For autonomous vehicles driving on roads, future trajectories of surrounding traffic agents (e.g., vehicles, bicycles, pedestrians) are essential information. The prediction of future trajectories is challenging as the motion of traffic agents is constantly affected by spatial-temporal interactions from agents and road infrastructure. To take those interactions into account, this study proposes a Graph Attention Transformer (Gatformer) in which a traffic scene is represented by a sparse graph. To maintain the spatial and temporal information of traffic agents in a traffic scene, Convolutional Neural Networks (CNNs) are utilized to extract spatial features and a position encoder is proposed to encode the spatial features and the corresponding temporal features. Based on the encoded features, a Graph Attention Network (GAT) block is employed to model the agent-agent and agent-infrastructure interactions with the help of attention mechanisms. Finally, a Transformer network is introduced to predict trajectories for multiple agents simultaneously. Experiments are conducted over the Lyft dataset and state-of-the-art methods are introduced for comparison. The results show that the proposed Gatformer could make more accurate predictions while requiring less inference time than its counterparts.

Despite the advancements in the technologies of autonomous driving, it is still challenging to study the safety of a self-driving vehicle. Trajectory prediction is one core function of an autonomous vehicle. This study proposes an Attention-based Interaction-aware Trajectory Prediction (AI-TP) for traffic agents around the autonomous vehicle. With an encoder-decoder architecture, the AI-TP model uses Graph Attention Networks (GAT) to describe the interactions of traffic agents and Convolutional Gated Recurrent Units (ConvGRU) to carry out predictions. Based on the attention mechanism, the AI-TP model con-structs graphs from various traffic scenes to predict trajectories of different types of traffic agents. Traffic data from both the high-way (i.e., NGSIM) and urban road areas (i.e., ApolloScape and Argoverse) are used to evaluate the performance of the AI-TP model. Numerical results demonstrate that the AI-TP model requires less inference time and achieves better prediction accuracy than state-of-the-art methods. Specifically, the AI-TP model improves the performance by 36% on average with much less inference time on the NGSIM dataset, which shows the promise of predicting trajectories under various scenarios. The code of the AI-TP model will be available at https://github.com/KP-Zhang/AI-TP.

Intelligent Transportation Systems (ITS) research and applications benefit from accurate short-term traffic state forecasting. To improve the forecasting accuracy, this paper proposes a deep learning based multitask learning Gated Recurrent Units (MTL-GRU) with residual mappings. To enhance the performance of the MTL-GRU, feature engineering is introduced to select the most informative features for the forecasting. Then, based on real-world datasets, numerical results show that the MTL-GRU can well estimate traffic flow and speed simultaneously, and performs better than other counterparts. Experiments also show that the deep learning based MTL-GRU model can overpower the bottleneck caused by enlarging training datasets and continue to gain benefits. The results suggest the proposed MTL-GRU model with residual mappings is promising to forecast short-term traffic state.

Diabetes remains a great threat to human beings’ health and its world prevalence is projected to reach 9.9% by 2045. At present, the detection methods used are often invasive, cumbersome and time-consuming, thus increasing the burden on patients. In this paper, we propose a novel noninvasive and low-cost biosensor capable of detecting glucose in human sweat using enzyme-based electrodes for point-of-care uses. Specifically, an electrochemical method is applied for detection and the electrodes are covered with multilayered films including ferrocene-polyaniline (F-P), multi-walled carbon nanotubes (MWCNTs) and glucose oxidase (GOx) on Cu substrates (GOx/MWCNTs/F-P/Cu). The coated layers enhance the immobilization of GOx, increase the conductivity of the anode and improve the electrochemical properties of the electrode. Compared with the Cu electrode and the F-P/Cu electrode, a maximum peak current is obtained when the MWCNTs/F-P/Cu electrode is applied. We also study its current response by cyclic voltammetry (CV) at different concentrations (0–2.0 mM) of glucose solution. The best current response is obtained at 0.25 V using chronoamperometry. The effective working lifetime of an electrode is up to 8 days. Finally, to demonstrate the capability of the electrode, a portable, miniaturized and integrated detection device based on the GOx/MWCNTs/F-P/Cu electrode is developed. The results exhibit a short response time of 5 s and a correlation coefficient R² of 0.9847 between the response current of sweat with blood glucose concentration. The LOD is of 0.081 mM and the reproducibility achieved in terms of RSD is 3.55%. The sweat glucose sensor is noninvasive and point-of-care, which shows great development potential in the health examination and monitoring field.