A multi-document abstractive summarization system built by combining hybrid embeddings and optimized transformer models to generate high-quality research summaries.
A computer-vision–based compliance monitoring system that detects missing safety gear in real time.
Data-driven crop recommendation prototype using real-time soil, weather, and nutrient sensing.
A deep-learning–powered plant disease detection system.
A retrofittable ADAS system built for heavy vehicles designed to eliminate blind spots with real-time detection, stitched vision, and intelligent alerts.
IoT-powered hydroponics system that tracks water quality and delivers actionable insights through.
A camera-based detection prototype that monitors metro platforms for yellow-line breaches, helping prevent accidents and improve passenger safety.
A wireless system enabling vehicles to communicate in real time, improving safety around blind spots and supporting smart parking notifications.
A Raspberry Pi–powered system that detects potholes in real time and logs their exact GPS locations for automated road-quality mapping.
This AI research prototype compares multiple CNN models for deepfake detection and contributed to a successful IEEE-published paper.
A comparative deepfake detection case study using CGAN and DCGAN to reveal how synthetic media is generated and how manipulated images can be identified.
Advanced Driver Assistance System (ADAS) using YOLOv8 for obstacle and lane detection.
This prototype randomly selects one seat in a community gathering setup, giving a fair chance for any participant to speak.
A lightweight ML-powered system that detects ransomware threats in real time by scanning newly connected devices for suspicious file behavior.
This system is a memory game that challenges players to remember and repeat a sequence of balls raising out of a box.
System using face recognition and fingerprint verification, developed as a functional prototype.