Skip to main content
Top
Published in:

10-11-2023

A Novel Feature Fusion Approach for Classification of Motor Imagery EEG Based on Hierarchical Extreme Learning Machine

Authors: Lijuan Duan, Zhaoyang Lian, Yuanhua Qiao, Juncheng Chen, Jun Miao, Mingai Li

Published in: Cognitive Computation | Issue 2/2024

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Because feature extraction from electroencephalogram (EEG) signals is essential for cognitive investigations, effective feature extraction approaches are needed to improve the practical recognition accuracy of EEG signals. In this paper, a strategy is presented for fusing both the linear and nonlinear features from EEG signals to improve the accuracy of motor imagery classification. First, principal component analysis (PCA) is used to extract the linear features from EEG, and linear discriminant analysis (LDA) is introduced to supplement the discriminant features by utilizing the label information of the training data. Second, we use parametric t-distributed stochastic neighbor embedding (PTSNE) to extract the nonlinear features reflecting the original manifold structure of the EEG data. Third, these linear and nonlinear features are fused to generate the final features for classification. After feature extraction, we choose the hierarchical extreme learning machine (HELM) algorithm, which has a high classification accuracy for EEG signal classification of motor imagery. To verify the validity of the strategy, we compare the accuracy of the proposed method with that of other methods on the motor imagery dataset. We achieve a high accuracy of 95.89% and an average accuracy of 93.45%. The performance shows that the accuracy of the proposed feature fusion strategy is effective for classification and that the recognition accuracy is improved compared with other state-of-the-art methods.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
2.
go back to reference Ruffino C, Papaxanthis C, Lebon F. Neural plasticity during motor learning with motor imagery practice: review and perspectives. Neuroscience. 2017;341:61.CrossRef Ruffino C, Papaxanthis C, Lebon F. Neural plasticity during motor learning with motor imagery practice: review and perspectives. Neuroscience. 2017;341:61.CrossRef
3.
go back to reference Wong CK, Luo Q, Zotev V, et al. Automatic cardiac cycle determination directly from EEG-fMRI data by multi-scale peak detection method. J Neurosci Methods. 2018. Wong CK, Luo Q, Zotev V, et al. Automatic cardiac cycle determination directly from EEG-fMRI data by multi-scale peak detection method. J Neurosci Methods. 2018.
4.
go back to reference Jain A, Abbas B, Farooq O, et al. Fatigue detection and estimation using auto-regression analysis in EEG. International Conference on Advances in Computing, Communications and Informatics. IEEE. 2016:1092-1095. Jain A, Abbas B, Farooq O, et al. Fatigue detection and estimation using auto-regression analysis in EEG. International Conference on Advances in Computing, Communications and Informatics. IEEE. 2016:1092-1095.
5.
go back to reference Ahirwal MK, Kumar A, Singh GK. Adaptive filtering of EEG/ERP through bounded range artificial bee colony (BR-ABC) algorithm. Digital Signal Process. 2014;25(1):164–72.CrossRef Ahirwal MK, Kumar A, Singh GK. Adaptive filtering of EEG/ERP through bounded range artificial bee colony (BR-ABC) algorithm. Digital Signal Process. 2014;25(1):164–72.CrossRef
6.
go back to reference Ahirwal MK, Kumar A, Singh GK. Adaptive filtering of EEG/ERP through noise cancellers using an improved PSO algorithm. Swarm Evol Comput. 2014;14:76–91.CrossRef Ahirwal MK, Kumar A, Singh GK. Adaptive filtering of EEG/ERP through noise cancellers using an improved PSO algorithm. Swarm Evol Comput. 2014;14:76–91.CrossRef
7.
go back to reference Pan X, Xue L, Lu Y, et al. Hybrid particle swarm optimization with simulated annealing. Multimed Tools Appl. 2019;78(21):29921–36.CrossRef Pan X, Xue L, Lu Y, et al. Hybrid particle swarm optimization with simulated annealing. Multimed Tools Appl. 2019;78(21):29921–36.CrossRef
8.
go back to reference Taran S, Bajaj V. Sleep apnea detection using artificial bee colony optimize Hermite basis functions for EEG signals. IEEE Trans Instrum Meas. 2019. Taran S, Bajaj V. Sleep apnea detection using artificial bee colony optimize Hermite basis functions for EEG signals. IEEE Trans Instrum Meas. 2019.
