Shreeya Chakraborty completed Machine Learning for Automotive Safety

Built a perception validation dossier end to end for a synthetic Aurora-7 detector: defined detection correctly at IoU >= 0.5, scored precision/recall and VRU false-negative rate from a detections table, and sliced recall by lighting, visibility, and rarity to expose the worst night-and-occluded pedestrian risk. The final safety case tied those measurements to ISO 21448-style functional insufficiency chains and produced a GO-WITH-CONDITIONS verdict grounded in the candidate’s own evidence.

• Leakage-Free Detection Definition
• Safety-Critical Metric Selection
• Per-Condition Failure Triage
• ISO 21448 SOTIF Reasoning