Track Deflection Monitoring for Railway Construction Based on Dynamic Brillouin Optical Time-Domain Reflectometry.

Real-time online monitoring of track deformation during railway construction is crucial for ensuring the safe operation of trains. However, existing monitoring technologies struggle to effectively monitor both static and dynamic events, often resulting in high false alarm rates. This paper presents a monitoring technology for track deformation during railway construction based on dynamic Brillouin optical time-domain reflectometry (Dy-BOTDR), which effectively meets requirements in the monitoring of both static and dynamic events of track deformation.

On Security Performance of SWIPT Multi-User Jamming Based on Mixed RF/FSO Systems with Untrusted Relay.

This paper presents research on the security performance of a multi-user interference-based mixed RF/FSO system based on SWIPT untrusted relay. In this work, the RF and FSO channels experience Nakagami-m fading distribution and Málaga (M) turbulence, respectively. Multiple users transmit messages to the destination with the help of multiple cooperating relays, one of which may become an untrusted relay as an insider attacker.

Structural Design and Electromagnetic Performance Analysis of Octupole Active Radial Magnetic Bearing.

This study addresses the challenges of magnetic circuit coupling and control complexity in active radial magnetic bearings (ARMBs) by systematically investigating the electromagnetic performance of four magnetic pole configurations (NNSS, NSNS, NNNN, and SSSS). Initially, equivalent magnetic circuit modeling and finite element analysis (FEA) were employed to analyze the magnetic circuit coupling phenomena and their effects on the magnetic flux density distribution for each configuration. Subsequently, the air gap flux density and electromagnetic force were quantified under rotor eccentricity caused by unbalanced disturbances, and the dynamic performances of the ARMBs were evaluated for eccentricity along the x-axis and at 45°.

p-CuO/n-ZnO Heterojunction Pyro-Phototronic Photodetector Controlled by CuO Preparation Parameters.

The combination of ZnO with narrow bandgap materials such as CuO is now a common method to synthesize high-performance optoelectronic devices. This study focuses on optimizing the performance of p-CuO/n-ZnO heterojunction pyroelectric photodetectors, fabricated through magnetron sputtering, by leveraging the pyro-phototronic effect. The devices' photoresponse to UV (365 nm) and visible (405 nm) lasers is thoroughly examined.

EGNet: 3D Semantic Segmentation Through Point-Voxel-Mesh Data for Euclidean-Geodesic Feature Fusion.

With the advancement of service robot technology, the demand for higher boundary precision in indoor semantic segmentation has increased. Traditional methods of extracting Euclidean features using point cloud and voxel data often neglect geodesic information, reducing boundary accuracy for adjacent objects and consuming significant computational resources. This study proposes a novel network, the Euclidean-geodesic network (EGNet), which uses point cloud-voxel-mesh data to characterize detail, contour, and geodesic features, respectively.

A User Association and Resource Allocation Algorithm for UAV-Assisted Smart Grid.

Recently, massive intelligent applications have emerged for the smart grid (SG), such as inspection and sensing. To support these applications, there have been high requirements on wireless communication for the SG, especially in remote areas. To tackle these challenges, a UAV-assisted heterogeneous wireless network is proposed in this paper for the SG, where multiple UAVs and a macro base station collaboratively provide a wide range of communication services.

Endpoint Distribution Modeling-Based Capture Algorithm for Interfering Multi-Target.

In physical spaces, pointing interactions cannot rely on cursors, rays, or virtual hands for feedback as in virtual environments; users must rely solely on their perception and experience to capture targets. Currently, research on modeling target distribution for pointing interactions in physical space is relatively sparse. Area division is typically simplistic, and theoretical models are lacking.

Binary Transformer Based on the Alignment and Correction of Distribution.

Transformer is a powerful model widely used in artificial intelligence applications. It contains complex structures and has extremely high computational requirements that are not suitable for embedded intelligent sensors with limited computational resources. The binary quantization technology takes up less memory space and has a faster calculation speed; however, it is seldom studied for the lightweight transformer.

A Green Computing Business Aggregation Strategy for Low Earth Orbit Satellite Networks.

