This project aims to develop an AI-driven Intrusion Detection System (IDS) tailored for IoT networks. Given the increasing security risks in IoT environments, this system will use machine learning algorithms to detect abnormal network traffic patterns and potential cyber threats in real time. The project will involve collecting IoT network traffic data, feature extraction, model training using supervised and unsupervised learning techniques, and real-time monitoring. The system will be tested using datasets like CICIDS or real IoT environments to evaluate its efficiency in detecting cyberattacks such as DDoS, malware, and unauthorized access.

This project will design a 5G-enabled smart traffic management system that leverages edge computing and real-time data analytics to optimize urban traffic flow. Using vehicle-to-infrastructure (V2I) communication, the system will collect real-time traffic data from sensors, cameras, and connected vehicles. Edge computing will be used to process data locally, reducing latency and ensuring faster response times. The system will implement AI-based predictive analytics to control traffic signals dynamically, reduce congestion, and improve emergency response times. It will also integrate a mobile app for drivers, providing real-time traffic updates and optimal route suggestions.

This project focuses on developing an AI-powered code review tool that uses Natural Language Processing (NLP) and deep learning to detect bugs, vulnerabilities, and code inefficiencies in software repositories. The system will integrate with platforms like GitHub and GitLab, analyzing pull requests and commits for security vulnerabilities, coding standard violations, and logical errors. It will also provide suggestions for improving code readability and efficiency. The model will be trained on large-scale open-source codebases and will support multiple programming languages.