Application of Multi-task Transfer Learning: The Combination of EA and Optimized Subband Regularized CSP to Classification of 8-channel EEG Signals with Small Dataset

Overview

Journal Front Hum Neurosci

Specialty Neurology

Date 2023 Apr 14

PMID 37056962

Authors

Taixue Long

Min Wan

Wenjuan Jian

Honghui Dai

Wenbing Nie

Jianzhong Xu

Affiliations

Soon will be listed here.

Abstract

Introduction: The volume conduction effect and high dimensional characteristics triggered by the excessive number of channels of EEG cap-acquired signals in BCI systems can increase the difficulty of classifying EEG signals and the lead time of signal acquisition. We aim to combine transfer learning to decode EEG signals in the few-channel case, improve the classification performance of the motor imagery BCI system across subject cases, reduce the cost of signal acquisition performed by the BCI system, and improve the usefulness of the system.

Methods: Dataset2a from BCI CompetitionIV(2008) was used as Dataset1, and our team's self-collected dataset was used as Dataset2. Dataset1 acquired EEG signals from 9 subjects using a 22-channel device with a sampling frequency of 250 Hz. Dataset2 acquired EEG signals from 10 healthy subjects (8 males and 2 females; age distribution between 21-30 years old; mean age 25 years old) using an 8-channel system with a sampling frequency of 1000 Hz. We introduced EA in the data preprocessing process to reduce the signal differences between subjects and proposed VFB-RCSP in combination with RCSP and FBCSP to optimize the effect of feature extraction.

Results: Experiments were conducted on Dataset1 with EEG data containing only 8 channels and achieved an accuracy of 78.01 and a kappa coefficient of 0.54. The accuracy exceeded most of the other methods proposed in recent years, even though the number of channels used was significantly reduced. On Dataset 2, an accuracy of 59.77 and a Kappa coefficient of 0.34 were achieved, which is a significant improvement compared to other poorly improved classical protocols.

Discussion: Our work effectively improves the classification of few-channel EEG data. It overcomes the dependence of existing algorithms on the number of channels, the number of samples, and the frequency band, which is significant for reducing the complexity of BCI models and improving the user-friendliness of BCI systems.

Citing Articles

Enhancing Deep-Learning Classification for Remote Motor Imagery Rehabilitation Using Multi-Subject Transfer Learning in IoT Environment.

Khabti J, AlAhmadi S, Soudani A Sensors (Basel). 2025; 24(24.

PMID: 39771862 PMC: 11679204. DOI: 10.3390/s24248127.

Optimal Channel Selection of Multiclass Motor Imagery Classification Based on Fusion Convolutional Neural Network with Attention Blocks.

Khabti J, AlAhmadi S, Soudani A Sensors (Basel). 2024; 24(10).

PMID: 38794022 PMC: 11125262. DOI: 10.3390/s24103168.

References

Allison B, Kubler A, Jin J . 30+ years of P300 brain-computer interfaces. Psychophysiology. 2020; 57(7):e13569. DOI: 10.1111/psyp.13569. View

Zhang K, Robinson N, Lee S, Guan C . Adaptive transfer learning for EEG motor imagery classification with deep Convolutional Neural Network. Neural Netw. 2021; 136:1-10. DOI: 10.1016/j.neunet.2020.12.013. View

Saha S, Ahmed K, Mostafa R, Hadjileontiadis L, Khandoker A . Evidence of Variabilities in EEG Dynamics During Motor Imagery-Based Multiclass Brain-Computer Interface. IEEE Trans Neural Syst Rehabil Eng. 2018; 26(2):371-382. DOI: 10.1109/TNSRE.2017.2778178. View

Luo T, Zhou C, Chao F . Exploring spatial-frequency-sequential relationships for motor imagery classification with recurrent neural network. BMC Bioinformatics. 2018; 19(1):344. PMC: 6162908. DOI: 10.1186/s12859-018-2365-1. View

Tangermann M, Muller K, Aertsen A, Birbaumer N, Braun C, Brunner C . Review of the BCI Competition IV. Front Neurosci. 2012; 6:55. PMC: 3396284. DOI: 10.3389/fnins.2012.00055. View

