Kernel Semi-supervised Extreme Learning Machine Applied in Urban Traffic Congestion Evaluation

Abstract

In urban transportation assessment system, semi-supervised extreme learning machine (SSELM) can be used to unite manual observed data and extensively collected data and cooperatively build connection between congestion condition and road information. Optimized by kernel function, Kernel-SSELM can achieve higher classification accuracy and robustness. In this paper, Kernel-SSELM model is used to train the traffic congestion evaluation framework, with both small-scale labeled data and large-scale unlabeled data. Both the experiment and the real-time application show the evaluation system can precisely reflect the traffic condition.