A5050878399- Advanced Algorithms and Applications
- Advanced Sensor and Control Systems
- Energy Efficient Wireless Sensor Networks
- Industrial Technology and Control Systems
- Wireless Sensor Networks and IoT
- Fault Detection and Control Systems
- Advanced Computational Techniques and Applications
- Mobile Ad Hoc Networks
- Security in Wireless Sensor Networks
- Advanced Measurement and Detection Methods
- Target Tracking and Data Fusion in Sensor Networks
- EEG and Brain-Computer Interfaces
- Stroke Rehabilitation and Recovery
- Muscle activation and electromyography studies
- Indoor and Outdoor Localization Technologies
- Prosthetics and Rehabilitation Robotics
- Neuroscience and Neural Engineering
- Advanced Control Systems Optimization
- Advanced Decision-Making Techniques
- Gaze Tracking and Assistive Technology
- Water Quality Monitoring Technologies
- Control Systems and Identification
- Distributed Control Multi-Agent Systems
- Metaheuristic Optimization Algorithms Research
- Spectroscopy and Chemometric Analyses
Southeast University
2014-2025
Jiangsu University
2023
State Key Laboratory of Digital Medical Engineering
2022
Jiangnan University
2007-2016
Nanjing University of Posts and Telecommunications
2012-2013
Tsinghua University
2008-2013
Changshu Institute of Technology
2008-2012
Fujian Research Institute of Light Industry
2011
Guizhou University
2009-2010
System Equipment (China)
2009
For monitoring burst events in a kind of reactive wireless sensor networks (WSNs), multipath routing protocol (MRP) based on dynamic clustering and ant colony optimization (ACO) is proposed.. Such an approach can maximize the network lifetime reduce energy consumption. An important attribute WSNs their limited power supply, therefore some metrics (such as consumption communication among nodes, residual energy, path length) were considered very criteria while designing MRP. Firstly, cluster...
The controlling of robotic arms based on brain–computer interface (BCI) can revolutionize the quality life and living conditions for individuals with physical disabilities. Invasive electroencephalography (EEG)-based BCI has been able to control multiple degrees freedom (DOFs) in three dimensions. However, it is still hard a multi-DOF arm reach grasp desired target accurately complex three-dimensional (3D) space by noninvasive system mainly due limitation EEG decoding performance. In this...
Brain-machine interface (BMI) can be used to control the robotic arm assist paralysis people for performing activities of daily living. However, it is still a complex task BMI users process objects grasping and lifting with arm. It hard achieve high efficiency accuracy even after extensive trainings. One important reason lacking sufficient feedback information user perform closed-loop control. In this study, we proposed method augmented reality (AR) guiding assistance provide enhanced visual...
Brain-computer interface (BCI) provides new communication and control channels that do not depend on the brain’s normal output of peripheral nerves muscles. In this paper, we report results developing a single trial online motor imagery feature extraction method for BCI. The wavelet coefficients autoregressive parameter model was used to features from EEG linear discriminant analysis based mahalanobis distance utilized classify pattern left right hand movement imagery. performance tested by...
Brain computer interface (BCI) adopts human brain signals to control external devices directly without using normal neural pathway. Recent study has explored many applications, such as controlling a teleoperation robot by electroencephalography (EEG) signals. However, utilizing the motor imagery EEG-based BCI perform for reach and grasp task still difficulties, especially in continuous multidimensional of tactile feedback. In this research, system with feedback was proposed. Firstly, mental...
A significant number of people with disabilities rely on assistive devices, yet these technologies often face limitations, including restricted functionality, inadequate user-centered design, and a lack standardized evaluation metrics. While upper-limb prosthetics remain key research focus, existing commercial solutions still fall short meeting daily reliability usability needs, leading to high abandonment rates. CYBATHLON integrates into living tasks, driving innovation prioritizing user...
Feature extraction plays an important role in brain-computer interface (BCI) systems. In order to characterize the motor imagery related rhythm and higher-order statistics information contained within EEG signals, a novel feature method based on harmonic wavelet transform bispectrum is developed applied recognition of right left imageries for developing EEG-based BCI The experimental results Graz data set have shown that separability two classes features extracted by proposed notable. Its...
