DEPARTMENT OF COMPUTER ENGINEERING

This study presents the design and implementation of a smart, lightweight, federated deep learning system that integrates solar-powered cameras for automated attendance, unauthorized entry prevention and real-time cyber threat detection in academic environments. Using TensorFlow Lite, Python, and a Flask-based web interface, the model achieved high accuracy in facial recognition while maintaining low computational and energy costs. A structured SQLite3 database supported efficient local data handling, while solar energy integration enabled autonomous and sustainable operation. This project validates the potential of combining renewable energy, artificial intelligence, and federated learning to enhance classroom management and IoT security in lowresource settings.

Lithium-ion batteries have completely changed our world, powering everything from the smartphones in our pockets to electric cars and solar power grids. However, these batteries have a major flaw: they are highly sensitive and can easily get damaged, fail early, or even catch fire if they get too hot, overcharge, or drain too deeply. Traditional battery systems usually react only after a problem has already happened, which is not safe enough for modern technology. The main goal of this project was to design and test a Smart Management System (SMS) that acts as an intelligent brain for lithium-ion battery packs, actively keeping them safe, helping them last longer, and making them work more efficiently. To achieve this, the project used MATLAB and Simulink software to build a detailed, realistic model of a lithium-ion battery pack. Inside this virtual setup, special control logic was built to constantly track individual battery cell voltages, current, and the overall State of Charge (how much energy is left) in real time. Safety boundaries were explicitly programmed into the system to flag an error the moment voltage crossed unsafe limits—specifically setting an upper overvoltage limit of 16.6 V and a lower under-voltage limit of 11.2 V. The simulation was run under different lifelike work situations and heavy loads to see how well the smart system would respond to sudden changes. The results clearly showed that the system works exactly as planned. The moment an unsafe voltage limit was crossed, the smart system reacted immediately, flagging the error and stabilizing the voltage safely within its target boundaries to prevent any damage to the battery cells. The system also smoothly tracked the steady drop in the battery's energy capacity as it discharged over time. Ultimately, this project proves that using an intelligent, software-based management system is a highly reliable and affordable way to protect modern energy systems before moving on to building expensive physical hardware.

In today's computing landscape, it is all about the proactive and intelligent solutions that extend beyond the reactive nature of a standard system monitoring solution. This project focuses on creating an AI-based System Monitor and Process Manager for Windows OS in the Rust programming language, with real-time intelligent analysis powered by Google's Gemini API. It overcomes the shortcomings of traditional monitoring solutions, including fixed thresholds, lack of elasticity for changing workloads, and the absence of human-readable insights, by combining Rust's performance and memory safety with cloud-based large language model (LLM) reasoning. Through the use of the sysinfo crate system metrics, such as CPU utilization, memory, disk I/O, and network traffic are collected and packaged into prompts sent to the Gemini 1.5 Flash API, which provides actionable, natural language summaries for each metric that are categorized by anomalies, optimizations, and priorities. High metric accuracy was shown through validation testing with the Windows Task Manager (1– 3% deviation, which is acceptable for real time monitoring). The AI-generated responses have always been relevant to the content, and 75-80% of them contained specific recommendations. The non-technical evaluators and technical evaluators both provided user feedback that showed a great preference for the use of the natural language interface system as opposed to traditional numerical dashboards. Although complete automation of the process was not achieved for security and complexity reasons, the system provides a good proof of concept for the feasibility of a hybrid architecture between a low-level native monitoring system and an AI-based semantic analysis system. The tool can be deployed as standalone tool without any dependency that requires a Windows executable file, which makes it easy to use for both individual and enterprise users. This work presents a novel methodology for proactive system performance management, especially important for resource-constrained systems, and serves as a stepping stone for future advancements such as predictive analytics, automated process control, and local LLM inference. Key components: System monitoring, Windows OS, Rust programming language, Artificial Intelligence, Gemini API, process management, anomaly detection, real-time analysis.

The integration of renewable energy systems, particularly photovoltaic (PV) technology, has become increasingly essential in addressing global energy demands and environmental concerns. However, the nonlinear and time-varying characteristics of solar irradiation and temperature significantly affect the efficiency of PV systems. Maximum Power Point Tracking (MPPT) techniques are employed to ensure that PV modules operate at their optimal power point under varying conditions. Traditional MPPT methods such as Perturb and Observe (P&O) and Incremental Conductance (IncCond) offer simplicity but often suffer from oscillations, slow convergence, and reduced performance under dynamic conditions.
This research investigates the application of reinforcement learning (RL) algorithms for MPPT control in PV systems, aiming to enhance tracking speed, stability, and adaptability. By formulating the MPPT problem as a sequential decision-making process, RL agents learn optimal control policies through continuous interaction with the PV environment without requiring explicit system modeling.
Various RL approaches—such as Q-learning, Deep Q-Networks (DQN), and Policy Gradient methods—are analyzed and compared with conventional techniques through simulation studies. The results demonstrate that RL-based MPPT controllers can effectively handle rapidly changing environmental conditions, minimize steady-state oscillations, and achieve superior energy harvesting efficiency. This study highlights the potential of reinforcement learning as a robust and intelligent solution for real-time PV power optimization

