Arunkumar Kesavan completed Machine Learning for Automotive Safety

Built an end-to-end perception validation dossier for a synthetic Aurora-7 detector: defined the IoU-based detection rule, computed aggregate precision/recall and VRU false-negative rate, sliced recall by lighting/visibility/class to expose the night and occlusion collapse, and translated the top misses into ISO 21448 SOTIF chains with concrete mitigations. Finished with an evidence-based GO-WITH-CONDITIONS release recommendation tied directly to the measured safety gaps.

• Leakage-Free Metric Definition
• Condition-Sliced Safety Analysis
• SOTIF Functional-Insufficiency Reasoning
• Evidence-Based Release Decision