Vehicle trajectory prediction is a keystone for the application of the internet of vehicles (IoV). With the help of deep learning and big data, it is possible to understand the between-vehicle interaction pattern hidden in the complex traffic environment. In this paper, we propose a novel spatial-temporal dynamic attention network for vehicle trajectory prediction, which can comprehensively capture temporal and social patterns in a hierarchical manner. The social relation between vehicles is captured at each timestamp and thus retains the dynamic variation of interaction. The temporal correlation in terms of individual motion state as well as social interaction is captured by different sequential models. Furthermore, a driving intention-specific feature fusion mechanism is proposed such that the extracted temporal and social features can be integrated adaptively for the maneuver-based multi-modal trajectory prediction. Experimental results on two real-world datasets show that compared with the state-of-the-art algorithms, our proposal achieves comparable prediction performance for short-term prediction, however, works much better for long-term prediction. Additionally, various ablation analysis is provided to evaluate the effectiveness of our proposed network components. The code will be available at https://xbchen82.github.io/resource/ .

As a core function of autonomous driving (AD) and the Internet of Vehicles (IoV), accurately predicting the trajectory of vehicles can significantly improve traffic safety and reduce crash injuries. In this article, we propose an intention-aware non-autoregressive Transformer model with multi-attention learning for multimodal vehicle trajectory prediction. We first present social attention learning (SAL) where graph attention is properly integrated with the Transformer encoder so as to model the social interaction between vehicles. Then, the social and temporal dependency across consecutive frames is captured by temporal attention learning (TAL). The above social and temporal attention modules can be interleaved and stacked to achieve the coupled modeling and thus extract abundant features from trajectory data. To implement precise prediction as well as efficient inference, we further put forward an intention-aware decoder query generation approach to produce multiple possible trajectories concurrently. Finally, cross-attention learning (CAL) is devised to make full use of the encoded features, therefore, yielding future predictions. The proposed model is evaluated on two large-scale vehicle trajectory datasets and the experimental results verify that our algorithm achieves better performance compared with some state-of-the-art models. The root-mean-square error (RMSE) of the predicted trajectory over 5-s time horizon for the next generation simulation (NGSIM) and HighD datasets is 3.43 and 1.10 m, respectively.

Brain functional connectivity network (FCN) based on resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to identify neuropsychiatric disorders such as autism spectrum disorder (ASD). Most existing FCN-based methods only estimate the correlation between brain regions of interest (ROIs), without exploring more informative higher-level interactions among multiple ROIs which could be beneficial to disease diagnosis. To fully explore the discriminative information provided by different brain networks, a cluster-based multi-view high-order FCN (Ho-FCN) framework is proposed in this paper. Specifically, we first group the functional connectivity (FC) time series into different clusters and compute the multi-order central moment series for the FC time series in each cluster. Then we utilize the correlation of central moment series between different clusters to reveal the high-order FC relationships among multiple ROIs. In addition, to address the phase mismatch issue in conventional FCNs, we also adopt the central moments of the correlation time series as the temporal-invariance features to capture the dynamic characteristics of low-order dynamic FCN (Lo-D-FCN). Experimentalresults on the ABIDE dataset validate that: 1) the proposed multi-view Ho-FCNs is able to explore rich discriminative information for ASD diagnosis; 2) the phase mismatch issue can be well circumvented by using central moments; and 3) the combination of different types of FCNs can significantly improve the diagnostic accuracy of ASD (86.2%).

Multi-agent trajectory prediction plays a pivotal role for intelligent transportation and autonomous driving. Modeling the social interaction among agents and revealing the inherent relationship between interaction and future trajectory are crucial for accurate trajectory prediction. To address these challenges, this letter proposes a goal-guided and interaction-aware state refinement graph attention network (SRGAT) for multi-agent trajectory prediction. Specifically, the trajectory sequence of individual agent is firstly converted into a compact representation by exploiting Transformer encoder and gated recurrent unit (GRU). Then, a social state refinement (SSR) module for modeling social influence between agents is proposed to include more interaction-related features. Subsequently, multiple goals are predicted for each agent, followed by another goal-guided SSR module to incorporate goal information into social interaction. Finally, the multimodal trajectory is forecasted by fusing the features from forward and backward GRU. Experiments on public benchmark datasets are carried out to evaluate the effectiveness of our model. The results demonstrate the superior performance of our model compared with the state-of-the-art methods.

The Internet of Things (IoT) has enormous potential to transform the transport industry by improving passenger experiences, safety, and efficiency. However, the collected spatiotemporal data by traffic sensor network often suffer from missing values (MVs), which affect the overall performance of the system. As a result, accurate recovery of MVs is essential for the successful application of IoT in transportation. In this article, we propose a novel MVs imputation model by integrating low-rank tensor completion (LRTC) and sparse self-representation into a unified framework. In doing so, the global multidimensional correlation, as well as sample self-similarity, can be well leveraged for imputation. In order to solve the proposed model, an elaborate solution algorithm is developed, following the principle of alternating direction method of multipliers (ADMMs). Importantly, each step in ADMM can be implemented efficiently by analyzing the problem structure. Moreover, in order to select proper parameters for the model, an improved harmony search heuristic algorithm based on dual harmonies generation strategy is developed, thus sufficiently considering the information contained in current harmony memory. The experiments on two real-world traffic data are carried out to evaluate the proposed approach. The results verify that in comparison with the classic matrix/tensor completion and other competing algorithms, our method significantly improves the imputation performance.