As the world continues to embrace cleaner and smarter energy solutions, there's a growing need for tools that not only design microgrids but also make them smarter, more responsive, and easier to manage. This project introduces an Intelligent Microgrid Management and Optimization System — a desktop application built with Python — designed to help users plan, optimize, and monitor solar-powered microgrid systems more efficiently. What sets this tool apart is its ability to pull live weather data (like sunlight levels and temperature) using the Open Weather Map API. With this, it can predict how much energy your solar panels might generate and how much power you’ll need, thanks to built-in machine learning models. The system then uses a genetic algorithm to figure out the best combination of solar panel size and battery capacity to meet your energy needs while keeping costs low. The application runs through a simple and responsive user interface (built with PyQt6), offering features like real-time graphs, a weather dashboard, and system control panels. It also supports SCADA-style monitoring, so users can see power generation, battery status, and energy demand in real time. Overall, this tool is designed to be both smart and user-friendly, making it useful not just for engineers and developers, but also for students, researchers, and organizations working on renewable energy solution

In today’s digital economy, efficient client engagement and seamless delivery of services are instrumental to the competitiveness of Information Technology (IT) consulting firms, especially in developing economies like Nigeria. However, with the majority of Nigerian IT consultancies, including small and medium-sized businesses (SMEs), still manually managing appointments and client engagement, there is inherent inefficiency in operations, missed opportunities, and decreased client retention.

These challenges are overcome in this research by conceptualizing, designing, and implementing a web-based IT consulting platform with automated appointment scheduling and email marketing functionalities. Based on the strategies of Service-Dominant Logic (SDL) and Human-Computer Interaction (HCI), the project uses a formal methodology based on requirement analysis, system design, development, testing, and evaluation. The resulting platform allows clients to schedule consultations, receive automated email reminders and confirmations, and allow administrators to manage client information and campaigns through
an interactive dashboard.

The solution was constructed using traditional web technologies (HTML, CSS, JavaScript, Node.JS, and PostgreSQL) with an intrinsic emphasis on mobile responsiveness and lowbandwidth support. Testing ensured that the combined solution is more accessible to users, simpler to administer, and enhances client-consultant communication. The project adds an addition to a context-specific digital framework tailor-made for the infrastructural environment of Nigerian SMEs and offers an extensible template for other service-delivery sectors in need of digitalization.

This project proposes the design and implementation of a smart meter management system. The system will focus on electricity metering and leverage smart meter technology to collect realtime consumption data. Improvements in metering infrastructure are required due to the growing need for better customer service and energy efficiency. The “Design and Implementation of Smart Meter Management System” project aims to create an efficient and intelligent system for managing energy consumption using smart meters. Smart meters, equipped with advanced sensors and communication modules, enable real-time data collection and bidirectional communication between utility providers and consumers. This smart meter management system has the potential to revolutionize energy management by providing valuable insights into consumption patterns, enabling optimized billing practices, and empowering consumers to make informed choices about their energy use. The system will gather, analyze, and manage smart meter data to improve energy usage monitoring, billing accuracy, and resource optimization.

This project presents the design and implementation of an automated waste management system utilizing an Arduino Uno microcontroller, ultrasonic sensors, and a servo motor to enhance efficiency and hygiene in waste disposal. The system continuously monitors the fill level of a waste bin using an ultrasonic sensor, which provides real-time data to the Arduino. When the sensor detects that the bin is nearing capacity or a user is present, the Arduino activates a servo motor to automatically open and close the bin lid, enabling touchless operation and reducing the risk of contamination. Powered by a 9V replaceable battery, the system is portable and well-suited for environments with unreliable electricity supply. Rapid lid response, with positive user feedback regarding convenience and hygiene. The project highlights the potential for scalable, low-cost smart waste solutions in both urban and rural settings, and lays the groundwork for future enhancements such as IoT connectivity, renewable energy integration, and automated waste sorting for improved sustainability and resource management.

A Battery Management System (BMS) is an electronic control system that monitors and manages rechargeable battery packs. Secondary batteries are commonly used as the storage of energy produced by solar panels. However, the utilization of a battery without proper management can cause damage due to overcharging and over-discharging.
The BMS continuously monitors cell voltages, current, temperature, and state of charge while protecting potentially damaging conditions such as overcharging, over-discharging, excessive current, and temperature extremes. Advanced systems incorporate cell balancing to maintain uniform charge distribution across multiple cells, thermal management to regulate operating temperatures, and sophisticated algorithms to estimate battery state of health and remaining useful life.
This study aims to design a battery management system (BMS) on a Valve Regulated LeadAcid (VRLA) battery. The method used was the battery State of Charge (SOC) estimation using Coulomb Counting (CC) method. The results showed that the BMS was successfully designed and implemented to automatically cut-off the current when the SOC value is 100% (charging limit) and 20% (discharging limit)

As the world continues to embrace cleaner and smarter energy solutions, there's a growing need for tools that not only design microgrids but also make them smarter, more responsive, and easier to manage. This project introduces an Intelligent Microgrid Management and Optimization System — a desktop application built with Python — designed to help users plan, optimize, and monitor solar-powered microgrid systems more efficiently. What sets this tool apart is its ability to pull live weather data (like sunlight levels and temperature) using the OpenWeatherMap API. With this, it can predict how much energy your solar panels might generate and how much power you’ll need, thanks to built-in machine learning models. The system then uses a genetic algorithm to figure out the best combination of solar panel size and battery capacity to meet your energy needs while keeping costs low. The application runs through a simple and responsive user interface (built with PyQt6), offering features like real-time graphs, a weather dashboard, and system control panels. It also supports SCADA-style monitoring, so users can see power generation, battery status, and energy demand in real time. Overall, this tool is designed to be both smart and user-friendly, making it useful not just for engineers and developers, but also for students, researchers, and organizations working on renewable energy solutions.