A5101857276- Energy Load and Power Forecasting
- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Image and Signal Denoising Methods
- Neuroscience and Neural Engineering
- Process Optimization and Integration
- Hand Gesture Recognition Systems
- Radiomics and Machine Learning in Medical Imaging
- Tactile and Sensory Interactions
- Genital Health and Disease
- Building Energy and Comfort Optimization
- Robot Manipulation and Learning
- Image Processing Techniques and Applications
- Robotic Locomotion and Control
- Urban Heat Island Mitigation
- Urological Disorders and Treatments
- Robotic Mechanisms and Dynamics
- Urologic and reproductive health conditions
- Advanced Sensor and Energy Harvesting Materials
- Optical Coherence Tomography Applications
- Grey System Theory Applications
- Advanced Neural Network Applications
- Modular Robots and Swarm Intelligence
- Medical Image Segmentation Techniques
Huazhong University of Science and Technology
2022-2024
University of Science and Technology of China
2019
Yuxian People's Hospital
2015
Objective: The objective of this work is to develop a novel method for adaptive calibration the electrode array shifts toward achieving robust myoelectric pattern-recognition control. Methods: This inspired by idea image object detection when high-density surface electromyogram signals recorded from two-dimensional carry rich spatial information and can serve as muscular activation image. A convolutional neural network involving transfer learning (from recognition) used learn activity...
Since the visual system is susceptible to lighting condition and surroundings changes, accuracy for object localization of robot grasping based on servo rather poor so as low success rate bad robustness whole system. In view such phenomenon, in this paper, we propose a method fusing binocular camera accompany with monocular vision, IR sensors, tactile sensors encoders design reliable robust that could offer real-time feedback information. order avoid situation grasping-nothing, use vision...
Pattern-recognition-based myoelectric control systems are not yet widely available due to their limited robustness in real-life situations. Some postprocessing methods were introduced improve the previous studies, but there is lack of investigation into movement transition phases. This article presents a novel method based on pattern (MPT) detection. An image-based index used quantify similarity adjacent feature matrices from high-density surface electromyogram (EMG) signals. MPT detection...
Male circumcision is the most frequently performed procedure by urologists. Safety and efficacy of requires continual improvement. In present study, we investigated safety a new male technique involving use circular stapler. total, 879 consecutive adult patients were randomly divided into 2 groups: 441 underwent stapler circumcision, 438 conventional circumcision. The operative time, pain score, blood loss volume, healing treatment costs, postoperative complications compared between two...
Semi-supervised segmentation is highly significant in 3D medical image segmentation. The typical solutions adopt a teacher-student dual-model architecture, and they constrain the two models' decision consistency on same task. However, scarcity of samples can lower diversity tasks, reducing effectiveness constraint. issue further worsen as weights models gradually become synchronized. In this work, we have proposed to construct diverse joint-tasks using masked modelling for enhancing...