This project is a restaurant delivery web application developed using Django and HTML. The platform allows users to browse the restaurant's menu, place orders online, and for the restaurant's admin team to manage and track deliveries. This system simplifies the food ordering process and enhances the delivery management workflow.

I presented a collaborative research paper titled "Enhancing Face Recognition Accuracy through Integration of YOLO v8 and Deep Learning: A Custom Recognition Model Approach" at the 22nd Asia Simulation Conference 2023, organized by the Malaysian Society. Co-authored with Dr. Mohamad Hafis Izran Ishak, our study aimed to advance face recognition technology and has been published following the conference.

This project showcases the application of neural networks in predicting concrete strength, emphasizing a data-driven approach within civil engineering and materials science. Through meticulous stages spanning dataset acquisition, preprocessing, model development, training, and evaluation, the project highlights the effectiveness of neural networks in tackling real-world challenges.

The project focuses on implementing an object detection system for supermarkets using the YOLOv3 algorithm and Python programming language. Its primary objective is to accurately identify various items commonly found in supermarkets, such as fruits, vegetables, packaged goods, and beverages, in real-time. By leveraging YOLOv3's efficiency and accuracy, the system aims to facilitate tasks like inventory management and automated checkout processes. Challenges such as dataset limitations, class imbalance, and performance optimization are addressed through techniques like data augmentation, class weighting, and model optimization.

The "AIWatchGate" project presents an intelligent solution for mask and temperature monitoring, aiming to enforce safety protocols at entry points. Leveraging Python and Machine Learning techniques, it utilizes Raspberry Pi 4 B as the core processing unit, integrated with a Pi camera, temperature sensor, servo motor, and LEDs. Through TensorFlow and Keras, the system employs the MobileNetV2 model for mask detection, while OpenCV facilitates face detection and image manipulation. Challenges include hardware-software integration, real-time performance, and environmental variability, addressed through thorough testing, multi-threading, model optimization, and resource-efficient algorithms. The project offers a scalable and adaptable solution for ensuring compliance with safety measures in various settings.

The "Attendance System Using Artificial Intelligence" project leverages face recognition technology to automate attendance tracking across diverse settings such as educational institutions, workplaces, and events. This system streamlines the traditional manual attendance recording process by identifying individuals from images and automatically recording their attendance.