EVALUATING VEHICLE SAFETY AND ACCEPTABILITY USING MACHINE LEARNING ALGORITHMS

ABSTRACT

This study focuses on evaluating vehicle safety and acceptability using machine learning algorithms. Traditional methods for assessing safety and acceptability in vehicles have become inadequate due to technological advancements and increasing complexity. To address this, the study collects a diverse dataset that includes crash test data, sensor measurements, vehicle features, and human factors. Various machine learning algorithms such as decision trees, random forests, support vector machines, neural networks, and gradient boosting models are applied to the dataset using cross-validation techniques. The algorithms help predict crash outcomes, analyze severity, and identify areas for improvement in vehicle design and safety features. Additionally, machine learning algorithms are used to analyze user feedback, survey responses, and contextual data to understand user preferences and improve acceptability. The study also explores interpretability techniques to provide insights into the decision-making process. A comparative analysis of the algorithms' performance, accuracy, interpretability, and efficiency is presented. Overall, this research demonstrates the potential of machine learning algorithms in enhancing vehicle safety standards and improving user satisfaction.