This paper proposes a green computing strategy for low Earth orbit (LEO) satellite networks (LSNs), addressing energy efficiency and delay optimization in dynamic and energy-constrained environments. By integrating a Markov Decision Process (MDP) with a Double Deep Q-Network (Double DQN) and introducing the Energy-Delay Ratio (EDR) metric, this study effectively quantifies and balances energy savings with delay costs. Simulations demonstrate significant energy savings, with reductions of up to 47.

High-Performance CP Magneto-Electric Dipole Antenna Fed by Printed Ridge Gap Waveguide at Millimeter-Wave.

This paper presents a high-performance circularly polarized (CP) magneto-electric (ME) dipole antenna optimized for wideband millimeter-wave (mm-wave) frequencies, specifically targeting advancements in 5G and 6G technologies. The CP antenna is excited through a transverse slot in a printed ridge gap waveguide (PRGW), which operates in a quasi-transverse electromagnetic (Q-TEM) mode. Fabricated on Rogers RT 3003 substrate, selected for its low-loss and cost-effective properties at high frequencies, the design significantly enhances both impedance and axial ratio (AR) bandwidths.

Dynamic Boundary Estimation of Suspended Sediment Plume Benefit by the Autonomous Underwater Vehicle Sensing.

The suspended sediment plume generated in the deep-sea mining process significantly impacts the marine environment and seabed ecosystem. Accurate boundary estimation can effectively monitor the scope of environmental impact, guiding mining operations to prevent ecological damage. In this paper, we propose a dynamic boundary estimation approach for the suspended sediment plume, leveraging the sensing capability of the Autonomous Underwater Vehicles (AUVs).

HKAN: A Hybrid Kolmogorov-Arnold Network for Robust Fabric Defect Segmentation.

Currently, fabric defect detection methods predominantly rely on CNN models. However, due to the inherent limitations of CNNs, such models struggle to capture long-distance dependencies in images and fail to accurately detect complex defect features. While Transformers excel at modeling long-range dependencies, their quadratic computational complexity poses significant challenges.

DSiam-CnK: A CBAM- and KCF-Enabled Deep Siamese Region Proposal Network for Human Tracking in Dynamic and Occluded Scenes.

Despite the accuracy and robustness attained in the field of object tracking, algorithms based on Siamese neural networks often over-rely on information from the initial frame, neglecting necessary updates to the template; furthermore, in prolonged tracking situations, such methodologies encounter challenges in efficiently addressing issues such as complete occlusion or instances where the target exits the frame. To tackle these issues, this study enhances the SiamRPN algorithm by integrating the convolutional block attention module (CBAM), which enhances spatial channel attention. Additionally, it integrates the kernelized correlation filters (KCFs) for enhanced feature template representation.

Lightweight Siamese Network with Global Correlation for Single-Object Tracking.

Recent advancements in the field of object tracking have been notably influenced by Siamese-based trackers, which have demonstrated considerable progress in their performance and application. Researchers frequently emphasize the precision of trackers, yet they tend to neglect the associated complexity. This oversight can restrict real-time performance, rendering these trackers inadequate for specific applications.

Wavelet-Driven Multi-Band Feature Fusion for RGB-T Salient Object Detection.

RGB-T salient object detection (SOD) has received considerable attention in the field of computer vision. Although existing methods have achieved notable detection performance in certain scenarios, challenges remain. Many methods fail to fully utilize high-frequency and low-frequency features during information interaction among different scale features, limiting detection performance.

MambaPose: A Human Pose Estimation Based on Gated Feedforward Network and Mamba.

Human pose estimation is an important research direction in the field of computer vision, which aims to accurately identify the position and posture of keypoints of the human body through images or videos. However, multi-person pose estimation yields false detection or missed detection in dense crowds, and it is still difficult to detect small targets. In this paper, we propose a Mamba-based human pose estimation.

A Lightweight and Small Sample Bearing Fault Diagnosis Algorithm Based on Probabilistic Decoupling Knowledge Distillation and Meta-Learning.

Rolling bearings play a crucial role in industrial equipment, and their failure is highly likely to cause a series of serious consequences. Traditional deep learning-based bearing fault diagnosis algorithms rely on large amounts of training data; training and inference processes consume significant computational resources. Thus, developing a lightweight and suitable fault diagnosis algorithm for small samples is particularly crucial.

