Accurate and timely location prediction of moving objects is crucial for intelligent transportation systems and traffic management. In recent years, ubiquitous location acquisition technologies have provided the opportunity for mining knowledge from trajectories, making location prediction and real-time decisions more feasible. Previous location prediction methods have mostly developed on the basis of shallow models whereas shallow models are not competent for some tricky challenges such as multi-time-step location coordinates prediction. Motivated by the current study status, we are dedicated to a deep-learning-based approach to predict the coordinates of several future locations of moving objects based on recent trajectory records. The method of this work consists of three successive parts: trajectory preprocessing, prediction model construction, and post-processing. In this work, a prediction model named the bidirectional recurrent mixture density network (BiRMDN) was constructed by integrating the long short-term memory (LSTM) and mixture density network (MDN) together. This model has the ability to learn long-term contextual information from recent trajectory and model real-valued location coordinates. We employed a vessel trajectory dataset for the implementation of this approach and determined the optimal model configuration after several parameter analysis experiments. Experimental results involving a performance comparison with other widely used methods demonstrate the superiority of the BiRMDN model.

A navigation grade Strapdown Inertial Navigation System (SINS) combined with a Doppler Velocity Log (DVL) is widely used for autonomous navigation of underwater vehicles. Whether the DVL is able to provide continuous velocity measurements is of crucial importance to the integrated navigation precision. Considering that the DVL may fail during the missions, a novel neural network-based SINS/DVL integrated navigation approach is proposed. The nonlinear autoregressive exogenous (NARX) neural network, which is able to provide reliable predictions, is employed. While the DVL is available, the neural network is trained by the body frame velocity and its increment from the SINS and the DVL measurements. Once the DVL fails, the well trained network is able to forecast the velocity which can be used for the subsequent navigation. From the experimental results, it is clearly shown that the neural network is able to provide reliable velocity predictions for about 200 s–300 s during DVL malfunction and hence maintain the short-term accuracy of the integrated navigation.

Massive trajectory data generated by ubiquitous position acquisition technology are valuable for knowledge discovery. The study of trajectory mining that converts knowledge into decision support becomes appealing. Mobility modes awareness is one of the most important aspects of trajectory mining. It contributes to land use planning, intelligent transportation, anomaly events prevention, etc. To achieve better comprehension of mobility modes, we propose a method to integrate the issues of mobility modes discovery and mobility modes identification together. Firstly, route patterns of trajectories were mined based on unsupervised origin and destination (OD) points clustering. After the combination of route patterns and travel activity information, different mobility modes existing in history trajectories were discovered. Then a convolutional neural network (CNN)-based method was proposed to identify the mobility modes of newly emerging trajectories. The labeled history trajectory data were utilized to train the identification model. Moreover, in this approach, we introduced a mobility-based trajectory structure as the input of the identification model. This method was evaluated with a real-world maritime trajectory dataset. The experiment results indicated the excellence of this method. The mobility modes discovered by our method were clearly distinguishable from each other and the identification accuracy was higher compared with other techniques.

Traffic situation awareness is the key factor for intelligent transportation systems (ITS) and smart city. Short-term traffic flow prediction is one of the challenging tasks of traffic situation awareness, which is useful for route planning, traffic congestion alleviation, emission reduction, and so on. Over the past few years, ubiquitous location acquisition techniques and sensors digitized the road networks and generated spatiotemporal data. Massive traffic data provide an opportunity for short-term traffic flow prediction in a data-driven manner. Most of the existing short-term traffic flow prediction methods can be divided into two categories: nonparametric and parametric. Traditional parametric methods failed to obtain accurate prediction, due to the nonlinear and stochastic characteristics of short-term traffic flow. Recently, deep learning methods have been studied widely in the fields of short-term prediction. These nonparametric methods yielded promising results in practical experiments. Motivated by the current study status, we dedicate this paper to a short-term traffic flow prediction approach based on the recurrent mixture density network, the combination of recurrent neural network (RNN), and mixture density network (MDN). This approach is implemented on real-world traffic flow data and demonstrates the prominent superiority. To the best of our knowledge, this is the first time that the recurrent mixture density network is applied to a real-world short-term traffic flow prediction task.