With the evolution of Internet of Things (IoT), some IoT nodes possess a certain degree of mobility, and the gains of the corresponding channels vary dramatically, incurring the energy supply problem for IoT nodes. To tackle this problem, we study a wireless-powered IoT (WPIoT), where a static $U$ -antenna hybrid access point (HAP) coordinates the wireless energy transfer to mobile single-antenna IoT nodes and receives data from these IoT nodes. When IoT nodes have sufficient energy for transmitting generated data packets, we propose a generated data packets-based throughput maximization (GDPTM) algorithm for the short-term throughput maximization, and the GDPTM algorithm is designed to save nodes’ energy while transmitting all the generated data packets. Through monotonicity analysis, we prove the existence of the optimal transmit power that maximizes the throughput. When IoT nodes do not have sufficient energy for transmitting generated data packets, we propose a deep deterministic policy gradient (DDPG)-based multinode resource allocation (DMRA) algorithm. Through designing the action space, we find that the HAP under the DMRA algorithm manages the time, transmit power, and channel allocation of IoT nodes to improve the throughput. Numerical results validate that, when IoT nodes have sufficient energy, the GDPTM algorithm saves nodes’ energy and improves the throughput. When IoT nodes do not have sufficient energy, the DMRA algorithm also improves the throughput.

In this paper, we consider a wireless-powered communication network (WPCN) where one mobile hybrid access point (HAP) coordinates the wireless energy transfer to sensor nodes and receives data from sensor nodes, which are powered exclusively by the harvested wireless energy. As the harvest-then-transmit protocol is employed by sensor nodes, a major challenge lies on the tradeoff between achievable throughput and energy harvesting opportunity of sensor nodes. Confronting this challenge, we develop an energy threshold approach by jointly considering geographic locations and energy states of sensor nodes, where wireless energy transfer occurs when none of the sensor nodes in the range of data transmission has more energy than the threshold, otherwise data transmission from one randomly chosen qualified sensor node to the HAP occurs. By comparing the range of energy harvesting and that of data transmission, we divide the network topology into two cases for throughput analysis, and formulate the energy states of sensor nodes as Markov chain processes with different energy state spaces in the two cases. Through monotonicity analysis of achievable throughput and probability distribution of energy states, we prove the existence of the optimal energy threshold that maximizes the achievable throughput, and find that the achievable throughput under infinite battery size could be viewed as the upper bound of that under the limited battery size. Finally, simulation results validate theoretical results of the optimal energy threshold, and show the impacts of system parameters on the achievable throughput.

In the manufacturing process of industrial robots, the defect detection of raw materials includes two types of tasks, which makes the defect detection guarantee its accuracy. It also makes the defect detection task challenging in practical work. In analyzing the disadvantages of the existing defect detection task methods, such as low precision and low generalization ability, a detection method on the basis of attention mechanism and dilated convolution module is proposed. In order to effectively extract features, a two-stage detection framework is chosen by applying Resnet50 as the pre-training network of our model. With this foundation, the attention mechanism and dilated convolution are utilized. With the attention mechanism, the network can focus on the features of effective regions and suppress the invalid regions during detection. With dilated convolution, the receptive field of the model can be increased without increasing the calculation amount of the model. As a result, it can achieve a larger receptive field, which will obtain more dense data and improve the detection effect of small target defects. Finally, great experiments are conducted on the NEU-DET dataset. Compared with the baseline network, the proposed method in this paper achieves 81.79% mAP, which are better results.

The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.

This paper aims at helping researchers develop low-noise ECG monitors and analyze existing solutions for eliminating noise in ECG signals. A brief introduction of ECG signal, main kinds of noise in ECG signal and a summary of different kinds of low noise solutions is given. The components of the ECG signal and the origin of noise in the ECG signal are analyzed first. In order to find optimized solutions for eliminating the noise, highly effective solutions are listed and analyzed. Solutions are divided into three main directions, which are circuit design, signal processing and machine learning. Specific practical examples from former research and analyses for each direction help the reader understand and select different ways of eliminating noise in ECG signals. After introducing three directions, a summary and further improvement are given to help readers have a horizontal comparison between solutions.