Hybrid Grey Wolf: Bald Eagle search optimized support vector regression for traffic flow forecasting

In this digital interconnected era, Intelligent Transportation System (ITS) bridges the gap between communication and transportation engineering in a smarter way, thereby facilitating the trespassers and travellers with forecasting of traffic and broadcasting of traffic incidents, and infotainment data. Automatic prediction of congestion and traffic flow at one point is a challenging task. Although many machine learning algorithms exist for prediction, the selection of appropriate parameters of algorithms had a great impact on the accuracy of prediction. Hybrid combination of Grey Wolf Optimization (GWO) with new emerging Bald Eagle Search (BES) Optimization algorithm has been proposed to optimize the parameters of Support Vector regression to predict the traffic flow. This hybrid SVR-GWO-BES, has been applied to real-time traffic data of the open-source Performance Measurement system dataset and Indian road traffic, which has been proven to be better than existing methodologies.

Automated summary

In the digital era, Intelligent Transportation Systems play a crucial role in bridging communication and transportation engineering to provide traffic forecasting, incident broadcasting, and entertainment data. Improving the accuracy of machine learning algorithms in parameter selection is essential for accurate traffic flow prediction.