Adaptive Cruise Control System in Transportation Systems using Artificial Neural Network based Fuzzy Inference System

This study examines the use of Adaptive Neuro Fuzzy Inference Systems (ANFIS) and Shallow Neural Networks in designing an efficient Adaptive Cruise Control (ACC) system. The main objectives are to improve vehicular safety, passengers’ comfort, and fuel efficiency. The processed data from an ACC-enabled car were analyzed using clustering models, such as the Self-Organising Maps clustering technique, and fitting models on the samples taken for 15 minutes. The models were benchmarked for three and five-decimal point precision based on parameters like Root Mean Square Error (RMSE), training time, and adaptability. Results demonstrate the superior performance of Neural Networks in terms of speed and accuracy, while ANFIS provided interpretable rule-based responses. This comparative analysis highlights the potential of integrating Soft-Computing techniques to enhance ACC system precision and reliability, enabling safer and more efficient transportation.