This paper uses a neural network approach transformer of taxi driver behavior to predict the next destination with geographical factors. The problem of predicting the next destination is a well-studied application of human mobility, for reducing traffic congestion and optimizing the electronic dispatching system’s performance. According to the Intelligent Transport System (ITS), this kind of task is usually modeled as a multi-class problem. We propose the novel model Deep Wide Spatial-Temporal-Based Transformer Networks (DWSTTNs). In our approach, the encoder and decoder are the transformer’s primary units; with the help of Location-Based Social Networks (LBSN), we encode the geographical information based on visited semantic locations. In particular, we trained our model for the exact longitude and latitude coordinates to predict the next destination. The benefit in the real world of this kind of research is to reduce the customer waiting time for a ride and driver waiting time to pick up a customer. Taxi companies can also optimize their management to improve their company’s service, while urban transport planner can use this information to better plan the urban traffic. We conducted extensive experiments on two real-word datasets, Porto and Manhattan, and the performance was improved compared to the previous models.

Recently, for public safety and traffic management, traffic flow prediction is a crucial task. The citywide traffic flow problem is still a big challenge in big cities because of many complex factors. However, to handle some complex factors, e.g., spatial-temporal and some external factors in the intelligent traffic flow forecasting problem, spatial-temporal data for urban applications (i.e., travel time estimation, trajectory planning, taxi demand, traffic congestion, and the regional rainfall) is inherently stochastic and unpredictable. In this paper, we proposed a deep learning-based novel model called “multi-branching spatial-temporal attention-based long-short term memory residual unit (MBSTALRU)” for the citywide traffic flow from lower-level layers to high-level layers, simultaneously. In our work, initially, we have modeled the traffic flow with spatial correlations multiple 3D volume layers and propose the novel multi-branching scheme to control the spatial-temporal features. Our approach is useful for exploring temporal dependencies through the 3D convolutional neural network (CNN) multiple branches, which aim to merge the spatial-temporal characteristics of historical data with three-time intervals, namely closeness, daily, and weekly, and we have embedded features by attention-based long-short term memory (LSTM). Then, we capture the correlation between traffic inflow and outflow with residual layers units. In the end, we merge the external factors dynamically to predict citywide traffic flow simultaneously. The simulation results have been performed on two real-world datasets, BJTaxi and NYCBike, which show better performance and effectiveness of the proposed method than previous state-of-the-art models.

In recent years, the next-POI recommendation has become a trending research topic in the field of trajectory data mining. For protection of user privacy, users’ complete GPS trajectories are difficult to obtain. The check-in information posted by users on social networks has become an important data source for Spatio-temporal Trajectory research. However, state-of-the-art methods neglect the social meaning and the information dissemination function of check-in behavior. The social meaning is an important reason why users are willing to post check-in on social networks, and the information dissemination function means, users can affect each other’s behavior by check-ins. The above characteristics of the check-in behavior make it different from the visiting behavior. We consider a new problem of predicting the next check-in behavior including the check-in time, the POI (point-of-interest) where the check-in is located, functional semantics of the POI, and so on. To solve the proposed problem, we build a multi-task learning model called DPMTM, and a pre-training module is designed to extract dynamic social semantics of check-in behaviors. Our results show that the DPMTM model works well in the check-in behavior problem.