🛰️ SAHI-powered satellite reconnaissance system for detecting military vehicles in high-resolution imagery. Uses YOLOv8 with sliding window inference to detect small objects (tanks, trucks, AFVs) that standard detection misses due to aggressive image downscaling. Processes 4000x4000 images via 512x512 overlapping tiles.

⚓ ML system for submarine threat detection using SVM to classify sonar signals as mines or rocks. Features GridSearchCV optimization, sklearn pipelines, and comprehensive evaluation metrics for underwater anomaly recognition.

🔇 A production-grade deep learning system for real-time drone/UAV detection through acoustic signature analysis. Converts raw audio to Mel-Spectrograms and classifies using a custom CNN. Features auto-dataset ingestion, defense-optimized metrics (high recall), early stopping, model checkpointing, and a ready-to-use inference API.

Tactical Command Dashboard for Military Aircraft Detection using Deep Learning (CNN, MobileNetV2, EfficientNetB0) featuring real-time video inference, HUD simulation, and comprehensive model performance analytics built with Streamlit.

HISSI: A policy concept to secure U.S. humanoid robotics supply chains for defense, ensuring trusted manufacturing and ethical standards. Feedback welcome!

🤖 Secure the supply chain for humanoid robotics in U.S. defense, enhancing logistics and support roles through independent policy concepts.