.png&w=256&q=75)
🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
ZameenEye-AI
ZameenEye-AI is a wildfire detection pipeline that bridges computer vision with real-world geospatial infrastructure. At its core is a custom-trained YOLOv8 object detection model, trained end-to-end on AMD Radeon hardware via ROCm across 50 epochs, learning to identify wildfire and smoke hotspots from satellite and aerial imagery, reaching an mAP50 of 0.94 on the validation set. The inference pipeline runs natively on AMD GPU compute, with the device explicitly targeted via PyTorch's ROCm-backed CUDA interface (device='cuda:0'), confirmed through torch.cuda.get_device_name(). A single image passes through the model in roughly 4 milliseconds, fast enough for near real-time monitoring workflows. Detection doesn't stop at a bounding box. Each hotspot's pixel coordinates are passed through a georeferencing transform — linear interpolation across a defined area-of-interest's bounding coordinates — converting pixel-space detections into real-world latitude and longitude. The output is a structured, PostGIS-compatible payload (SRID=4326, WKT POINT geometry) with hazard type and confidence score, ready for ingestion into a spatial database for mapping, alerting, or historical tracking. The stack: YOLOv8 (Ultralytics) for detection, PyTorch with ROCm for AMD GPU acceleration, OpenCV for image I/O, and a Python inference layer producing PostGIS-ready JSON. The long-term architecture is designed to plug into a live satellite tile feed and a multi-tenant backend, turning raw imagery into actionable, geolocated wildfire alerts for wildfire-prone regions, including areas across Pakistan where early-detection infrastructure is limited.
13 Jul 2026
ZKSentinel
ZKSentinel: Secure, Verifiable Autonomous Trading Overview ZKSentinel is an autonomous AI trading agent designed for the Agentic Web (2026), bridging the gap between sophisticated momentum strategies and on-chain trust. Built for the Lablab.ai AI Trading Agents Hackathon, it addresses the "Black Box" problem of automated trading by implementing the ERC-8004 standard for verifiable intent. Technical Strategy The agent utilizes the Volume-Confirmed Momentum Strategy, a three-pillar voting system that requires confluence before execution: Trend Analysis: A 9-period EMA filters primary price direction. Volume Integrity: On-Balance Volume (OBV) tracks buying pressure to avoid "fakeouts." Liquidity Verification: Entries require a volume median ratio of 1.5x to ensure high-conviction momentum. Risk Management & Guardrails ZKSentinel prioritizes capital preservation through hard-coded "Sentinel Guardrails": Circuit Breaker: Automatic halt after 3 consecutive losses to prevent death spirals. Volatility Guard: Blocks new entries during extreme price swings exceeding 3%. Cooldown Logic: A mandatory 3-candle rest period after every exit to avoid choppy market noise. Precision Exit: Strict Stop-Loss (0.8%) and Take-Profit (1.5%) targets ensure a disciplined risk-to-reward ratio. ERC-8004 & Cryptographic Trust Every trade generates an ERC-8004 Validation Artifact. Using SHA-256 hashing, the agent creates a "fingerprint" of its strategy checkpoints (EMA deltas, volume ratios, and trade intent). This provides a transparent, tamper-proof audit trail for stakeholders without exposing proprietary weights. Roadmap Phase 1 (Current): Strategy hardening via CoinGecko API and ERC-8004 artifact logging. Phase 2 (Q4 2026): Transitioning artifacts into ZK-SNARKs to prove risk compliance while maintaining total strategy privacy and MEV resistance.
12 Apr 2026
