Extracting roads from remote sensing images is of significant importance for automatic road network updating, urban planning, and construction. However, various factors in complex scenes (e.g., high vegetation coverage occlusions) may lead to fragmentation in the extracted road networks and also affect the robustness of road extraction methods. This study proposes a multi-scale road extraction method with asymmetric generative adversarial learning (MS-AGAN). First, we design an asymmetric GAN with a multi-scale feature encoder to better utilize the context information in high-resolution remote sensing images (HRSIs). Atrous spatial pyramid pooling (ASPP) and feature fusion are integrated into the asymmetric encoder–decoder structure to avoid feature redundancy caused by multi-level cascading operations and enhance the generator network’s ability to extract fine-grained road information at the pixel level. Second, to maintain road connectivity, topologic features are considered in the pixel segmentation process. A linear structural similarity loss ($L_{SSIM}$) is introduced into the loss function of MS-AGAN, which guides MS-AGAN to generate more accurate segmentation results. Finally, to fairly evaluate the performance of deep models under complex backgrounds, the Bayesian error rate (BER) is introduced into the field of road extraction for the first time. Experiments are conducted via Gaofen-2 (GF-2) high-resolution remote sensing images with high vegetation coverage in the Daxing District of Beijing, China, and the public DeepGlobe dataset. The performance of MS-AGAN is compared with a list of advanced models, including RCFSNet, CoANet, UNet, DeepLabV3+, and DiResNet. The final results show that (1) with respect to road extraction performance, the Recall, F1, and IoU values of MS-AGAN on the Daxing dataset are 2.17%, 0.04%, and 2.63% higher than the baselines. On DeepGlobe, the Recall, F1, and IoU of MS-AGAN improve by 1.12%, 0.42%, and 0.25%, respectively. (2) On road connectivity, the Conn index of MS-AGAN from the Daxing dataset is 46.39%, with an improvement of 0.62% over the baselines, and the Conn index of MS-AGAN on DeepGlobe is 70.08%, holding an improvement of 1.73% over CoANet. The quantitative and qualitative analyses both demonstrate the superiority of MS-AGAN in preserving road connectivity. (3) In particular, the BER of MS-AGAN is 20.86% over the Daxing dataset with a 0.22% decrease compared to the best baselines and 11.77% on DeepGlobe with a 0.85% decrease compared to the best baselines. The proposed MS-AGAN provides an efficient, cost-effective, and reliable method for the dynamic updating of road networks via HRSIs.

In recent years, eHealth systems based on the Internet of Things (IoT) have attracted considerable attention. The wireless body area network (WBAN) is an essential technology of eHealth systems. A major challenge in WBAN is the design of the medium access control (MAC) protocol, which plays a significant role in avoiding collisions, enhancing the energy efficiency, maximizing the network life, and improving the quality of service (QoS) as well as the quality of experience (QoE). In this study, we apply the mobile edge computing (MEC) network architecture to an eHealth system and design a multi-channel MAC protocol for WBAN based on the Markov decision process (MDP). In this protocol, the channel condition and the reward value are considered. By continuously interacting with the environment, the optimal channel resource allocation strategy is generated. Simulation results indicate that the proposed WBAN MAC protocol can adaptively assign different channels to the sensor nodes for data transmission, thereby reducing the collision rate, decreasing the energy consumption, improving the channel utilization, and enhancing the system throughput and QoE.

Multiple unmanned aerial vehicles (UAVs) have a greater potential to be widely used in UAV-assisted IoT applications. UAV formation, as an effective way to improve surveillance and security, has been extensively of concern. The leader–follower approach is efficient for UAV formation, as the whole formation system needs to find only the leader’s trajectory. This paper studies the leader–follower surveillance system. Owing to different scenarios and assignments, the leading velocity is dynamic. The inevitable communication time delays resulting from information sending, communicating and receiving process bring challenges in the design of real-time UAV formation control. In this paper, the design of UAV formation tracking based on deep reinforcement learning (DRL) is investigated for high mobility scenarios in the presence of communication delay. To be more specific, the optimization UAV formation problem is firstly formulated to be a state error minimization problem by using the quadratic cost function when the communication delay is considered. Then, the delay-informed Markov decision process (DIMDP) is developed by including the previous actions in order to compensate the performance degradation induced by the time delay. Subsequently, an extended-delay informed deep deterministic policy gradient (DIDDPG) algorithm is proposed. Finally, some issues, such as computational complexity analysis and the effect of the time delay are discussed, and then the proposed intelligent algorithm is further extended to the arbitrary communication delay case. Numerical experiments demonstrate that the proposed DIDDPG algorithm can significantly alleviate the performance degradation caused by time delays.

