Aravindan M completed Machine Learning for Automotive Safety

Built a perception validation dossier that defined detection rigorously at IoU >= 0.5, scored a synthetic detections table, and separated headline recall from the safety-critical VRU false-negative rate. Also sliced recall by condition to expose night and occlusion collapse, then translated those failures into a conditional SOTIF-style release recommendation with a daylight cap and sensor-fusion fallback.

• Leakage-Free Detection Definition
• Safety-Critical Metric Selection
• Per-Condition Failure Triage
• Evidence-Based Release Recommendation