Artificial Intelligence in Urban Traffic Noise Prediction: A Systematic Review

The present work discusses the traffic noise prediction model based on Artificial Intelligence using Artificial Neural Networks (ANN), AI robot technology, and Intelligent Transportation Systems (ITS). This survey paper used a methodical review of the body of research on traffic prediction, with a particular emphasis on highlighting the most recent developments and untapped research opportunities in AI-based traffic prediction techniques which were used to look up papers in the IEEE Xplore, Web of Science, ACM Digital Library, and Scopus technology libraries. Taking into consideration a variety of input variables, such as traffic volumes, speed, and road conditions, these models are mainly designed with the goal of estimating road traffic noise levels. When compared to analytical techniques, machine learning algorithms have demonstrated good performance when used to model and predict a variety of variables. Artificial intelligence-based models have outperformed traditional and empirical models in traffic noise prediction due to its adaptive nature and capacity to manage non-linear properties. As a result, in contrast to nations with well-established empirical models, the application of AI-based methodologies provides an alternate strategy in nations with distinct traffic compositions and features. With the review, the explosive expansion of artificial intelligence (AI) offers potential for previously unheard-of productivity and creativity in controlling and organizing urban procedures and to serve as a solid resource for future urban traffic prediction using artificial intelligence (AI) research as well as an appropriate resource for readers to catch up on the state of the art rapidly.