Explore My Projects

Breast Cancer Prediction Using HoverNet Approach System

This project serves as my Final Year Project and focuses on developing a comprehensive web-based system for Breast Cancer Prediction. Leveraging cutting-edge deep learning techniques, the system implements the HoverNet framework to perform simultaneous segmentation and classification of nuclei in histopathology images. The primary objective is to analyze data from the PanNuke dataset and accurately predict cancerous cells, thereby enhancing diagnostic efficiency and accuracy for medical professionals.

The web application is built using Python and the Django framework, with an intuitive interface designed with HTML, CSS, and PHP. The back-end incorporates SQL for database management, enabling secure and efficient data handling. Development was conducted in Visual Studio Code, utilizing Excel for data preprocessing and analysis.

Web-Based System: Product Catalog

This project is a Product Catalog designed for managing and showcasing a variety of drawing tools. The web-based platform offers a user-friendly interface where users can browse, view, and select products, with detailed information about each tool. Built using HTML, CSS, PHP, and JavaScript, the system ensures a smooth and responsive experience for all users.

The application was developed on UKM's server, with backend functionality implemented using PHP and SQL. The design leverages HTML, CSS, Bootstrap, and JavaScript for an intuitive and visually appealing interface. The project was coded using Sublime Text and tested locally with XAMPP.

Sentiment Analysis Model from Tweets Data

This project involves developing a Sentiment Analysis Model that classifies tweets into positive, negative, or neutral sentiments. Using the "movie_data.csv" dataset, which contains tweet data collected from Twitter, the project aims to preprocess text data and evaluate multiple machine learning classifiers to determine their accuracy in sentiment prediction.

The preprocessing phase includes tasks such as text cleaning, tokenization, and vectorization. The processed data is then used to train three different machine learning models: Logistic Regression, Naive Bayes, and Support Vector Machines (SVM). Each model is evaluated based on its performance in classifying sentiments, providing valuable insights into public opinions on various topics.

My Personal Portfolio

This is a personal project where I created My Own Portfolio to showcase my web design skills. The portfolio is designed with a focus on responsiveness and visual appeal. It demonstrates my ability to create interactive and dynamic web pages using core web technologies such as HTML, CSS, and JavaScript.

The portfolio features a range of design elements including responsive layouts, smooth animations, and a user-friendly interface. It is fully optimized to adapt to different screen sizes, ensuring that visitors can enjoy a seamless browsing experience, whether they are on desktop or mobile devices.

Product Catalog for Drawing Art Tools Application

This project involves the creation of a Product Catalog for Drawing Art Tools application, built using Visual Studio 2019 with Visual Basic (VB), an Access Database for data storage, and MySQL for handling product and order data efficiently. The application provides an intuitive interface to create, update, and delete orders while managing a catalog of various drawing tools.

The system is designed to allow users to view and manage products, including adding new products, editing existing ones, and deleting items from the catalog. Additionally, users can place orders, track their status, and perform necessary updates to keep the catalog and orders up to date.

Project File: PRJ_DRAWINGARTSUPPLIES_A188417.sln

Customer Segmentation Analysis using K-Means Clustering

The objective of this project was to analyze customer data from the "Mall_Customer.csv" dataset and segment individuals into distinct groups based on their annual income and spending behavior using the K-Means clustering algorithm. The goal was to derive actionable insights that would help optimize customer engagement strategies.

The project employed a series of machine learning techniques to gain valuable insights into customer behavior. The process began with data preprocessing to clean and prepare the dataset for analysis. This was followed by exploratory data analysis (EDA) to identify patterns and relationships within the data. The K-Means clustering algorithm was then implemented to group customers into clusters based on their annual income and spending habits.

Tools such as Python, Jupyter Notebook, Pandas, Matplotlib, and Seaborn were utilized for data manipulation and visualization. The clusters identified provided valuable insights into high-value customer groups, allowing businesses to tailor their engagement strategies more effectively.

Real-Time Face Mask Detection System using YOLOv8 & OpenCV

This project focuses on developing a real-time face mask detection system utilizing YOLOv8 and OpenCV. The model is trained to detect whether individuals are wearing a face mask correctly, wearing it improperly, or not wearing it at all. The system is designed to be deployed as a web-based application using Flask, providing an intuitive user interface for real-time mask monitoring.

The model classifies face mask compliance into three categories:

• Good (Green): Properly worn face mask.
• Moderate (Yellow): Incorrectly worn face mask.
• Bad (Red): No face mask detected.

Repository: GitHub Repository →

Angular Authentication & Product Management System

This project showcases a responsive and interactive web application built using Angular 18+ that utilizes a RESTful API for user authentication and product data handling. The application features three core modules: Login Page, Home Page, and Detail Page — each with modern UI elements and client-side state management.