Travel Time Modelling of Urban Roads Using Coyote the Optimization-based Machine Learning Method

Travel time prediction as an essential issue has been scrutinized in recent decades. To this end, various techniques are applied to estimate travel duration in the dynamic networks and intelligent transportation systems. Accordingly, in this investigation, prediction of travel time is considered by machine learning techniques. Initially, the experimental test is planned, and the travel time effective parameters are spotted. Subsequently, with the assistance of the floating car method, and Mytacks application, the data are collected in six elected roads. After data preparation, stop delay, grades, and the number of the lane are determined as the most effective travel time criteria. In this study, a novel machine learning technique based on the coyote optimization algorithm is introduced, and its precision is compared with five conventional regression models. Drawing on results, the accuracy of the coyote optimization algorithm-based machine learning technique is more than that of other prediction methods. The coefficient of determination of the introduced machine learning technique for training and testing data is equal to 0.746 and 0.724, respectively. Furthermore, coyote optimization algorithm-based machine learning estimates 73% of testing data with an error of fewer than 20 seconds.