ADVANCED DRIVER ASSISTANCE SYSTEMS ROAD ACCIDENT DATA INSIGHTS: UNCOVERING TRENDS AND RISK FACTORS

Advanced Driver Assistance Systems (ADAS) have enhanced automotive safety by reducing driver errors andpreventing accidents. This study analyzes the impact of ADAS on road safety using real-world accident data from the United States.The research aims to identify factors influencing injury severity in ADAS-equipped vehicles and evaluate ADAS effectiveness inreducing accidents. A comprehensive dataset involving ADAS, Automated Driving Systems (ADS), and non-automated vehicles isanalyzed using a Random Forest Classifier machine learning approach. Key factors identified include mileage, incident month, andpre-crash speed, which significantly influence injury severity. The model's reliability was ensured through cross-validation, andlogistic regression was used to assess the impact of different ADAS features. Results show that higher mileage correlates withincreased injury severity, potentially due to ADAS performance degradation over time. Temporal factors like the month of theincident, influenced by seasonal weather and traffic, also impact ADAS effectiveness. Pre-crash speed is a crucial factor,highlighting the need for better speed management through ADAS. The study faced challenges in predicting severe injury cases dueto data imbalance. These findings underscore the need for regular updates and maintenance of ADAS technologies and enhanceddata collection on severe accidents. As ADAS adoption increases, collaboration among automakers, policymakers, and researchersis essential to ensure these technologies effectively reduce road accidents and save lives