A5001206420- Infrared Target Detection Methodologies
- Remote-Sensing Image Classification
- Advanced Neural Network Applications
- Advanced Image Fusion Techniques
- Industrial Vision Systems and Defect Detection
- Image Enhancement Techniques
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Visual Attention and Saliency Detection
- Impact of Light on Environment and Health
- UAV Applications and Optimization
- Machine Learning and ELM
- Photovoltaic System Optimization Techniques
- Dental Radiography and Imaging
- Advanced Image and Video Retrieval Techniques
- Gaze Tracking and Assistive Technology
- Advanced Sensor and Control Systems
- Robotics and Sensor-Based Localization
- Social Robot Interaction and HRI
- Image and Signal Denoising Methods
- Orthodontics and Dentofacial Orthopedics
- RNA and protein synthesis mechanisms
- Aerospace and Aviation Technology
- Network Security and Intrusion Detection
- Nasal Surgery and Airway Studies
Xi'an University of Science and Technology
2016-2025
Nanjing University
2024
Nanjing General Hospital of Nanjing Military Command
2024
University of Florida
2019-2022
Changchun Institute of Applied Chemistry
2022
Chinese Academy of Sciences
2021-2022
University of Science and Technology of China
2022
Hebei University
2021
Beihang University
2021
Shandong Institute of Automation
2021
Stretchable ionogels have recently emerged as promising soft and safe ionic conductive materials for use in wearable stretchable electrochemical devices. However, the complex preparation process insufficient thermomechanical stability greatly limit precise rapid fabrication application of ionogels. Here, we report an situ 3D printing method fabricating high-performance single network chemical advanced strain sensors. The consist a special cross-linking constructed by poly(ionic liquid)...
Insulator parallel gaps in a transmission line protect the insulator from arc burn and provide protection lightning. Detection of parallel-gap faults based on aerial inspection images lines may be hindered by various factors, such as complex background, scale distortion, occlusion. In this study, we propose prior knowledge transfer attention mechanism network (PKAMNet) to detect faulty gaps. First, capability PKAMNet learn features different types is improved constructing model visual...
Abstract As technology advances, Human-Robot Interaction (HRI) is boosting overall system efficiency and productivity. However, allowing robots to be present closely with humans will inevitably put higher demands on precise human motion tracking prediction. Datasets that contain both operating in the shared space are receiving growing attention as they may facilitate a variety of robotics human-systems research. track HRI rich information other than video images during daily activities...
Photovoltaic (PV) power-generation technology is an effective approach for alleviating the current energy crisis. However, PV modules are prone to hot-spot faults and shorter service lives because of harsh long-term operating conditions. Therefore, in this study, we propose a bi-branch collaborative training algorithm based on knowledge distillation photovoltaic detection systems, focusing accuracy computational efficiency algorithm. The proposed uses model “teacher student” structure...
A bifunctional bio-photoelectrochemical cell based on a biotic/abiotic hybrid strategy was fabricated as “trading” platform for renewable energy conversion and H 2 O output under mild pH conditions.
Traditional deep-learning-based fusion algorithms usually take the original image as input to extract features, which easily leads a lack of rich details and background information in results. To address this issue, we propose algorithm, based on mutually guided filtering cross-transmission, termed MGFCTFuse. First, an decomposition method is designed, one decomposes into base layer detail layer. Second, order preserve much possible during feature extraction, concatenated with corresponding...
It is critical to classify the landing terrain from aerial images when an unmanned vehicle lands at unprepared site autonomously by using a vision sensor. Owing interference of illumination variations and noises, different terrains may show similar image feature same have feature, which brings great difficulties classification. To address this issue, classification method based on low-rank recovery sparse representation proposed. Color moments Gabor texture are extracted fused construct...
In the retail environment, mobile robots start to serve as customer helpers and human worker assistants, which necessitates a safe, seamless, affective human-robot interaction. Individuals' physical responses during those interactions become crucial factors consider in order improve robots' functionality system productivity. The purpose of this study was assess individuals' typical environment. Eight participants were recruited complete shopping tasks (i.e., cart pushing, item picking,...
Abstract In this paper, we propose a statistical classification method based on discriminant analysis using the first and second moments of positions each nucleotide genome sequences as features, compare its performances with other methods well natural vector for comparative genomic analysis. We examine normality proposed features. The models used including linear analysis, quadratic diagonal k -nearest-neighbor classifier, logistic regression, support machines, trees. All these classifiers...
Lower extremity fatigue is a risk factor for falls and injuries. This paper proposes machine learning system to detect states, which considers the different influences of common daily activities on physical health. A wearable inertial unit devised gait data acquisition. The collected are reorganized into nine subsets dimension reduction, then preprocessed via cycle division, visualization, oversampling. Then, heterogeneous ensemble voting method employed train classifiers. results indicate...
Unmanned aerial vehicles, with their inherent fine attributes, such as flexibility, mobility, and autonomy, play an increasingly important role in the Internet of Things (IoT). Airborne infrared visible image fusion, which constitutes data basis for perception layer IoT, has been widely used various fields electric power inspection, military reconnaissance, emergency rescue, traffic management. However, traditional fusion methods suffer from weak detail resolution. In order to better...
The premise and foundation of autonomous landing relative navigation based on vision for unmanned aerial vehicle (UAV) are accurate detection cooperative target. In order to overcome the problem target susceptible illumination change interference, a new algorithm low rank matrix recovery theory is proposed. our model, an image represented as plus sparse noises, where can be explained by background indicated matrix. By giving image, we extract visual low-level features higher-level construct...