An algorithm for movement related potentials feature extraction based on transfer learning

Wang, Peitao; Lu, Jun; Lu, Chuan; Tang, Zeng

doi:10.1109/icist.2015.7288988

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, C t is calculated by using all the trials (without labels) of the target subject. Note that there is no any class information involved, as suggested in (Wang et al 2015). The basic idea of (5) is to measure the difference between the source subjects and the target subject.…”

Section: Regularized Common Spatial Patterns Based On Transfer Learnimentioning

confidence: 99%

“…Recently, the composite expression of the covariance matrix given in (Kang et al 2009) was applied to local temporal correlation CSP, yielded composite local temporal correlation CSP (CLTCCSP) (Hatamikia and Nasrabadi 2015). Moreover, the transfer learning technique was extended to discriminative spatial pattern (DSP) based on empirical maximum mean discrepancy to reduce differences between subjects (Wang et al 2015), and was generalized to transfer different domains of diseases (Cheng et al 2015).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Regularized common spatial patterns with subject-to-subject transfer of EEG signals

2016

View full text Add to dashboard Cite

In the context of brain-computer interface (BCI) system, the common spatial patterns (CSP) method has been used to extract discriminative spatial filters for the classification of electroencephalogram (EEG) signals. However, the classification performance of CSP typically deteriorates when a few training samples are collected from a new BCI user. In this paper, we propose an approach that maintains or improves the recognition accuracy of the system with only a small size of training data set. The proposed approach is formulated by regularizing the classical CSP technique with the strategy of transfer learning. Specifically, we incorporate into the CSP analysis inter-subject information involving the same task, by minimizing the difference between the inter-subject features. Experimental results on two data sets from BCI competitions show that the proposed approach greatly improves the classification performance over that of the conventional CSP method; the transformed variant proved to be successful in almost every case, based on a small number of available training samples.

show abstract

Section: Regularized Common Spatial Patterns Based On Transfer Learnimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Regularized common spatial patterns with subject-to-subject transfer of EEG signals

2016

View full text Add to dashboard Cite

show abstract

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review

Zhang

Zheng

et al. 2020

Sensors

View full text Add to dashboard Cite

The algorithms of electroencephalography (EEG) decoding are mainly based on machine learning in current research. One of the main assumptions of machine learning is that training and test data belong to the same feature space and are subject to the same probability distribution. However, this may be violated in EEG processing. Variations across sessions/subjects result in a deviation of the feature distribution of EEG signals in the same task, which reduces the accuracy of the decoding model for mental tasks. Recently, transfer learning (TL) has shown great potential in processing EEG signals across sessions/subjects. In this work, we reviewed 80 related published studies from 2010 to 2020 about TL application for EEG decoding. Herein, we report what kind of TL methods have been used (e.g., instance knowledge, feature representation knowledge, and model parameter knowledge), describe which types of EEG paradigms have been analyzed, and summarize the datasets that have been used to evaluate performance. Moreover, we discuss the state-of-the-art and future development of TL for EEG decoding. The results show that TL can significantly improve the performance of decoding models across subjects/sessions and can reduce the calibration time of brain–computer interface (BCI) systems. This review summarizes the current practical suggestions and performance outcomes in the hope that it will provide guidance and help for EEG research in the future.

show abstract

An algorithm for movement related potentials feature extraction based on transfer learning

Cited by 2 publications

References 23 publications

Regularized common spatial patterns with subject-to-subject transfer of EEG signals

Regularized common spatial patterns with subject-to-subject transfer of EEG signals

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review

Contact Info

Product

Resources

About