Traffic State Identification for Urban Roadways during Construction Period Based on Fuzzy C-Means and Kernel Extreme Learning Machine

The traffic state identification for urban roadways during construction period is the basis of making traffic organization scheme and implementing traffic control measures. Therefore, according to the characteristics of traffic during construction period, a traffic state identification method for urban roadways during construction period is presented based on fuzzy c-means and kernel extreme learning machine. Firstly, traffic volume, speed, and time occupancy are taken as the characteristic parameters of traffic state, and the data samples are divided into four types by fuzzy c-means. Then, kernel extreme learning machine is trained by classified data to obtain the model of traffic state identification for urban road during construction period. Finally, the method is verified by simulation data from VISSIM, and the results show that the proposed method has high accuracy and stability, and can effectively identify the traffic state of urban roadways during the construction period.