Vehicle trajectory prediction (VTP) is an important task that can enhance the safety and efficiency of autonomous driving. However, existing VTP methods often struggle to fully extract spatiotemporal features, resulting in inaccurate prediction results. To solve this problem, we propose a hierarchical long short-term memory and graph attention network (HLSTM-GAT) model. First, we design a hierarchical network architecture to model different spatiotemporal features. The first-layer network (FLN) focuses on short-term trajectory information and immediate vehicle interactions to generate preliminary candidate trajectories. In the FLN, long short-term memory (LSTM) encoder processes historical trajectories to extract temporal features of vehicles, while a graph attention network (GAT) handles the LSTM-encoded outputs to capture spatial features between vehicles. Second, the second-layer network (SLN) combines the candidate trajectories generated by the FLN with historical trajectories to form comprehensive trajectories for accurate prediction. Subsequently, SLN adopts a GAT to process these comprehensive trajectories to precisely model the spatial relationships between vehicles. Moreover, we propose two distance threshold-based dynamic GAT models to perfectly capture spatial features between vehicles. They construct vehicle spatial interaction relationships at two distinct levels based on real-time distances in the FLN and predicted future distances in the SLN, respectively. These dynamic GAT models effectively filter out irrelevant information and enable the proposed method to consider potential future interactions. Finally, we conduct extensive experiments on two publicly available datasets, and experimental results demonstrate that the proposed method outperforms other state-of-the-art VTP methods in terms of prediction accuracy, robustness and computational efficiency.

A broadband metasurface microwave absorber with a miniaturized size is presented under two mechanisms. A frequency selective surface based on the Minkowski (MSK) fractal structure is constructed to provide a lower resonance frequency with the similar size, and the Salisbury screen is designed to create high-frequency resonance. Then, a second-order MSK fractal ring is loaded to realize impedance matching over the entire bandwidth. The absorption performance of the metasurface absorber (MA) proposed is validated by the equivalent transmission line model, the Smith chart, and the surface current distribution. The simulation results demonstrate an absorption bandwidth of 125% with an absorption rate of >90% over 0.3–1.3 GHz. The thickness of the proposed absorber is 0.075λ, and the size of the unit cell is 0.1λ. The developed absorber exhibits stable absorption performance for both TE and TM polarizations within an incident angle of 40°. The experimental results agree with those of full-wave simulation.

This study proposes an advanced space radiation shielding design method that integrates multi-objective optimization with reliability evaluation to mitigate the impact of harsh space radiation environments on electronic systems. A genetic algorithm is employed to optimize multi-layer shielding configurations with respect to radiation dose reduction, mass efficiency, and structural thickness. To ensure practical applicability, a reliability evaluation framework incorporating uncertainty factors is developed, where shielding designs are considered acceptable when the risk confidence level (CL) remains below 5%. A case study simulating long-duration deep space missions demonstrates that the optimized five-layer shielding configuration reduces the radiation-induced failure rate by approximately 57%, enhancing the long-term reliability of core electronic components to 0.94 over a five-year mission. These findings validate the effectiveness of the proposed approach in supporting the development of reliable, lightweight radiation shielding for future space missions.

In developing modern intelligent transportation systems, integrated sensing and communication (ISAC) technology has become an efficient and promising method for vehicle road services. To enhance traffic safety and efficiency through real-time interaction between vehicles and roads, this paper proposes a searching–deciding scheme for an alternation radar-communication (radar-comm) system. Firstly, its communication performance is derived for a given detection probability. Then, we process the echo data from real-world millimeter-wave (mmWave) radar into four-dimensional (4D) point cloud datasets and thus separate different hybrid modes of single-vehicle and vehicle fleets into three types of scenes. Based on these datasets, an efficient labeling method is proposed to assist accurate vehicle target detection. Finally, a novel vehicle detection scheme is proposed to classify various scenes and accurately detect vehicle targets based on deep learning methods. Extensive experiments on collected real-world datasets demonstrate that compared to benchmarks, the proposed scheme obtains substantial radar performance and achieves competitive communication performance.

Jamming attacks pose a significant threat to aerial communication networks. However, it is challenging to resist various jamming patterns while transferring the existing anti-jamming abilities to a new scenario. Therefore, in this paper, a joint intelligent and generalized anti-jamming problem for multi-hop aerial communication networks is formulated to maximize the transmission success ratio with the consideration of mutual interference. To capture the features of partial observations for the considered model, we utilize a decentralized partially observable Markov decision process (Dec-POMDP) framework to reformulate the original problem, and propose the multi-agent reinforcement learning (MARL)-based algorithm to solve the nonconvex problem. Specifically, we first introduce an adversarial pre-training stage, in which we adopt a jammer population to initialize agents with a generalized anti-jamming strategy. Second, we propose a graph convolutional-based MARL anti-jamming algorithm that employs a parallel Q network to approach the near-optimal anti-jamming strategy. Third, a simple but effective information temporal smoothing (ITS) mechanism is designed to alleviate the unreliability and asynchrony issues associated with information in the confrontational environment. Extensive experiments are conducted to validate that the proposed anti-jamming solution has a better performance compared to the existing methods in terms of transmission success ratio, generalization ability, and energy efficiency.

Traffic flow prediction (TFP) plays a crucial role in optimizing road resource allocation and alleviating traffic congestion. However, existing TFP methods have limitations in capturing the complex spatiotemporal dependencies from traffic data, resulting in low prediction accuracy. To solve this problem, we propose a hybrid long short-term memory (LSTM) and graph attention network (GAT) model based on multi-scale temporal features (MSTF-LG) to predict traffic flow. Firstly, we employ trigonometric functions (TF) to process timestamp information to extract its periodicity and continuity features. These features are then integrated with traffic data to construct a comprehensive input representation. We further extract recent traffic data as well as daily, weekly, and monthly periodic data from this representation. Secondly, we adopt the LSTM encoder to process recent traffic data to extract recent trend features, and apply LSTM encoders to handle daily, weekly and monthly periodic data to extract periodic features. Furthermore, we employ the GAT to process these LSTM-encoded multi-scale temporal features of traffic data to capture dynamic spatial characteristics. The normalized GAT outputs are fed into the LSTM decoder to effectively capture the dynamic temporal changes of traffic data, and then a linear layer transforms the output of the LSTM decoder into TFP results. Finally, experimental results demonstrate that the proposed method outperforms existing TFP methods in terms of prediction accuracy, robustness and computational efficiency.