Things I’ve made trying to leave my legacy behind.

I’ve worked on tons of little projects over the years but these are the ones that I’m most proud of. Many of them are private repositories, so if you see something that piques your interest, reach out and I’ll be happy to share more details, or even collaborate on something similar.

  • Mobile Application for Cancer Detection (AI + Healthcare)

    Developed a CNN model for cancer detection (84% accuracy) and deployed it in a cross-platform mobile app with optimized inference speed (<100ms). Evaluated performance using precision, recall, and F1-score, comparing with ResNet and EfficientNet benchmarks.

    github.com

  • Autonomous Smart Wheelchair (AI + IoT)

    Implemented autonomous navigation using A* algorithm with YOLOv5 for real-time obstacle avoidance (<50ms latency). Integrated Raspberry Pi with LiDAR sensors and published research on enhanced A* for mobile robots.

    researchgate.net

  • Multimedia Mining & Indexing (2D/3D Retrieval & Classification)

    Developed 3D model search engine (89% accuracy on ShapeNet) using Fourier Coefficients and Zernike Moments. Built 2D image classification with color histograms and texture analysis, reducing search time by 60% using FAISS vector indexing.

    github.com

  • Academic Chatbot with NLP (LLaMA 3 + RAG)

    Fine-tuned LLaMA 3 with LoRA (+67% accuracy) and implemented RAG with ChromaDB. Deployed with Vue.js frontend and containerized Flask API supporting 100+ concurrent requests.

    github.com