An Uncertainty-based Neural Network for Explainable Trajectory Segmentation

作者：Xin Bi, Chao Zhang, Fangtong Wang, Zhixun Liu, Xiangguo Zhao, Ye Yuan, Guoren Wang · 发表于：ACM Transactions on Intelligent Systems and Technology · 年份：2021 · DOI：10.1145/3467978 · 被引用次数：8 · 研究领域：Traffic Prediction and Management Techniques、Data Management and Algorithms、Time Series Analysis and Forecasting

As a variant task of time-series segmentation, trajectory segmentation is a key task in the applications of transportation pattern recognition and traffic analysis. However, segmenting trajectory is faced with challenges of implicit patterns and sparse results. Although deep neural networks have tremendous advantages in terms of high-level feature learning performance, deploying as a blackbox seriously limits the real-world applications. Providing explainable segmentations has significance for result evaluation and decision making. Thus, in this article, we address trajectory segmentation by proposing a Bayesian Encoder-Decoder Network (BED-Net) to provide accurate detection with explainability and references for the following active-learning procedures. BED-Net consists of a segmentation module based on Monte Carlo dropout and an explanation module based on uncertainty learning that provides results evaluation and visualization. Experimental results on both benchmark and real-world datasets indicate that BED-Net outperforms the rival methods and offers excellent explainability in the applications of trajectory segmentation.