With the progress of the eras and the development of science and technology, the requirements of device-to-device (D2D) connectivity increased rapidly. As one important service in future systems, ultra-reliable low-latency communication (URLLC) has attracted attention in many applications, especially in the Internet of Things (IoT), smart cities, and other scenarios due to its characteristics of ultra-low latency and ultra-high reliability. However, in order to achieve the requirement of ultra-low latency, energy consumption often increases significantly. The optimization of energy consumption and the latency of the system in the communication field are often in conflict with each other. In this paper, in order to optimize the energy consumption and the latency jointly under different scenarios, and since the detailed requirements for latency and reliability are diverse in different services, we propose an adaptive UE aggregation (AUA)-based transmission scheme that explores the diversity gain of multiple simultaneous paths to reduce the overall latency of data transmission, wherein multiple paths correspond to multiple coordination nodes. Furthermore, it could provide the feasibility of link adaptation by adjusting the path number according to the real transmission environment. Then, unnecessary energy waste could be avoided. To evaluate the performance, the energy-delay product (EDP) is proposed for the latency and energy comparison. The provided simulation results align with the numerical data. Through the analysis, it can be proven that the proposed scheme can achieve a joint optimization of latency and energy consumption to meet different types of URLLC services.

With the rapid development of UAV technology, the research of optimal UAV formation tracking has been extensively studied. However, the high maneuverability and dynamic network topology of UAVs make formation tracking control much more difficult. In this paper, considering the highly dynamic features of uncertain time-varying leader velocity and network-induced delays, the optimal formation control algorithms for both near-equilibrium and general dynamic control cases are developed. First, the discrete-time error dynamics of UAV leader–follower models are analyzed. Next, a linear quadratic optimization problem is formulated with the objective of minimizing the errors between the desired and actual states consisting of velocity and position information of the follower. The optimal formation tracking problem of near-equilibrium cases is addressed by using a backward recursion method, and then the results are further extended to the general dynamic case where the leader moves at an uncertain time-varying velocity. Additionally, angle deviations are investigated, and it is proved that the similar state dynamics to the general case can be derived and the principle of control strategy design can be maintained. By using actual real-world data, numerical experiments verify the effectiveness of the proposed optimal UAV formation-tracking algorithm in both near-equilibrium and dynamic control cases in the presence of network-induced delays.

With the widespread deployment of 5G technology, high-precision positioning in global navigation satellite system (GNSS)-denied environments is a critical yet challenging task for emerging 5G applications, enabling enhanced spatial resolution, real-time data acquisition, and more accurate geolocation services. Traditional methods relying on single-source measurements like received signal strength information (RSSI) or time of arrival (TOA) often fail in complex multipath conditions. To address this, the positional encoding multi-scale residual network (PE-MSRN) is proposed, a novel deep learning framework that enhances positioning accuracy by deeply mining spatial information from 5G channel state information (CSI). By designing spatial sampling with multigranular data and utilizing multi-source information in 5G CSI, a dataset covering a variety of positioning scenarios is proposed. The core of PE-MSRN is a multi-scale residual network (MSRN) augmented by a positional encoding (PE) mechanism. The positional encoding transforms raw angle of arrival (AOA) data into rich spatial features, which are then mapped into a 2D image, allowing the MSRN to effectively capture both fine-grained local patterns and large-scale spatial dependencies. Subsequently, the PE-MSRN algorithm that integrates ResNet residual networks and multi-scale feature extraction mechanisms is designed and compared with the baseline convolutional neural network (CNN) and other comparison methods. Extensive evaluations across various simulated scenarios, including indoor autonomous driving and smart factory tool tracking, demonstrate the superiority of our approach. Notably, PE-MSRN achieves a positioning accuracy of up to 20 cm, significantly outperforming baseline CNNs and other neural network algorithms in both accuracy and convergence speed, particularly under real measurement conditions with higher SNR and fine-grained grid division. Our work provides a robust and effective solution for developing high-fidelity 5G positioning systems.