Multiclass Informative Instance Transfer Learning Framework for Motor Imagery-Based Brain-Computer Interface

Hossain, Ibrahim; Khosravi, Abbas; Hettiarachchi, Imali; Nahavandi, Saeid

doi:10.1155/2018/6323414

Cited by 35 publications

(13 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the first category, it is assumed that the partial source EEG data can be selected and considered together with few labeled target EEG data. The source EEG data are obtained through either instance selection or importance sampling crossvalidation (Li et al, 2010;Hossain et al, 2016Hossain et al, , 2018Zanini et al, 2018). For example, Hossain et al (2016) proposed an instance selection strategy based on active learning.…”

Section: Related Workmentioning

confidence: 99%

A Novel Transfer Support Matrix Machine for Motor Imagery-Based Brain Computer Interface

et al. 2020

View full text Add to dashboard Cite

In recent years, emerging matrix learning methods have shown promising performance in motor imagery (MI)-based brain-computer interfaces (BCIs). Nonetheless, the electroencephalography (EEG) pattern variations among different subjects necessitates collecting a large amount of labeled individual data for model training, which prolongs the calibration session. From the perspective of transfer learning, the model knowledge inherent in reference subjects incorporating few target EEG data have the potential to solve the above issue. Thus, a novel knowledge-leverage-based support matrix machine (KL-SMM) was developed to improve the classification performance when only a few labeled EEG data in the target domain (target subject) were available. The proposed KL-SMM possesses the powerful capability of a matrix learning machine, which allows it to directly learn the structural information from matrix-form EEG data. In addition, the KL-SMM can not only fully leverage few labeled EEG data from the target domain during the learning procedure but can also leverage the existing model knowledge from the source domain (source subject). Therefore, the KL-SMM can enhance the generalization performance of the target classifier while guaranteeing privacy protection to a certain extent. Finally, the objective function of the KL-SMM can be easily optimized using the alternating direction method of multipliers method. Extensive experiments were conducted to evaluate the effectiveness of the KL-SMM on publicly available MI-based EEG datasets. Experimental results demonstrated that the KL-SMM outperformed the comparable methods when the EEG data were insufficient.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Transfer Support Matrix Machine for Motor Imagery-Based Brain Computer Interface

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To solve this problem, transfer learning (TL), which applies the dataset in source domains for compensating insufficient labeled data in a target domain, has been proposed for MI-BCIs (Samek et al, 2013b ; Azab et al, 2018 ). This technology is developed in several ways, such as instance selection (Wu, 2016 ; Hossain et al, 2018 ), feature calibration (Samek et al, 2013a ; Zhao et al, 2019 ) and classification domains (Vidaurre et al, 2010 ; He and Wu, 2019 ). For instance, for selection, active learning is typically presented for selecting training data from intra- or inter-subject labeled trials (Hossain et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

The Brain Computer Interface (BCI) system is a typical neurophysiological application which helps paralyzed patients with human-machine communication. Stroke patients with motor disabilities are able to perform BCI tasks for clinical rehabilitation. This paper proposes an effective scheme of transfer calibration for BCI rehabilitation. The inter- and intra-subject transfer learning approaches can improve the low-precision classification performance for experimental feedback. The results imply that the systematical scheme is positive in increasing the confidence of voluntary training for stroke patients. In addition, it also reduces the time consumption of classifier calibration.

show abstract

“…In MI-based BCIs, transfer learning can be applied on either raw EEG, feature or classification domains. The proposed transfer learning algorithms on raw EEG have been mostly based on either importance sampling cross validation [14], [15] or instance selection [16], [17]. For example, a covariate shift adaptation has been proposed in [14], where data from other subjects were weighted based on importance sampling cross-validation.…”

Section: Introductionmentioning

confidence: 99%

“…The parts with high weights were then used to estimate the final prediction function. In [16], [17], an instance selection approach has been proposed based on active learning to select trials that were close to the few informative trials of the new subject. The selected trials were added to the existing labeled trials of the new subject to train the BCI model.…”

Section: Introductionmentioning

confidence: 99%

Weighted Transfer Learning for Improving Motor Imagery-Based Brain–Computer Interface

Azab

Mihaylova

Ang

et al. 2019

IEEE Trans. Neural Syst. Rehabil. Eng.

136

View full text Add to dashboard Cite

One of the major limitations of motor imagery (MI)based brain-computer interface (BCI) is its long calibration time. Due to between sessions/subjects variations in the properties of brain signals, typically a large amount of training data needs to be collected at the beginning of each session to calibrate the parameters of the BCI system for the target user. In this paper, we propose a novel transfer learning approach on the classification domain to reduce the calibration time without sacrificing the classification accuracy of MI-BCI. Thus, when only few subject-specific trials are available for training, the estimation of the classification parameters is improved by incorporating previously recorded data from other users. For this purpose, a regularization parameter is added to the objective function of the classifier to make the classification parameters as close as possible to the classification parameters of the previous users who have feature spaces similar to that of the target subject. In this study, a new similarity measure based on the kullback leibler divergence (KL) is used to measure similarity between two feature spaces obtained using subject-specific common spatial patterns (CSP). The proposed transfer learning approach is applied on the logistic regression classifier and evaluated using three datasets. The results showed that compared to the subject-specific classifier, the proposed weighted transfer learning classifier improved the classification results particularly when few subject-specific trials were available for training (p < 0.05). Importantly, this improvement was more pronounced for users with medium and poor accuracy. Moreover, the statistical results showed that the proposed weighted transfer learning classifier performed significantly better than the considered comparable baseline algorithms.

show abstract

Multiclass Informative Instance Transfer Learning Framework for Motor Imagery-Based Brain-Computer Interface

Cited by 35 publications

References 54 publications

A Novel Transfer Support Matrix Machine for Motor Imagery-Based Brain Computer Interface

A Novel Transfer Support Matrix Machine for Motor Imagery-Based Brain Computer Interface

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

Weighted Transfer Learning for Improving Motor Imagery-Based Brain–Computer Interface

Contact Info

Product

Resources

About