Efficient implementation of a wavelet neural network model for short-term traffic flow prediction: Sensitivity analysis

The concept of a smart city is emerging to address significant challenges arising from rapid urbanization, economic growth, and climate change. Innovative technologies can be used as a means to promote sustainable and inclusive urban development. These technolgies include the deployment of the internet of things (IoT), artificial intelligence (AI), energy management, and smart transportation. In a smart city, intelligent transportation systems ITSs play a vital role in efficient traffic management. This paper explores the use of hybrid AI techniques for predicting short-term traffic flow data from M25 motorways in the UK. Since volume traffic flow data are non-stationary, wavelet transform (WT), as a powerful signal analyzer, is applied to signal decomposition for the elimination of redundant data from input matrices. The feature selection method based on the Gram-Schmidt (GS) orthogonalization process is used for the selection of more valuable features. The elimination of redundant data can speed up the learning process and improve the generalisation capability of the prediction models. After a pre-processing stage, a wavelet neural network (WNN) with a simple structure is applied as a powerful prediction tool. Two separate structures are considered for the prediction of weekday and weekend traffic volume data. The experiments explore that the debauchies-4 (db4) wavelet function with 7 decomposition levels leads to the best detection accuracy. Moreover, factors such as the range of forecasting, the type of the day, and the level of decomposition all have an impact on prediction stability. Compared with existing prediction methods, the proposed approach produces lower values of root mean square error (RMSE) and mean absolute percentage error (MAPE) for all step-horizons analyzed. These findings provide valuable implications and insights into the development of an efficient and reliable road condition monitoring system for delivering secure and sustainable transportation services.