A5033076846- Surgical Simulation and Training
- Soft Robotics and Applications
- Medical Image Segmentation Techniques
- Advanced X-ray and CT Imaging
- Medical Imaging and Analysis
- Retinal Imaging and Analysis
- Advanced Neural Network Applications
- Anatomy and Medical Technology
- Intraocular Surgery and Lenses
- Teleoperation and Haptic Systems
- Augmented Reality Applications
- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Robotics and Sensor-Based Localization
- Stroke Rehabilitation and Recovery
- Robot Manipulation and Learning
- Prosthetics and Rehabilitation Robotics
- Robotic Locomotion and Control
- 3D Shape Modeling and Analysis
- Hand Gesture Recognition Systems
- Digital Imaging for Blood Diseases
- Glaucoma and retinal disorders
- Robotic Path Planning Algorithms
- Coronary Interventions and Diagnostics
- Retinal and Optic Conditions
Chinese Academy of Sciences
2016-2025
Institute of Automation
2015-2025
Shandong Institute of Automation
2016-2025
Beijing Information Science & Technology University
2023-2024
Zhengzhou University
2019-2023
Henan University of Engineering
2022-2023
Sun Yat-sen University
2023
University of Chinese Academy of Sciences
2016-2022
Beijing Academy of Artificial Intelligence
2020-2022
Beijing Institute of Technology
2008-2011
Google Colaboratory (also known as Colab) is a cloud service based on Jupyter Notebooks for disseminating machine learning education and research.It provides runtime fully configured deep free-of-charge access to robust GPU.This paper presents detailed analysis of regarding hardware resources, performance, limitations.This performed through the use accelerating computer vision other GPU-centric applications.The chosen test-cases are parallel tree-based combinatorial search two applications:...
The automatic defects detection for solar cell electroluminescence (EL) images is a challenging task, due to the similarity of defect features and complex background features. To address this problem, in article novel complementary attention network (CAN) designed by connecting channel-wise subnetwork with spatial sequentially, which adaptively suppresses noise highlights simultaneously employing advantage channel position In CAN, applies convolution operation integrate concatenated...
Adversary models have been fundamental to the various cryptographic protocols and methods. However, their use in most of branches research computer science is comparatively restricted, primarily case cyberphysical security (e.g., vulnerability studies, position confidentiality). In this article, we propose an energy-aware green adversary model for its smart industrial environment through achieving confidentiality. Even though, mutually hardware software parts systems can be improved decrease...
Segmentation for tracking surgical instruments plays an important role in robot-assisted surgery. of contributes to capturing accurate spatial information tracking. In this paper, a novel network, Refined Attention Network, is proposed simultaneously segment and identify their categories. The U-shape network which popular segmentation used. Different from previous work, attention module adopted help the focus on key regions, can improve accuracy. To solve class imbalance problem, weighted...
Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods detecting, segmenting medical based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, reliable performance state-of-the-art when run challenging (e.g. presence blood, smoke or motion artifacts). Secondly, generalization; algorithms trained specific intervention...
The precise segmentation of surgical instruments is the key link for stable and reasonable operation robots. However, accurate instrument still a challenging task due to complex environment in endoscopic images, low contrast between tissues, diversity their morphological variability. In recent years, deep learning has been widely applied into medical image achieved certain achievements, especially U-Net its variants. existing networks suffer from some shortcomings, such as insufficient...
Automatic surgical instrument segmentation is a necessary step for the steady operation of robots, and accuracy directly affects effect. Nevertheless, accurate from endoscopic images remains challenging task due to complex environment motion during surgery. Based on encoder–decoder structure, transformer-based multiscale fusion network, named TMF-Net, proposed address difficulties in area segmentation. To realize effective feature representation based pretrained ResNet34 transformer...
Precise segmentation of retinal vessels from fundus images is essential for intervention in numerous diseases, and helpful preventing treating blindness. Deep convolutional neural network (DCNN) based approaches have achieved an excellent success the automatic vessels. However, a single (CNN) structure can only capture limited local features lack ability to extract global contexts. Meanwhile, strategies used feature fusion low-level detail information with high-level semantic fail handle...
As a unique physiological electrical signal in the human body, surface electromyography (sEMG) signals always include movement intention and muscle state. Through collection of sEMG signals, different gestures can be effectively recognized. At present, convolutional neural network (CNN) has been widely applied to gesture recognition systems. However, due its inherent limitations global context feature extraction, it exists certain shortcoming on high-precision prediction tasks. To solve this...
Gait analysis for the patients with lower limb motor dysfunction is a useful tool in assisting clinicians diagnosis, assessment, and rehabilitation strategy making. Implementing accurate automatic gait hemiparetic after stroke great challenge clinical practice. This study to develop new system qualitatively recognizing quantitatively assessing abnormality of post-stroke patients. Twenty-one twenty-one healthy volunteers participated walking trials. Three most representative data, i.e.,...
The real-time segmentation of surgical instruments plays a crucial role in robot-assisted surgery. However, it is still challenging task to implement deep learning models do for due their high computational costs and slow inference speed. In this paper, we propose an attention-guided lightweight network (LWANet), which can segment real-time. LWANet adopts encoder-decoder architecture, where the encoder MobileNetV2, decoder consists depthwise separable convolution, attention fusion block,...