Yongcheng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yongcheng Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chengsi Hu
School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
1 shared publication - Chenying Xu
CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS), Shenzhen 518055, China
1 shared publication - Enrique Tonatihu Jimenez-Borgonio
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
1 shared publication - Guanglin Li
Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
1 shared publication - Guangqi Zhou
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
1 shared publication - Hao Chen
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
1 shared publication
Latest Publications
- Open Access
Dual-Manifold Contrastive Learning for Robust and Real-Time EEG Motor Decoding
Brain–computer interfaces (BCIs) have great potential for consumer electronics, as they enable the decoding of brain activity to control external devices and assist human–computer interaction. However, current decoding methods for BCIs face several challenges, such as low accuracy, poor stability under electrode shift, and slow processing for real-time use. In this paper, we propose a hybrid decoding framework designed to address the challenges of current EEG decoding methods. Our method combines manifold learning with contrastive learning. The core of our method lies in a dual-manifold model that uses non-negative matrix factorization (NMF) and a contrastive manifold learning framework to extract clear and useful features from brain signals. To improve decoding stability, we introduce a joint training strategy that enhances feature learning. Furthermore, the system is optimized for real-time interaction, reducing the system latency to 100 ms. We collect EEG signals from 15 subjects performing motor execution tasks and 10 subjects performing motor imagery tasks to construct a motor EEG dataset. On this dataset, the proposed method achieves superior decoding performance, reaching F1-scores of 0.7382 for the motor imagery tasks and 0.8361 for the motor execution tasks. Furthermore, the method maintains robustness even with reduced electrode counts and altered spatial distributions, highlighting its potential as a decoding solution for reliable and portable BCI systems.
Open AccessDual-Manifold Contrastive Learning for Robust and Real-Time EEG Motor Decoding
Brain–computer interfaces (BCIs) have great potential for consumer electronics, as they enable the decoding of brain activity to control external devices and assist human–computer interaction. However, current decoding methods for BCIs face several challenges, such as low accuracy, poor stability under electrode shift, and slow processing for real-time use. In this paper, we propose a hybrid decoding framework designed to address the challenges of current EEG decoding methods. Our method combines manifold learning with contrastive learning. The core of our method lies in a dual-manifold model that uses non-negative matrix factorization (NMF) and a contrastive manifold learning framework to extract clear and useful features from brain signals. To improve decoding stability, we introduce a joint training strategy that enhances feature learning. Furthermore, the system is optimized for real-time interaction, reducing the system latency to 100 ms. We collect EEG signals from 15 subjects performing motor execution tasks and 10 subjects performing motor imagery tasks to construct a motor EEG dataset. On this dataset, the proposed method achieves superior decoding performance, reaching F1-scores of 0.7382 for the motor imagery tasks and 0.8361 for the motor execution tasks. Furthermore, the method maintains robustness even with reduced electrode counts and altered spatial distributions, highlighting its potential as a decoding solution for reliable and portable BCI systems.
- Open Access
- 26 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 965
A Motor Imagery BCI-Triggered Hand Exoskeleton for Rehabilitation: Achieving Major Grasp Functions via Precise Finger Movement Control
Stroke-induced hand motor dysfunction severely limits activities of daily living (ADL). While conventional systems face challenges in portability and sustained actuation accuracy, this work addresses these limitations through an integrated adaptive control framework and a lightweight 10-degrees-of-freedom (DoFs) tendon-driven exoskeleton. The system employs a rigid–flexible coupling design with a wearable mass under 300 g, ensuring compatibility across various finger lengths. The system is implemented via a motor imagery-based brain–computer interface (MI-BCI); by processing 64-channel electroencephalogram (EEG) signals, the system adaptively maps motor intent into three discrete grasp intensity levels (20%, 50%, and 80% maximum voluntary contraction). To reduce cognitive load and enhance system stability during rehabilitation, we propose a novel “Force–Topology Coupling” control paradigm. This paradigm functions as a synergistic filter, leveraging the correlation between intended effort level (IEL) and grasp taxonomy to map intensity levels to ADL-specific grasps (lateral, precision, and power). Validation with healthy subjects demonstrated 0° to 90° joint mobility and the successful execution of 9 ADL tasks. The results verify the efficacy of utilizing adaptive MI-BCI modulation to trigger biomechanically precise assistance, establishing a foundational computational paradigm with significant potential for clinical stroke rehabilitation.
- 26 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 965
Open AccessA Motor Imagery BCI-Triggered Hand Exoskeleton for Rehabilitation: Achieving Major Grasp Functions via Precise Finger Movement Control
Stroke-induced hand motor dysfunction severely limits activities of daily living (ADL). While conventional systems face challenges in portability and sustained actuation accuracy, this work addresses these limitations through an integrated adaptive control framework and a lightweight 10-degrees-of-freedom (DoFs) tendon-driven exoskeleton. The system employs a rigid–flexible coupling design with a wearable mass under 300 g, ensuring compatibility across various finger lengths. The system is implemented via a motor imagery-based brain–computer interface (MI-BCI); by processing 64-channel electroencephalogram (EEG) signals, the system adaptively maps motor intent into three discrete grasp intensity levels (20%, 50%, and 80% maximum voluntary contraction). To reduce cognitive load and enhance system stability during rehabilitation, we propose a novel “Force–Topology Coupling” control paradigm. This paradigm functions as a synergistic filter, leveraging the correlation between intended effort level (IEL) and grasp taxonomy to map intensity levels to ADL-specific grasps (lateral, precision, and power). Validation with healthy subjects demonstrated 0° to 90° joint mobility and the successful execution of 9 ADL tasks. The results verify the efficacy of utilizing adaptive MI-BCI modulation to trigger biomechanically precise assistance, establishing a foundational computational paradigm with significant potential for clinical stroke rehabilitation.