A5080753841- Musculoskeletal pain and rehabilitation
- Spine and Intervertebral Disc Pathology
- Liver Disease Diagnosis and Treatment
- Industrial Vision Systems and Defect Detection
- Medical Imaging and Analysis
- Hepatitis B Virus Studies
- Image Processing Techniques and Applications
- Image Enhancement Techniques
- Data Stream Mining Techniques
- Pain Management and Treatment
- Advanced Text Analysis Techniques
- Stock Market Forecasting Methods
- Muscle activation and electromyography studies
- Soft Robotics and Applications
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Lung Cancer Diagnosis and Treatment
- Hepatocellular Carcinoma Treatment and Prognosis
- Textile materials and evaluations
- Adversarial Robustness in Machine Learning
- Cardiac and Coronary Surgery Techniques
- Advanced X-ray and CT Imaging
- Surgical Simulation and Training
- Hepatitis C virus research
- EEG and Brain-Computer Interfaces
Guangzhou University
2024
Fudan University
2021-2023
Shenzhen University
2014-2023
Central South University of Forestry and Technology
2022
Central South University
2022
Wuhu Hit Robot Technology Research Institute
2022
In a vascular interventional surgery robot system, accurately pushing the guidewire into patient-specific branch vessel is core step of entire operation, so it has become focus master-slave co-control propulsion and manipulation mechanism. Some robots have been used for delivery guidewire; however, problems such as inability to reliably clamp lack accurate force feedback prevent doctors from using delivery. addition, failure disinfect surgical quickly completely increases risk surgery. This...
Low back pain has been torturing people around the world as a common and chronic disease, main inducement of which is lumbar disc herniation (LDH). To alleviate patients' noninvasively, this paper proposes new spinal rehabilitation exoskeleton. This exoskeleton composed two bands connected by four motor-driven piston pushrods, where range band can be adjusted to adapt with different waistlines. The pushrods provide support forces hold upper body relieve burden lumbar. joints between are...
The lumbar EMG(Electromyography) can effectively reflect the current activity state of human muscles; however, cardiac signals in EMG significantly impacts accuracy analysis. Currently, there are some problems research signal interference removal, such as poor removal effects and low operation efficiencies, which do not meet requirement real-time processing. To solve this problem, paper proposes a method for removing ECG(Electrocardiogram) from based on segmentation SSA(Singular Spectrum...
Abstract Lumbar disc herniation is a common disease that causes low back pain. Due to the high cost of medical diagnosis, as well shortage and uneven distribution resources, system can automatically analyze diagnose lumbar spine Magnetic Resonance Imaging (MRI) becoming an urgent need. This study uses deep learning methods establish classifier herniation. An MRI classification dataset consisting public images presented used train proposed classifier. Because difficulty in applying computer...
The identification of textile fiber materials is a tedious task. Traditional physical or chemical methods rely on specialist knowledge and expensive instruments. Currently, the deep learning-based are limited by lack sufficient image samples. In this paper, we propose method for classification based advanced densely connected convolutional networks (Densenet) using fabric surface images. Firstly, selected small sample dataset containing five types performed some pre-processing, including...
For the problem of noncooperative target tracking in General Aviation's air traffic control system, a novel particle filtering algorithm is proposed. Firstly, order to obtain azimuth information accurately, Infrared sensor inducted search/track by using radar track information, and then new measurement reconstructed utilizing information. Secondly, adaptively 3-D target, an importance density based on maneuver index Finally, simulation results show that proposed effective its performance...
One of the challenges in field medical image classification is expensiveness labeled data. Most previous computer-aided diagnostic methods are based on a paradigm object detection. Such ways need tons sample images with positioning annotations, which always practicing radiologists to process data manually. We focus Chest X-ray(CXR) and propose an effective framework for lung disease diagnosis self-supervised feature extracting mechanism trained constrained contrastive method. Our proposed...
With the continuous development of smart grids, power inspections have become intelligent and sophisticated. This paper proposes a method based on inclined boxes for automatic position recognition diagnosis suspension insulators under visible light channel. The rotational region convolutional neural networks (R2CNN) algorithm is used to extract features large sample images insulators, model trained identify select insulated devices in any direction. open-source TensorFlow software as...