Travelling Modes Recognition via Bayes Neural Network with Bayes by Backprop Algorithm
Shaocheng Jia, Yun Yue, Zi Yang, Xin Pei, Yashen Wang · CICTP 2020 · 2020
Travelling modes recognition is essential to traffic and infrastructure management. Nevertheless, adverse factors such as lacking training data, unbalanced trip mode data, and undetermined input features hinder the process of obtaining a precise and robust travelling modes recognition. In this paper, we develop a novel method using Bayes neural network (BNN) with Bayes by Backprop algorithm to solve the problem. First, the trajectories are segmented into sub-trajectories in the transportation modes. Then, velocity statistics histogram feature (VSHF) is built as the input of our BNN. Each parameter of BNN is a distribution rather than a fixed constant, so it can avoid overfitting. In addition, BNN has a strong capability to predict the unseen data. The experiments showed that BNN can significantly improve the performance of traditional neural networks in travelling mode recognition. Our method can also be applied to other tasks requiring accuracy improvement or robustness increment.