Rehabilitation Treatment of Motor Dysfunction Patients Based on Deep Learning Brain–Computer Interface Technology

  title={Rehabilitation Treatment of Motor Dysfunction Patients Based on Deep Learning Brain–Computer Interface Technology},
  author={Huihai Wang and Qinglun Su and Zhenzhuang Yan and Fei Lu and Qin Zhao and Zhen Liu and Fang Zhou},
  journal={Frontiers in Neuroscience},
In recent years, brain–computer interface (BCI) is expected to solve the physiological and psychological needs of patients with motor dysfunction with great individual differences. However, the classification method based on feature extraction requires a lot of prior knowledge when extracting data features and lacks a good measurement standard, which makes the development of BCI. In particular, the development of a multi-classification brain–computer interface is facing a bottleneck. To avoid… 
Brain-Computer Interfaces Systems for Upper and Lower Limb Rehabilitation: A Systematic Review
A systematic review of the state of the art and opportunities in the development of BCIs for the rehabilitation of upper and lower limbs of the human body found that using EEG signals, and user feedback offer benefits including cost, effectiveness, better training, user motivation and there is a need to continue developing interfaces that are accessible to users, and that integrate feedback techniques.
Comparison of EEG Data Processing Using Feedforward and Convolutional Neural Network∗
EEG signals are the overall reflection of the physiological activities of brain nerve cells in the cerebral cortex and scalp. By classifying and processing EEG signals, it is possible to identify
Biosignal-Based Human–Machine Interfaces for Assistance and Rehabilitation: A Survey
The large literature of the last two decades regarding biosignal-based HMIs for assistance and rehabilitation is reviewed to outline state-of-the-art and identify emerging technologies and potential future research trends.
A Charge Balanced Neural Stimulator Silicon Chip for Human-Machine Interface
This paper proposes a neural stimulator silicon chip design with an improved charge balancing technology. The proposed neural stimulation integrated circuit (IC) uses two charge balancing modules


Deep Multi-View Feature Learning for EEG-Based Epileptic Seizure Detection
Experimental studies show that the classification accuracy of the proposed multi-view deep feature extraction method is at least 1% higher than that of common feature extraction methods such as principal component analysis (PCA), FFT and WPD.
Seizure Classification From EEG Signals Using an Online Selective Transfer TSK Fuzzy Classifier With Joint Distribution Adaption and Manifold Regularization
This study proposes an online selective transfer TSK fuzzy classifier underlying joint distribution adaption and manifold regularization and results indicate that this classifier wins the best performance and is not very sensitive to its parameters.
Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System
Transductive transfer learning is used to reduce the discrepancy in data distribution between the training and testing data, semi-supervised learning is employed to use the unlabeled testing data to remedy the shortage of training data, and TSK fuzzy system is adopted to increase model interpretability.
Epileptic EEG Signals Recognition Using a Deep View-Reduction TSK Fuzzy System With High Interpretability
A deep view-reduction TSK fuzzy system termed as DVR-TSK-FS in which two powerful mechanisms associating with a deep structure are developed during the multi-view learning in each component.
Transcranial direct current stimulation for the treatment of motor impairment following traumatic brain injury
A combination of task-oriented training using virtual reality with tDCS can be considered as a potent tele-rehabilitation tool in the home setting, increasing the dose of rehabilitation and neuromodulation, resulting in better motor recovery.
“Remind-to-Move” Treatment Enhanced Activation of the Primary Motor Cortex in Patients with Stroke
Investigation of cortical activation patterns using functional near-infrared spectroscopic topography for patients with chronic stroke receiving RTM by comparing with their healthy counterparts found effects of RTM were robust and more widely distributed in healthy participants, comparing to patients with stroke.
Introducing the thematic series on transcranial direct current stimulation (tDCS) for motor rehabilitation: on the way to optimal clinical use
This collection of articles was thought to present the most recent advances in tDCS for motor rehabilitation, addressing topics such as theoretical, methodological, and practical approaches to be considered when designing tDCS-based rehabilitation.
Wearable technology in stroke rehabilitation: towards improved diagnosis and treatment of upper-limb motor impairment
The present review aims to provide an overview of wearable sensors used in stroke rehabilitation research, with a particular focus on the upper extremity.
Transcranial direct current stimulation combined with visuo-motor training as treatment for chronic stroke patients.
Four-week visuo-motor training combined with tDCS showed no difference between the Active and Sham groups in the total UE FMA score, which may be explained by heterogeneity of the degree of recovery in the Active group.
Common and Special Knowledge-Driven TSK Fuzzy System and Its Modeling and Application for Epileptic EEG Signals Recognition
A common and special knowledge-driven TSK fuzzy system (CSK-TSK-FS), in which the parameters corresponding to each feature in then-parts of fuzzy rules always keep invariant and these parameters are viewed as common knowledge.