An Inter- and Intra-Subject Transfer Calibration Scheme for Improving Feedback Performance of Sensorimotor Rhythm-Based BCI Rehabilitation

Cao, Lei; Chen, Shugeng; Jia, Jie; Fan, Chunjiang; Wang, Haoran; Xu, Zongben

doi:10.3389/fnins.2020.629572

Cited by 9 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the regularization parameter calculated using the divergences of all source subjects is added to the objective function of logistic regression classifier to make full use of the labeled samples from the source subjects correctly. Cao et al (2021) verified the applicability of wLRTL approach for stroke patients and intra/inter- subjective conditions.…”

Section: Transfer Learningmentioning

confidence: 54%

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain–Computer Interface

Huang

Hua

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.

show abstract

Section: Transfer Learningmentioning

confidence: 54%

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain–Computer Interface

Huang

Hua

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Moreover, in 2020, we confirmed the clinical efficacy of BCI training on stroke patients with upper limb dysfunction in both sub-acute and chronic stages, and we explored the closed-loop brain activation changes in sensorimotor rhythm (Chen et al, 2020a;Miao et al, 2020). In 2021, we proposed an inter-and intra-subject transfer calibration scheme for improving feedback performance of the closed-loop BCI training (Cao et al, 2020). In the same year, we compared the differences between motor attempt and motor imagery tasks, which are commonly used in a closed-loop BCI system (Chen et al, 2021).…”

Section: Introduction Concept and Development Of The Theory Of Centra...mentioning

confidence: 84%

Exploration on neurobiological mechanisms of the central–peripheral–central closed-loop rehabilitation

Jia

2022

Front. Cell. Neurosci.

Self Cite

View full text Add to dashboard Cite

Central and peripheral interventions for brain injury rehabilitation have been widely employed. However, as patients’ requirements and expectations for stroke rehabilitation have gradually increased, the limitations of simple central intervention or peripheral intervention in the rehabilitation application of stroke patients’ function have gradually emerged. Studies have suggested that central intervention promotes the activation of functional brain regions and improves neural plasticity, whereas peripheral intervention enhances the positive feedback and input of sensory and motor control modes to the central nervous system, thereby promoting the remodeling of brain function. Based on the model of a central–peripheral–central (CPC) closed loop, the integration of center and peripheral interventions was effectively completed to form “closed-loop” information feedback, which could be applied to specific brain areas or function-related brain regions of patients. Notably, the closed loop can also be extended to central and peripheral immune systems as well as central and peripheral organs such as the brain–gut axis and lung–brain axis. In this review article, the model of CPC closed-loop rehabilitation and the potential neuroimmunological mechanisms of a closed-loop approach will be discussed. Further, we highlight critical questions about the neuroimmunological aspects of the closed-loop technique that merit future research attention.

show abstract

“…The number of studies exploring transfer learning using stroke data is limited. Cao et al proposed a scheme to conduct transfer calibration based on the performance of existing methods [55]. They evaluated intra-and inter-subject transfer learning calibrations using data from seven stroke patients and found that their scheme benefitted low-precision sessions the most.…”

Section: Transfer Learning In Stroke Patientsmentioning

confidence: 99%

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain–computer interface

Nagarajan,

Robinson,

Ang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective: Motor imagery (MI) brain-computer interfaces (BCI) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients. Approach: We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients. Main Results: Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects’ data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p < 0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p < 0.001) and 5.55% (p < 0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p > 0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients. Significance: Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.

show abstract

An Inter- and Intra-Subject Transfer Calibration Scheme for Improving Feedback Performance of Sensorimotor Rhythm-Based BCI Rehabilitation

Cited by 9 publications

References 37 publications

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain–Computer Interface

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain–Computer Interface

Exploration on neurobiological mechanisms of the central–peripheral–central closed-loop rehabilitation

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain–computer interface

Contact Info

Product

Resources

About