- Robot Manipulation and Learning
- Teleoperation and Haptic Systems
- Context-Aware Activity Recognition Systems
- Hand Gesture Recognition Systems
- Muscle activation and electromyography studies
- Prosthetics and Rehabilitation Robotics
- Soft Robotics and Applications
- Augmented Reality Applications
- Gaze Tracking and Assistive Technology
- Virtual Reality Applications and Impacts
- Robotic Locomotion and Control
- Anomaly Detection Techniques and Applications
- Security and Verification in Computing
- Robotics and Automated Systems
- Advanced Malware Detection Techniques
- IoT and Edge/Fog Computing
- Internet Traffic Analysis and Secure E-voting
- Cryptography and Data Security
- Interactive and Immersive Displays
- Tactile and Sensory Interactions
- EEG and Brain-Computer Interfaces
- Medical Imaging Techniques and Applications
- Non-Invasive Vital Sign Monitoring
- Advanced Computing and Algorithms
- Human Pose and Action Recognition
South China University of Technology
2022-2025
Canon (United States)
2023-2024
North China University of Technology
2024
Central South University
2023
Xiangya Hospital Central South University
2023
Xiangtan University
2023
Guangzhou Experimental Station
2023
Politecnico di Milano
2017-2022
China Telecom
2022
China Telecom (China)
2022
Touch-free guided hand gesture recognition for human-robot interactions plays an increasingly significant role in teleoperated surgical robot systems. Indeed, despite depth cameras provide more practical information accuracy enhancement, the instability and computational burden of data represent a tricky problem. In this letter, we propose novel multi-sensor system teleoperation. A fusion model is designed performing interference presence occlusions. multilayer Recurrent Neural Network (RNN)...
For bilateral teleoperation, the haptic feedback demands availability of accurate force information transmitted from remote site. Nevertheless, due to limitation size, sensor is usually attached outside patient's abdominal cavity for surgical operation. Hence, it measures not only interaction forces on tip but also tool dynamics. In this letter, a model-free based deep convolutional neural network (DCNN) structure proposed dynamics identification, which features fast computation and noise...
Human activity recognition (HAR) using smartphones provides significant healthcare guidance for telemedicine and long-term treatment. Machine learning deep (DL) techniques are widely utilized the scientific study of statistical models human behaviors. However, performance existing HAR platforms is limited by complex physical activity. In this article, we proposed an adaptive real-time monitoring system activities (Ada-HAR), which expected to identify more motions in dynamic situations. The...
In next-generation network architecture, the Cybertwin drove sixth generation of cellular networks sixth-generation (6G) to play an active role in many applications, such as healthcare and computer vision. Although previous (5G) provides concept edge cloud core cloud, internal communication mechanism has not been explained with a specific application. This article introduces possible based multimodal (beyond 5G) for electrocardiogram (ECG) patterns monitoring during daily activity. paradigm...
The presence of unknown physical interaction between the patients’ body and surgical tool in laparoscopic surgery requires a secure end-effector positioning while assuring reliable constraint motion. In this work, task-space control approach based on fuzzy approximation is proposed for teleoperated scenario utilizing serial redundant robot manipulator (7 degrees freedom), motions which are constrained with respect to point known as remote center motion (RCM). dynamical uncertainties due...
In the field of robotics, soft robots have been showing great potential in areas medical care, education, service, rescue, exploration, detection, and wearable devices due to their inherently high flexibility, good compliance, excellent adaptability, natural safe interactivity. Pneumatic occupy an essential position among because features such as lightweight, efficiency, non-pollution, environmental adaptability. Thanks its mentioned benefits, increasing research interests attracted...
Playing games between humans and robots have become a widespread human-robot confrontation (HRC) application. Although many approaches were proposed to enhance the tracking accuracy by combining different information, problems of intelligence degree robot anti-interference ability motion capture system still need be solved. In this paper, we present an adaptive reinforcement learning (RL) based multimodal data fusion (AdaRL-MDF) framework teaching hand play Rock-Paper-Scissors (RPS) game...
Recently, the human-like behavior on anthropomorphic robot manipulator is increasingly accomplished by kinematic model establishing relationship of an and human arm motions. Notably, growth broad availability advanced data science techniques facilitate imitation learning process in robotics. However, enormous dataset causes labeling prediction burden. In this article, swivel motion reconstruction approach was applied to imitate using mapping redundancy. For sake efficient computing, a novel...
Objective: This study aims to understand breathing patterns during daily activities by developing a wearable respiratory and activity monitoring (WRAM) system. Methods: A novel multimodal fusion architecture is proposed calculate the exercise parameters simultaneously identify human actions. hybrid hierarchical classification (HHC) algorithm combining deep learning threshold-based methods presented distinguish 15 complex for accuracy enhancement fast computation. series of signal processing...
