Predicting future locations of moving objects with deep fuzzy-LSTM networks

Abstract

Trajectory prediction plays an important role in supporting many advanced applications such as location-based services and advanced intelligent traffic managements. Most existing trajectory prediction methods employed fixed spatial division and focused on human closeness movement patterns. However, these methods could lead to a sharp boundary limitation and ignore the periodic characteristics of human mobility. This paper proposes a novel trajectory prediction method based on long short-term memory network (LSTM) called the trajectory predictor with fuzzy-long short-term memory network (TrjPre-FLSTM). First, we introduce a new fuzzy trajectory concept and extend the LSTM to a fuzzy-LSTM to overcome the sharp boundary limitation. Second, we explicitly incorporate the periodic movement patterns of moving objects in the trajectory prediction. Using a real-world mobile phone dataset, we evaluate the performance of TrjPre-FLSTM with two latest competitors. The case study results indicate that the proposed method outperforms the comparative methods in terms of the prediction accuracy.