Sajal Thalakottukkara Stanly completed Machine Learning for Automotive Safety

Built a perception-validation dossier that defined detection rigorously with IoU>=0.5, scored a synthetic detections table, and separated headline accuracy from the safety-critical VRU false-negative rate. Also analyzed recall by lighting, visibility, and rarity to surface the night/occluded pedestrian risk and tied that failure mode back to the real Uber Tempe crash.

• Leakage-Free Detection Definition
• Safety-Critical Metric Selection
• Per-Condition Failure Analysis
• Evidence-Based Case Linking