A5101581665- Advanced Neural Network Applications
- Muscle activation and electromyography studies
- Advanced SAR Imaging Techniques
- Prosthetics and Rehabilitation Robotics
- Stroke Rehabilitation and Recovery
- Anomaly Detection Techniques and Applications
- Advanced Image Processing Techniques
- EEG and Brain-Computer Interfaces
- Video Surveillance and Tracking Methods
- Machine Fault Diagnosis Techniques
- Human Pose and Action Recognition
- Machine Learning and ELM
- Underwater Acoustics Research
- Gamma-ray bursts and supernovae
- Image Enhancement Techniques
- Radar Systems and Signal Processing
- Generative Adversarial Networks and Image Synthesis
- Microwave Dielectric Ceramics Synthesis
- Advanced Sensor and Energy Harvesting Materials
- Engineering Diagnostics and Reliability
- Advanced Algorithms and Applications
- Non-Invasive Vital Sign Monitoring
- Traditional Chinese Medicine Studies
- Advanced Sensor and Control Systems
- Automated Road and Building Extraction
Nanchang University
2020-2025
Nanjing University of Science and Technology
2020-2024
Beijing Normal University
2014-2024
Yanshan University
2023
Shandong Institute of Business and Technology
2021-2022
Air Force Engineering University
2010-2019
Heilongjiang University of Technology
2018
Shandong Normal University
2014
South China Agricultural University
2011-2013
Tân Tạo University
1999
Self-powered photodetectors (PDs) with distinguishable wavelength detection have great application potential in intelligent optoelectronics. However, slow response speed, low responsivity, and signal interference prevent its development applications. Here, an asymmetric bipolar p-NiO/n-ZnO/p-Si heterojunction is designed as a wavelength-distinguishable PD by using two tandem p–n junctions to reduce the effectively separate photo-generated carriers. Bidirectional transient photocurrents are...
Abstract Image inpainting networks based on deep learning techniques have been widely used in many important fields. However, most fail to generate desirable repaired images. This may be due their failure extract effective features and accurately assign high weights the undamaged regions. To alleviate these problems, an image network gated convolution multi‐level attention mechanism (IIN‐GCMAM) is proposed this paper. follows encoder–decoder architecture, consisting of encoder (GC‐encoder)...
Abstract Recently, deep learning techniques have significantly bolstered the advancement of intelligent fault diagnosis. However, in engineering practice, limited availability samples poses considerable challenges to existing methods. To address this problem, a hierarchical Transformer-based adaptive metric and joint-learning network (HTAMJN) is suggested paper. Firstly, progressive fusion encoder based on orthogonal self-attention devised, which effectively enhances model’s attention local...
In recent years, surface electromyogram signals have been increasingly used to operate wearable devices. These devices can aid help workers or soldiers lower the load in task boost efficiency. However, achieving effective signal prediction has always a challenge. It is critical use an appropriate preprocessing method and algorithm when developing controller that accurately predict control human movements real time. For this purpose, article investigates effect of various methods algorithms...
In the present study, we used a transformer model and fusion of biosignals to estimate rotational acceleration in elbow shoulder joints. To achieve our study objectives, proposed mechanomyography (MMG) signal isolation technique based on variational mode decomposition (VMD) algorithm. Our results show that VMD algorithm delivered excellent performance MMG extraction compared commonly empirical (EMD). addition, found models estimates joint were more precise than those produced by mainstream...
Vehicle re-identification (Vehicle Re-ID) aims at retrieving and tracking the specified target vehicle with multiple other cameras, which can provide help in checking violations catching fugitives, but there are still following problems that need to be solved urgently. First, existing collected Re-ID data often have low resolution blur local regions, so algorithm cannot accurately extract subtle feature representations. In addition, small features easy cause disappearance of under operation...
Abstract Targeting the problem of high real-time requirements in astronomical data processing, this paper proposes a early warning model for light curves based on Gated Recurrent Unit (GRU) network. Using memory function GRU network, prediction curve is established, and trained using collected data, so that can predict star magnitude value next moment historical data. In paper,we calculate difference between actual observation set threshold. If exceeds threshold, at considered to be an...
Abstract In order to solve the problem of large test workload by using traditional mine ventilation measurement methods, impact support methods on resistance coefficient was analyzed emphatically. The Particle Swarm Optimization Support Vector Machine(PSO-SVM)algorithm used model three types supported roadways: wood-supported roadways, I-steel-supported and bolt-net-supported roadways. roadway attribute parameters concrete were analyzed, PSO-SVM regression supporting friction under specific...
We fabricated the low loss Li3Mg2NbO6-xV2O5 (x = 0.25–1.25 wt%)ceramics by solid-state reaction procedure and discussed impacts of V2O5 addition on phase structure, sintering characteristics, microstructure, grain growth, size microwave dielectric characterizations ceramics. Single-phase Li3Mg2NbO6 orthorhombic structure was obtained for all compositions substitution V5+ ions Nb5+ occurred. Homogeneous dense microstructures with ~11.2 μm could be observed when sintered at 925 °C, indicating...