As a significant role in healthcare and sports applications, human activity recognition (HAR) techniques are capable of monitoring humans' daily behavior. It has spurred the demand for intelligent sensors been giving rise to explosive growth wearable mobile devices. They provide most availability data (big data). Powerful algorithms required analyze these heterogeneous high-dimension streaming efficiently. This paper proposes novel fast robust deep convolutional neural network structure...
In the human–robot interaction, especially when hand contact appears directly on robot arm, dynamics of human arm presents an essential component in interaction and object manipulation. Modeling estimation show great potential for achieving more natural safer interaction. To enrich dexterity guarantee accuracy manipulation, mapping motor functionality muscle using biosignals becomes a popular topic. this article, novel algorithm was constructed deep learning to explore model between surface...
Purpose The purpose of this paper is to develop a human activity-aware adaptive shared control solution for human–robot interaction in surgical operation. Hands-on and teleoperation are two main procedures switched frequently teleoperated minimally invasive surgery (MIS). detailed activity the can be defined recognized using sensor information. In paper, novel continuous method proposed manipulators with Cartesian impedance scenario. Design/methodology/approach A by adjusting weight function...
Background Immune checkpoint inhibitors (ICIs) therapy targeting programmed cell death 1 (PD-1)/programmed ligand (PD-L1) shows promising clinical benefits. However, the relatively low response rate highlights need to develop an alternative strategy target PD-1/PD-L1 immune checkpoint. Our study focuses on role and mechanism of annexin A1 (ANXA1)-derived peptide A11 degrading PD-L1 effect tumor evasion in multiple cancers. Methods Binding was identified by biotin pull-down coupled with mass...
Information centric networks (ICNs) allow content objects to be cached within the network, so as provide efficient data delivery. Existing works on in-network caches mainly focus minimizing redundancy of improve cache hit ratio, which may not lead significant bandwidth saving. On other hand, it could result in too frequent caching operations, i.e., placement and replacement, causing more power consumption at nodes, shall avoided energy-limited delivery environments, e.g., wireless networks....
Human-like behavior has emerged in the robotics area for improving quality of Human-Robot Interaction (HRI). For human-like imitation, kinematic mapping between a human arm and robot manipulator is one popular solutions. To fulfill this requirement, reconstruction method called swivel motion was adopted to achieve imitation. This approach aims at modeling regression relationship pose angle. Then it reaches using its redundant degrees manipulator. characteristic holds most anthropomorphic...
Electroencephalography (EEG) is a common and significant tool for aiding in the diagnosis of epilepsy studying human brain electrical activity. Previously, traditional machine learning (ML)-based classifier are used to identify seizure by extracting features from EEG signals manually. Although effectiveness these contributions have already been proved, they cannot achieve multiple class classification with automatic feature extraction. Meanwhile, identifiable segment too long limit...
Purpose This paper aims on the trajectory tracking of developed six wheel-legged robot with heavy load conditions under uncertain physical interaction. The accuracy and stable operation are main challenges parallel mechanism for robots, especially in complex road conditions. To guarantee performance an environment, disturbances, including internal friction, external environment interaction, should be considered practical system. Design/methodology/approach In this paper, a fuzzy...
Hand gesture recognition has been applied to many research fields and shown its prominent advantages in increasing the practicality of Human-Robot Interaction (HRI). The development advanced techniques data science, such as big machine learning, facilitate accurate classification hand gestures using electromyography (EMG) signals. However, processing collection label large set imposes a high work burden results time-consuming implementations. Therefore, novel method is proposed combine...
Collaborative robots sensing and understanding the movements intentions of their human partners are crucial for realizing human-robot collaboration. Human skeleton sequences widely recognized as a kind data with great application potential in action recognition. In this letter, multi-scale skeleton-based recognition network is proposed, which leverages spatio-temporal attention mechanism. The achieves high-accuracy prediction by aggregating multi-level key point features applying mechanism...
The integration of advanced sensor technologies has significantly propelled the dynamic development robotics, thus inaugurating a new era in automation and artificial intelligence. Given rapid advancements robotics technology, its core area—robot control technology—has attracted increasing attention. Notably, sensors fusion technologies, which are considered essential for enhancing robot have been widely successfully applied field robotics. Therefore, techniques with enables adaptation to...
Open-source kernels have been adopted by massive downstream vendors on billions of devices. However, these often omit or delay the adoption patches released in mainstream version. Even worse, many are not publicizing patching progress even disclosing misleading information. status is critical for groups (e.g., governments and enterprise users) that keen to security threats. Such a practice motivates need reliable patch presence testing kernels. Currently, best means examine existence target...