Understanding Mobility via Deep Multi-Scale Learning

Abstract With the rapid development of mobile Internet and the Internet of Things, mobile devices are generating massive amounts of spatio-temporal trajectory data. This paper aims to propose a method that can automatically mine trajectory data and help people understand mobility of moving objects, thus making people’s life more convenient and traffic management easier. Classifying trajectories is an important method to uncover mobility of moving objects so that we can describe the mobility of moving objects under specific spatial and temporal scales. Although there have been some studies on trajectory classification, yet they either require manual feature selection or fail to fully consider the impact of time and space on classification results. Hence, we propose Deep Multi-Scale Learning Model and design a deep neural network to automatically learn features under multi-scale time and space granularities. The obtained features are fused to output final classification results. Our method is based on the DenseNet, and attention mechanism and residual learning. Our model is able to fully capture spatial features so as to enhance feature propagation and capture long-term dependence. Moreover, the number of network structure parameters is also reduced. We have evaluated our Deep Multi-Scale Learning Model on two real datasets. The results show that our model is superior to the current state-of-the-art models in accuracy, precision, recall and f1-score. Furthermore, the classification results from our model can help to understand mobility accurately.