algorithm was implemented to optimize the feature space, successfully reducing the data to a parsimonious subset of seven critical features. For classification, a stacking ensemble model was constructed using five diverse base learners which are Decision Tree, Support Vector Machine, Logistic Regression, Random Forest, and XGBoost and unified by Random Forest as meta-learner to synthesize their predictive strengths. Experimental results demonstrated that the proposed Hybrid RFE-FA Stack Ensemble achieved a superior accuracy of 90.57% and an F1-score of 0.7619. This performance significantly outperformed individual base classifiers as well as ensembles using standalone feature selection methods. The study concludes that integrating hybrid feature selection strategy with an advance stack ensemble classifier effectively mitigates overfitting and provides a robust, highperformance tool for clinical decision-making in cardiac arrest detection.

This research examined the extent of A Quasi-Experimental Study on the Effect of Informatics in Teaching and Learning in Universities in Edo State, with particular emphasis on differences across federal, state, and private institutions. The study adopted a descriptive survey research design and was guided by the Technology Acceptance Model (TAM) and the Unified Theory of Acceptance and Use of Technology (UTAUT). Data were collected from 345 lecturers and students using a structured questionnaire designed around key constructs such as ICT infrastructure availability, utilization, digital competency, and perceived challenges. Data analysis involved descriptive statistics, Analysis of Variance (ANOVA), correlation, and regression analysis using SPSS. Findings revealed that ICT infrastructure and utilization levels were generally high, with private universities demonstrating significantly higher adoption compared to public institutions. Gender did not significantly influence ICT utilization, while institutional type and academic role (lecturer or student) were significant determinants. Regression results further confirmed that ICT utilization positively and significantly enhances teaching and learning effectiveness. The study concludes that institutional readiness, infrastructural support, and digital competency are critical to effective ICT integration in higher education. It recommends increased investment in ICT infrastructure, continuous capacity building, and supportive institutional policies to enhance technology driven teaching and learning.

Fisheries and aquaculture are vital to global food security but face critical challenges, including security threats from unauthorized access, the limitations of reactive manual monitoring, and uncertainty in long-term production forecasting. Existing management tools often lack a unified approach to integrate real-time operational surveillance with predictive decision-support analytics. This study aims to address these gaps by designing and developing a hybrid methodological framework that integrates computer vision for security and advanced machine learning and time-series forecasting for production analysis and stock management. The study employed a dual-component methodology. For security, an OpenCV-based Histogram of Oriented Gradients (HOG) descriptor combined with a Support Vector Machine (SVM) was implemented to achieve automated, real-time human intrusion detection and alarm triggering. For predictive analytics, a hybrid approach was utilized, applying Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SARIMAX) for long-term production forecasting and various ensemble classifiers (Random Forest, Gradient Boosting, K-Nearest Neighbors) to analyze fish survivability and production trends. Results demonstrate that this integrated framework is highly effective across operational and strategic levels. The computer vision system successfully provided continuous, automated surveillance with verifiable digital evidence. The ensemble classifiers achieved near-perfect performance in survivability prediction (e.g., Random Forest Accuracy = 0.98, F1-score = 0.99, AUC ≈ 0.999). Furthermore, the SARIMAX model effectively projected a steady increase in global fish production, forecasting growth from 232.19 million tonnes in 2024 to 272.12 million tonnes by 2043—a 17.19% increase—capturing long-term temporal dynamics that static regressors fail to model. Based on these findings, it is recommended that fisheries stakeholders prioritize the deployment of computer vision-based surveillance to reduce security risks and labor costs. Additionally, management authorities should integrate ensemble classifiers into stock-management systems to optimize survivability and adopt SARIMAX-based forecasting for robust, evidence-based policy planning. The implementation of these data-driven platforms will significantly enhance sustainable fisheries governance and support proactive resource allocation.

The procurement of motor-vehicle spare parts through traditional physical markets presents challenges such as difficulty in identifying compatible parts, lack of price transparency, geographic and time constraints, and absence of centralized vendor platforms. This study focused on the design and development of a web-based online marketplace for motor-vehicle spare parts to address these limitations by providing a centralized, secure, and user-friendly platform connecting vendors and customers. The research adopted the Agile methodology using the Scrum framework and implemented a layered system architecture consisting of presentation, application, data access, and data storage layers. The system was developed using PHP for server-side processing, MySQL for database management, and HTML5, CSS3, JavaScript, and the Bootstrap framework for responsive user interface design. Selected spare-parts markets in Benin City, Edo State—Evbareke Market, Uwelu Market, and Igun Market were used as case studies to understand vendor operations and customer needs. The study objectives included designing a marketplace that supports product listing and searching based on vehicle make and model, implementing secure user authentication for buyers and vendors, enabling price comparison and vendor rating features, and testing the system to ensure reliable operation. The implemented system successfully delivered a functional multi-vendor marketplace with advanced search and filtering, vehicle compatibility matching, secure shopping cart and checkout processes, order management, inventory control, and role-based access control. Results demonstrated that the system effectively addresses problems associated with traditional spare- parts procurement by improving accessibility, transparency, and efficiency. Challenges such as database optimization, security implementation, responsive design, and system integration were encountered and resolved. The study concludes that web-based marketplace technologies can effectively transform spare-parts trading and support digital transformation in the automotive industry.