Comprehensive Improvement of Binocular Structured Light Calibration Method Based on Radical-Conservative Cooperative Particle Swarm.

To achieve high-precision 3D reconstruction, a comprehensive improvement has been made to the binocular structured light calibration method. During the calibration process, the calibration object's imaging quality and the camera parameters' nonlinear optimization effect directly affect the caibration accuracy. Firstly, to address the issue of poor imaging quality of the calibration object under tilted conditions, a pixel-level adaptive fill light method was designed using the programmable light intensity feature of the structured light projector, allowing the calibration object to receive uniform lighting and thus improve the quality of the captured images.

Humidity-Activated Ammonia Sensor Based on Carboxylic Functionalized Cross-Linked Hydrogel.

Owing to its extensive use and intrinsic toxicity, NH detection is very crucial. Moisture can cause significant interference in the performance of sensors, and detecting NH in high humidity is still a challenge. In this work, a humidity-activated NH sensor was prepared by urocanic acid (URA) modifying poly (ethylene glycol) diacrylate (PEGDA) via a thiol-ene click cross-linking reaction.

Distributed Consensus Control for Discrete-Time T-S Fuzzy Multiple-Agent Systems Based on an Unknown Input Observer.

This paper investigates a consensus problem for a class of T-S fuzzy multiple-agent systems (MASs) with unknown input (UI). To begin with, an unknown input observer (UIO) is able to asymptotically estimate the system state and the UI is designed for each agent. In order to construct the UIO, the state interval estimation is obtained by first using zonotope theory.

A Registration Method Based on Ordered Point Clouds for Key Components of Trains.

Point cloud registration is pivotal across various applications, yet traditional methods rely on unordered point clouds, leading to significant challenges in terms of computational complexity and feature richness. These methods often use k-nearest neighbors (KNN) or neighborhood ball queries to access local neighborhood information, which is not only computationally intensive but also confines the analysis within the object's boundary, making it difficult to determine if points are precisely on the boundary using local features alone. This indicates a lack of sufficient local feature richness.

G-RCenterNet: Reinforced CenterNet for Robotic Arm Grasp Detection.

In industrial applications, robotic arm grasp detection tasks frequently suffer from inadequate accuracy and success rates, which result in reduced operational efficiency. Although existing methods have achieved some success, limitations remain in terms of detection accuracy, real-time performance, and generalization ability. To address these challenges, this paper proposes an enhanced grasp detection model, G-RCenterNet, based on the CenterNet framework.

Development of a Virtual Robot Rehabilitation Training System for Children with Cerebral Palsy: An Observational Study.

This paper presents the development of a robotic system for the rehabilitation and quality of life improvement of children with cerebral palsy (CP). The system consists of four modules and is based on a virtual humanoid robot that is meant to motivate and encourage children in their rehabilitation programs. The efficiency of the developed system was tested on two children with CP.

Empowering Privacy Through Peer-Supervised Self-Sovereign Identity: Integrating Zero-Knowledge Proofs, Blockchain Oversight, and Peer Review Mechanism.

Frequent user data breaches and misuse incidents highlight the flaws in current identity management systems. This study proposes a blockchain-based, peer-supervised self-sovereign identity (SSI) generation and privacy protection technology. Our approach creates unique digital identities on the blockchain, enabling secure cross-domain recognition and data sharing and satisfying the essential users' requirements for SSI.

DCA-YOLOv8: A Novel Framework Combined with AICI Loss Function for Coronary Artery Stenosis Detection.

Coronary artery stenosis detection remains a challenging task due to the complex vascular structure, poor quality of imaging pictures, poor vessel contouring caused by breathing artifacts and stenotic lesions that often appear in a small region of the image. In order to improve the accuracy and efficiency of detection, a new deep-learning technique based on a coronary artery stenosis detection framework (DCA-YOLOv8) is proposed in this paper. The framework consists of a histogram equalization and canny edge detection preprocessing (HEC) enhancement module, a double coordinate attention (DCA) feature extraction module and an output module that combines a newly designed loss function, named adaptive inner-CIoU (AICI).