Graduate Research Assistant - Computer Vision

• Engineered AR/VR/XR solutions using YOLOv8 on HoloLens 2 and edge AI servers.
• Reduced system latency by 30% and boosted energy efficiency by 25% via optimized model deployment and binary offloading.
• Contributed to research in embedded vision systems for defense and real-time analytics.

Embedded Systems and IoT Intern

• Designed an IoT-based road condition monitoring system using IMU, GPS, DHT-22, and GSM modules.
• Achieved 96.92% accuracy in pothole detection and 99.04% in hard braking event classification using Extra Trees Classifier.
• Integrated real-time sensor data with machine learning models on Arduino and Raspberry Pi platforms.

Master of Science in Computer Engineering

Grade: 4.00/4.00

Bachelor of Science in Electrical and Electronic Engineering

Grade: 3.78/4.00