Vehicle identification and verification play a critical role in ensuring the security of controlled environments such as university campuses. At the University of Benin’s Ugbowo Campus, the existing manual vehicle verification process suffers from several limitations, including delays, human error, poor record keeping, and the absence of real-time validation. This study addresses these challenges by designing and implementing an Automated Car Plate Number Recognition (ANPR) system capable of detecting, recognizing, and verifying vehicle license plates using computer vision and optical character recognition (OCR) techniques. The system was developed using the Flask web framework, OpenCV for image preprocessing and license plate localization, and the Tesseract OCR engine for extracting alphanumeric characters. A MySQL database was integrated for storing records of registered vehicles and maintaining logs of recognition events. The system allows security personnel to upload vehicle images through a web interface, after which the application automatically processes the image, recognizes the plate number, checks its validity against the stored records, and provides immediate feedback. Testing of the system using images captured under different conditions such as clear daytime lighting, low light, skewed angles, and motion blur revealed that the system performs accurately under favourable conditions and provides partial or usable information even under challenging scenarios. Although recognition performance decreases with poor image quality, the system still offers considerable improvements over manual verification by reducing reliance on human judgment and enhancing the accuracy, speed, and reliability of vehicle monitoring.

Machine learning has become an important technology used in many areas such as healthcare, banking, education, and mobile applications. However, traditional machine learning methods usually require large amounts of data to be collected and stored in one central location, which can create privacy and security concerns. This project focuses on the design and implementation of a Federated Learning system for privacy-preserving machine learning. Federated Learning is a modern approach that allows multiple users or organizations to train a machine learning model together without sharing their raw data. Instead of sending personal or sensitive information to a central server, each participant trains the model on their local device and only shares model updates. This helps to protect privacy while still allowing the model to learn effectively. In this project, a federated learning prototype was developed using Python and machine learning tools. The system was designed with features such as secure aggregation and differential privacy to improve data protection and reduce the risk of information leakage. The performance of the system was tested using distributed datasets to simulate real-world situations where data is stored in different locations. The results showed that the proposed system was able to maintain a good level of model accuracy while protecting user privacy. It also demonstrated that federated learning can be a practical solution for organizations that need to use machine learning without exposing sensitive data. The study concludes that federated learning has great potential for institutions such as the University of Benin and other organizations in Nigeria that require secure and privacy-aware machine learning solutions.

This study proposes the design and implementation of an intelligent chatbot system for the Department of Computer Science, University of Benin, to improve communication between students and departmental administration. Currently, information such as registration deadlines, exam timetables, and announcements is shared through traditional means like notice boards and emails, which often cause delays and inefficiencies. The proposed chatbot, built using Google Dialogflow (NLP) and a PHP-based backend, will provide real-time, accurate responses to student queries through a responsive web interface. System development will include requirement gathering, chatbot design, and integration with a structured knowledge base. Evaluation will focus on response accuracy, usability, and user satisfaction. Expected outcomes include reduced administrative workload, faster and more consistent information dissemination, and improved student experience. The study also aims to offer a scalable framework for applying AI-powered communication tools in other university departments across Nigeria.

Implementing blockchain-based certification systems is pivotal for enhancing the security, transparency, and efficiency of credential verification in academic and professional sectors. This study explores the design and deployment of an NFT-based certificate verification system, leveraging Ethereum blockchain, smart contracts, and decentralized storage (IPFS) to issue, verify, and manage digital credentials. By applying blockchain technology, smart contract logic, and decentralized file systems, this research addresses challenges such as certificate forgery, inefficient manual verification, and limited global accessibility. Key methodologies include the use of Solidity smart contracts for minting NFTs, Web3.js for blockchain interaction, and React.js for user interface development, alongside IPFS for secure off-chain certificate storage. The system is designed to reflect real-world use cases involving students, educational institutions, and verifiers, supporting operations such as certificate issuance, revocation, and verification. Outcomes include instant, tamper-proof verification processes, reduced operational costs, and improved user trust in credential authenticity. By integrating emerging technologies like Web3 and decentralized identity (DID), this research establishes a foundation for scalable, secure, and adaptable certification systems capable of meeting the evolving needs of education and professional validation