Convolutional neural networks have achieved good results in target detection in many application scenarios, but convolutional neural networks still face great challenges when facing scenarios with small target sizes and complex background environments. To solve the problem of low accuracy of infrared weak target detection in complex scenes, and considering the real-time requirements of the detection task, we choose the YOLOv5s target detection algorithm for improvement. We add the Bottleneck Transformer structure and CoordConv to the network to optimize the model parameters and improve the performance of the detection network. Meanwhile, a two-dimensional Gaussian distribution is used to describe the importance of pixel points in the target frame, and the normalized Guassian Wasserstein distance (NWD) is used to measure the similarity between the prediction frame and the true frame to characterize the loss function of weak targets, which will help highlight the targets with flat positional deviation transformation and improve the detection accuracy. Finally, through experimental verification, compared with other mainstream detection algorithms, the improved algorithm in this paper significantly improves the target detection accuracy, with the mAP reaching 96.7 percent, which is 2.2 percentage points higher compared with Yolov5s.

In this paper, we propose a new filtering switch with excellent working performance made using an optimized coupled microstrip line. Upon analyzing the RF (radio frequency) front-end’s system structure, the switching device was simplified to a diode, which was connected to the microstrip circuit we designed to become a filter switch with both filtering and shutdown functions. First, we obtained an equivalent schematic of this filtering switch based on the relevant microstrip line theory. This switch consists of two coupled microstrip circuits, parallel-coupled feed lines and coupled-line stub-load resonators (CLSs), and a PIN diode. Second, the operating principle is described by the switching of the operating states, with ideal shutdown performance in the off state and considerable selectivity and excellent out-of-band rejection performance in the filtered state. Finally, a prototype filtering switch with a center frequency of 0.8 GHz was designed and tested. After subsequent optimization and improvement, the simulation and test performance results were noticeably consistent, consequently verifying the performance requirements of this filtering switch in two operating states in the center frequency band.

UAVs and reconfigurable intelligent surfaces (RISs) have emerged as promising solutions to enhance communication coverage and performance. However, existing studies primarily focus on optimizing the amplitude and phase shift of a STAR-RIS without considering the impact of varying UAV hovering angles on signal reflection and transmission. In this paper, we propose a novel STAR-RIS-assisted UAV service enhancement mechanism that dynamically adjusts reflection/transmission regions based on the real-time user distribution, significantly improving the channel quality for both edge and occluded users. This work is the first to jointly optimize the phase and amplitude of the STAR-RIS, the UAV flight trajectory, and the hovering angle, addressing the critical challenge of co-channel interference caused by dynamically partitioned service areas. The complex optimization problem is decomposed into subproblems, where the UAV flight trajectory is optimized using the Chained Lin–Kernighan (CLK) algorithm and the STAR-RIS parameters and UAV hovering angle are optimized using the TD3 algorithm. The experimental results show that the proposed mechanism effectively reduces the system service time and user transmission time, outperforming traditional methods.

This paper proposes a collaborative optimization strategy of regenerative braking in heavy-duty electric logistics vehicles under complex driving conditions to improve energy recovery efficiency. Based on the actual operational data of 18-ton electric trucks in the southwestern region of China, three driving scenarios for heavy commercial vehicles are determined via the K-Means clustering algorithm. Key features are extracted using Recursive Feature Elimination and employed to train a Learning Vector Quantization neural network for precise real-time condition recognition. The identified driving condition parameters, including vehicle speed, remaining battery power, and braking force, collectively regulate the intensity of regenerative braking. Simulation results under double-WTVC (World Transient Vehicle Cycle) conditions indicate that the proposed strategy can effectively adapt regenerative braking behavior to diverse road conditions. In comparison with conventional control methods, this approach enhances battery energy recovery efficiency by 5.8% while preventing control discontinuities.