Architecting Intelligent Systems with Deep Learning & Code
Discover the logic behind a portfolio that echoes innovation, algorithms, and seamless digital experiences.
Building predictive models and intelligent algorithms
Extracting deep insights from complex visual data
Creating seamless end-to-end web applications
Transforming raw data into actionable intelligence
Motivated B.Tech Information Technology student at MBIT, Anand, Gujarat. I specialize in
building end-to-end AI-powered systems — from real-time computer vision pipelines to
full-stack civic platforms.
I thrive at the intersection of machine learning and software engineering, turning complex
ideas into real-world, deployable solutions. Fast learner, team player, and always chasing the next hard
problem.
An advanced AI-powered image restoration pipeline that automatically detects and repairs physical photo damage. Features a sequential 5-model deep learning architecture utilizing EfficientNet-B4 + UNet, LaMa inpainting, DnCNN denoising, and Real-ESRGAN 4x super-resolution scaling.
An intelligent stock analysis and predictive trading insights platform. Combines real-time market data streaming with automated technical analysis (RSI, MACD, Bollinger Bands), interactive candlestick visualizers, and hybrid buy/sell recommendations.
A smart city civic issue reporting and municipal management system. Features location-aware complaint submission with GPS boundary validation, real-time interactive Leaflet GIS map visualization, and Gemini AI image verification.
A high-accuracy biometric facial recognition attendance platform. Utilizes OpenCV and facial embedding feature extraction for instant live student verification, liveness validation, and automated CSV/PDF logging.
A real-time dual-phase computer vision safety system. Uses MediaPipe Face Mesh for Eye Aspect Ratio (EAR) calculations and head pose estimation, coupled with a custom YOLOv11 model to detect phone distraction.
System ready. Waiting for incoming data packet. Establish connection via preferred channels below.
DOWNLOAD_RESUME