With the development and popularization of Intelligent Transportation Systems (ITS), Vehicle Ad-Hoc Networks (VANETs) have attracted extensive attention as a key technology. In order to achieve real-time monitoring, VANET technology enables vehicles to collect real-time traffic updates through information collection devices and transmit this information to Roadside Units (RSUs), which are processed and integrated by an information processing center. However, high vehicle density leads to a conflict between minimizing the interval for vehicles to send Basic Safety Messages (BSMs) to RSUs and the limited communication resources of VANETs. To address this issue, we propose a MAC protocol based on the 802.11 CSMA/CA mechanism with the Preemptive-Resume Priority scheme. The arbitration device provides preemptive service to data packets with higher priority levels, thereby reducing data transmission delay. Moreover, queuing theory is employed to calculate the total delay for vehicles to send BSMs to a drone receiver, minimizing the BSM transmission interval and achieving minimal delay to meet safety driving requirements. The effectiveness and superiority of this mechanism and algorithm are demonstrated through simulation experiments.

In recent years, the advancement of deep learning technology has led to excellent performance in synthetic aperture radar (SAR) automatic target recognition (ATR) technology. However, due to the interference of speckle noise, the task of classifying SAR images remains challenging. To address this issue, a multi-scale local–global feature fusion network (MFN) integrating a convolution neural network (CNN) and a transformer network was proposed in this study. The proposed network comprises three branches: a CovNeXt-SimAM branch, a Swin Transformer branch, and a multi-scale feature fusion branch. The CovNeXt-SimAM branch extracts local texture detail features of the SAR images at different scales. By incorporating the SimAM attention mechanism to the CNN block, the feature extraction capability of the model was enhanced from the perspective of spatial and channel attention. Additionally, the Swin Transformer branch was employed to extract SAR image global semantic information at different scales. Finally, the multi-scale feature fusion branch was used to fuse local features and global semantic information. Moreover, to overcome the problem of poor accuracy and inefficiency of the model due to empirically determined model hyperparameters, the Bayesian hyperparameter optimization algorithm was used to determine the optimal model hyperparameters. The model proposed in this study achieved average recognition accuracies of 99.26% and 94.27% for SAR vehicle targets under standard operating conditions (SOCs) and extended operating conditions (EOCs), respectively, on the MSTAR dataset. Compared with the baseline model, the recognition accuracy has been improved by 12.74% and 25.26%, respectively. The results demonstrated that Bayes-MFN reduces the inter-class distance of the SAR images, resulting in more compact classification features and less interference from speckle noise. Compared with other mainstream models, the Bayes-MFN model exhibited the best classification performance.

Higher Order Sectorization (HOS), which splits macro base stations into a larger number of sectors, is widely considered in the cellular community as a cost-effective means of improving network capacity. We develop two general and low-complexity analytical models to characterize and relate the uplink performance indicators with key dynamic functionalities and variables, such as fractional power control (FPC), directional antenna radiation patterns and the multi-cell inter-cell interference (ICI). The adopted methodology approximates the uplink ICIs from individual cell sectors by log-normal random variables, of which the statistical parameters can be estimated using approaches that trade-off complexity and accuracy. Furthermore, the aggregate uplink ICI is approximated with a log-normal random variable, from which network performance metrics are computed. Compared to two existing baseline analytical methods the proposed analytical models have improved accuracy. The analytical models are applied to evaluate HOS deployments with both regular and irregular cell geometries. Results on sectorization scaling show it is an effective method in capacity scaling, but at the cost of increased outage probability. The proposed theoretical models can be used as a fast and effective tool for performance assessment and optimization of Long-Term Evolution (LTE) and 5G networks.

Carrier aggregation (CA) technology in the Fifth-Generation (5G) network can be considered as a major feature for high-rate data services, which can be combined with the concept of 5G in unlicensed band (5G-U) for data offloading to further enhance the efficiency of the scarce licensed spectral resource. However, the introduction of cellular services in an unlicensed spectrum can force unlicensed band users to silent mode. Meanwhile, the coexistence among different radio access technologies operating on the same frequency band is a complex issue, especially considering the requirement diversity of quality of service (QoS) in networking. In this paper, we propose an optimal resource allocation mechanism to maximize system performance satisfaction for multiple types of services with different QoS requirements in the 5G-U network with a CA feature to address the challenge. Additionally, the performance of services in Wi-Fi system is protected by reserving the minimum spectrum resource when offloading for the 5G-U network. Analytical results on the mean ergodic achievable rate of Wi-Fi services and the mean packet delay of 5G services are provided to maximize the system performance satisfaction. Numerical results demonstrate the effectiveness of the proposed algorithm, wherein optimal spectrum and power allocation can contribute to the maximum system satisfaction in a 5G-U network with a CA feature.

Background: Efficient decoding of motor imagery (MI) electroencephalogram (EEG) signals is essential for the precise control and practical deployment of brain-computer interface (BCI) systems. Owing to the complex nonlinear characteristics of EEG signals across spatial, spectral, and temporal dimensions, efficiently extracting multidimensional discriminative features remains a key challenge to improving MI-EEG decoding performance. Methods: To address the challenge of capturing complex spatial, spectral, and temporal features in MI-EEG signals, this study proposes a multi-branch deep neural network, which jointly models these dimensions to enhance classification performance. The network takes as inputs both a three-dimensional power spectral density tensor and two-dimensional time-domain EEG signals and incorporates four complementary feature extraction branches to capture spatial, spectral, spatial-spectral joint, and temporal dynamic features, thereby enabling unified multidimensional modeling. The model was comprehensively evaluated on two widely used public MI-EEG datasets: EEG Motor Movement/Imagery Database (EEGMMIDB) and BCI Competition IV Dataset 2a (BCIIV2A). To further assess interpretability, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the spatial and spectral features prioritized by the model. Results: On the EEGMMIDB dataset, it achieved an average classification accuracy of 86.34% and a kappa coefficient of 0.829 in the five-class task. On the BCIIV2A dataset, it reached an accuracy of 83.43% and a kappa coefficient of 0.779 in the four-class task. Conclusions: These results demonstrate that the network outperforms existing state-of-the-art methods in classification performance. Furthermore, Grad-CAM visualizations identified the key spatial channels and frequency bands attended to by the model, supporting its neurophysiological interpretability.

With the rapid development of Internet of Vehicles (IoV) technology, massive data are continuously integrated into intelligent transportation systems, making efficient computing resource allocation a critical challenge for enhancing network performance. Due to the dynamic and real-time characteristics of IoV tasks, existing static offloading strategies fail to effectively cope with the complexity caused by network fluctuations and vehicle mobility. To address this issue, this paper proposes a task offloading algorithm based on the dynamic adjustment of the parallel factor in directed acyclic graphs (DAG), referred to as Dynamic adjustment of Parallel Factor (DPF). By leveraging edge computing, the proposed algorithm adaptively adjusts the parallel factor according to the dependency relationships among subtasks in the DAG, thereby optimizing resource utilization and reducing task completion time. In addition, the algorithm continuously monitors network conditions and vehicle states to dynamically schedule and offload tasks according to real-time system requirements. Compared with traditional static strategies, the proposed method not only significantly reduces task delay but also improves task success rates and overall system efficiency. Extensive simulation experiments conducted under three different task load conditions demonstrate the superior performance of the proposed algorithm. In particular, under high-load scenarios, the DPF algorithm achieves markedly better task completion times and resource utilization compared to existing methods.