Decision-Making in Automotive Working Employee Safety Projects Using AI With IoT-Driven Analytics Using Big Data

This research explores the integration of Artificial Intelligence (AI) and IoT-driven analytics using Big Data technologies to enhance decision-making in automotive employee safety projects. The research employs Real-Time Predictive Analytics with Machine Learning (XGBoost) as the primary method, leveraging its efficiency in identifying patterns and predicting safety risks from vast datasets. Apache Spark with IoT Integration serves as the core tool for handling real-time data ingestion, processing, and analysis from connected IoT sensors, wearables, and environmental monitors deployed across automotive work environments. The framework ensures real-time anomaly detection, predictive insights, and instant safety interventions, enabling a 35% reduction in latency and improved hazard prediction accuracy. The results demonstrate the system's capability to process high-velocity data streams efficiently, offering scalability, accuracy, and transparency.