Wang B, Man Wong C, Kang Z, Liu F, Shui C, Wan F . Common Spatial Pattern Reformulated for Regularizations in Brain-Computer Interfaces. IEEE Trans Cybern. 2020; 51(10):5008-5020. DOI: 10.1109/TCYB.2020.2982901. View

Liavas A, Moustakides G, Henning G, Psarakis E, Husar P . A periodogram-based method for the detection of steady-state visually evoked potentials. IEEE Trans Biomed Eng. 1998; 45(2):242-8. DOI: 10.1109/10.661272. View

Pfurtscheller G, Neuper C, Flotzinger D, Pregenzer M . EEG-based discrimination between imagination of right and left hand movement. Electroencephalogr Clin Neurophysiol. 1998; 103(6):642-51. DOI: 10.1016/s0013-4694(97)00080-1. View

Chen X, Wang Y, Gao S, Jung T, Gao X . Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain-computer interface. J Neural Eng. 2015; 12(4):046008. DOI: 10.1088/1741-2560/12/4/046008. View

10.

Cohen J . Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit. Psychol Bull. 2009; 70(4):213-20. DOI: 10.1037/h0026256. View

11.

Bottger D, Herrmann C, von Cramon D . Amplitude differences of evoked alpha and gamma oscillations in two different age groups. Int J Psychophysiol. 2002; 45(3):245-51. DOI: 10.1016/s0167-8760(02)00031-4. View

12.

He H, Wu D . Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach. IEEE Trans Biomed Eng. 2019; 67(2):399-410. DOI: 10.1109/TBME.2019.2913914. View

13.

Jian W, Chen M, McFarland D . Use of phase-locking value in sensorimotor rhythm-based brain-computer interface: zero-phase coupling and effects of spatial filters. Med Biol Eng Comput. 2017; 55(11):1915-1926. PMC: 5857965. DOI: 10.1007/s11517-017-1641-y. View

14.

Cho H, Ahn M, Kim K, Jun S . Increasing session-to-session transfer in a brain-computer interface with on-site background noise acquisition. J Neural Eng. 2015; 12(6):066009. DOI: 10.1088/1741-2560/12/6/066009. View

15.

Xu Y, Hua J, Zhang H, Hu R, Huang X, Liu J . Improved Transductive Support Vector Machine for a Small Labelled Set in Motor Imagery-Based Brain-Computer Interface. Comput Intell Neurosci. 2019; 2019:2087132. PMC: 6925734. DOI: 10.1155/2019/2087132. View

16.

Cai Y, She Q, Ji J, Ma Y, Zhang J, Zhang Y . Motor imagery EEG decoding using manifold embedded transfer learning. J Neurosci Methods. 2022; 370:109489. DOI: 10.1016/j.jneumeth.2022.109489. View

17.

Wolpaw J, Birbaumer N, Heetderks W, McFarland D, Peckham P, Schalk G . Brain-computer interface technology: a review of the first international meeting. IEEE Trans Rehabil Eng. 2000; 8(2):164-73. DOI: 10.1109/tre.2000.847807. View

18.

Zhang S, Zhu Z, Zhang B, Feng B, Yu T, Li Z . The CSP-Based New Features Plus Non-Convex Log Sparse Feature Selection for Motor Imagery EEG Classification. Sensors (Basel). 2020; 20(17). PMC: 7506901. DOI: 10.3390/s20174749. View

19.

Jian W, Chen M, McFarland D . EEG based zero-phase phase-locking value (PLV) and effects of spatial filtering during actual movement. Brain Res Bull. 2017; 130:156-164. PMC: 5406268. DOI: 10.1016/j.brainresbull.2017.01.023. View

20.

Lazarou I, Nikolopoulos S, Petrantonakis P, Kompatsiaris I, Tsolaki M . EEG-Based Brain-Computer Interfaces for Communication and Rehabilitation of People with Motor Impairment: . Front Hum Neurosci. 2018; 12:14. PMC: 5810272. DOI: 10.3389/fnhum.2018.00014. View