This paper is concerned with the identification problems of linear parameter varying (LPV) system missing output in presence time-delay. A multiple-model approach adopted. Local models from one operating point to another are first described by finite impulse response (FIR) models. To handle and time-delay, expectation-maximization (EM) algorithm utilized estimate unknown parameters time-delay simultaneously. Output Error (OE) widely used controller design. Therefore, auxiliary model...
Capturing finger joint angle information has important applications in human–computer interaction and hand function evaluation. In this paper, a novel wearable data glove is proposed for capturing angles. A sensing unit based on grating strip an optical detector specially designed measurement. To measure the angles of joints, 14 units are arranged back glove. There each middle phalange, proximal metacarpal finger, except thumb. For thumb, two distributed phalange metacarpal, respectively....
. In the field of motor imagery (MI) electroencephalography (EEG)-based brain-computer interfaces, deep transfer learning (TL) has proven to be an effective tool for solving problem limited availability in subject-specific data training robust (DL) models. Although considerable progress been made cross-subject/session and cross-device scenarios, more challenging cross-task TL remains largely unexplored.
SUMMARY Clinical outcomes have shown that robot-assisted rehabilitation is potential of enhancing quantification therapeutic process for patients with stroke. During robotic exercise, the assistive robot must guarantee subject's safety in emergency situations, e.g., sudden spasm or twitch, abruptly severe tremor, etc. This paper presents a hierarchical control strategy, which proposed to improve and robustness system. The architecture composed two main components: high-level supervisory...
On a basis of Retinex and YIQ color space, new approach image enhancement is presented in this paper. The original the RGB space converted to multi-scale (MSR) algorithm introduced enhance its Y-component. two-dimensional discrete Fourier transform (DFT) employed accelerate information processing for MSR, while both I-component Q-component keep unchangeably so as obtain completely constant result. Finally, brightness contrast are enhanced evidently well reserved. Experimental results...
Brain-computer interface (BCI) provides new communication and control channels that do not depend on the brain's normal output of peripheral nerves muscles. In this paper, we report results developing a single trial online motor imagery feature extraction method for BCI. The wavelet coefficients autoregressive parameter model was used to features from EEG linear discriminant analysis based mahalanobis distance utilized classify pattern left right hand movement imagery. performance tested by...
The energy constraint sensor nodes operate on limited batteries, so the consumption is a key design criterion for routing protocols in wireless networks. Comparing with single path algorithm, multi-path algorithm can balance network distribution and extend lifetime better. In this paper, we propose an Ant Colony- Based Multi-path Routing Algorithm, which uses Colony Algorithm(ACA) to discover disjoint multipaths between source sink node. We also load balancing scheme distribute traffic over...
Wireless sensor networks (WSNs) consist of a large number nodes with limited battery power. Thus, the communication must be designed to conserve energy resources nodes. In this paper, we propose cluster-based multipath delivery scheme, called CMDS, which uses cluster and improve capability load balance, thus prolonging network lifetime. Firstly, CMDS organizes into clusters so that communicate information only clusterheads take task data aggregation. Then, transmit base station (sink) along...
SUMMARY This study presents novel robotic therapy control algorithms for upper-limb rehabilitation, using newly developed passive and progressive resistance modes. A fuzzy-logic based proportional-integral-derivative (PID) position strategy, integrating a patient's biomechanical feedback into the loop, is proposed movements. allows robot to smoothly stretch impaired limb through increasingly rigorous training trajectories. fuzzy adaptive impedance force controller addressed in muscle...
Muscle strength training for stroke patients is of vital importance helping survivors to progressively restore muscle and improve the performance their activities in daily living (ADL). An adaptive hierarchical therapy control framework which integrates patient's real biomechanical state estimation with task-performance quantitative evaluation proposed. Firstly, a high-level progressive resistive supervisory controller designed determine force base each session based on online evaluation....