9.
go back to reference Rajaguru H, Prabhakar S K. Power spectral density with correlation dimension for epilepsy classification from EEG signal. International Conference on Communication and Electronics Systems. 2017:376-379. Rajaguru H, Prabhakar S K. Power spectral density with correlation dimension for epilepsy classification from EEG signal. International Conference on Communication and Electronics Systems. 2017:376-379.
10.
go back to reference Al-Marridi AZ, Mohamed A, Erbad A. Convolutional autoencoder approach for EEG compression and reconstruction in m-health systems. In Proc. 14th Int. Wireless Commun. Mobile Comput. Conf. (IWCMC), Jun. 2018, pp. 370-375. Al-Marridi AZ, Mohamed A, Erbad A. Convolutional autoencoder approach for EEG compression and reconstruction in m-health systems. In Proc. 14th Int. Wireless Commun. Mobile Comput. Conf. (IWCMC), Jun. 2018, pp. 370-375.
11.
go back to reference Tang X, Yang J, Wan H. A hybrid SAE and CNN classifier for motor imagery EEG classification // Artificial Intelligence and Algorithms in Intelligent Systems. 2019. Tang X, Yang J, Wan H. A hybrid SAE and CNN classifier for motor imagery EEG classification // Artificial Intelligence and Algorithms in Intelligent Systems. 2019.
12.
go back to reference George ST, Subathra MSP, Sairamya NJ, et al. Classification of epileptic EEG signals using PSO based artificial neural network and tunable-Q wavelet transform. Biocybern Biomed Eng. 2020. George ST, Subathra MSP, Sairamya NJ, et al. Classification of epileptic EEG signals using PSO based artificial neural network and tunable-Q wavelet transform. Biocybern Biomed Eng. 2020.
13.
go back to reference Tang Z. Conditional adversarial domain adaptation neural network for motor imagery EEG decoding. Entropy. 2020;22(1):96.MathSciNetCrossRef Tang Z. Conditional adversarial domain adaptation neural network for motor imagery EEG decoding. Entropy. 2020;22(1):96.MathSciNetCrossRef
14.
go back to reference Mammone N, Ieracitano C, Morabito FC. A deep CNN approach to decode motor preparation of upper limbs from time-frequency maps of EEG signals at source level. Neural Netw. 2020;124:357–72.CrossRef Mammone N, Ieracitano C, Morabito FC. A deep CNN approach to decode motor preparation of upper limbs from time-frequency maps of EEG signals at source level. Neural Netw. 2020;124:357–72.CrossRef
15.
go back to reference Tortora S, Ghidoni S, Chisari C, et al. Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network. J Neural Eng. 2020. Tortora S, Ghidoni S, Chisari C, et al. Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network. J Neural Eng. 2020.
16.
go back to reference Cai H, Sha X, Han X, Wei S, Hu B. Pervasive EEG diagnosis of depression using deep belief network with three-electrodes EEG collector. In Proc. IEEE Int. Conf. Bioinformatics Biomed. (BIBM), Dec. 2016, pp, 1239-1246. Cai H, Sha X, Han X, Wei S, Hu B. Pervasive EEG diagnosis of depression using deep belief network with three-electrodes EEG collector. In Proc. IEEE Int. Conf. Bioinformatics Biomed. (BIBM), Dec. 2016, pp, 1239-1246.
17.
go back to reference Cheng L, Li D, Yu G, et al. A motor imagery EEG feature extraction method based on energy principal component analysis and deep belief networks. IEEE Access. 2020;8:21453–72.CrossRef Cheng L, Li D, Yu G, et al. A motor imagery EEG feature extraction method based on energy principal component analysis and deep belief networks. IEEE Access. 2020;8:21453–72.CrossRef
18.
go back to reference Dong W, Woźniak M, Wu J, et al. Denoising aggregation of graph neural networks by using principal component analysis. IEEE Trans Industr Inf. 2022;19(3):2385–94.CrossRef Dong W, Woźniak M, Wu J, et al. Denoising aggregation of graph neural networks by using principal component analysis. IEEE Trans Industr Inf. 2022;19(3):2385–94.CrossRef
19.
go back to reference Huang S, Zhang J, Yang C, et al. The interval grey QFD method for new product development: integrate with LDA topic model to analyze online reviews. Eng Appl Artif Intell. 2022;114. Huang S, Zhang J, Yang C, et al. The interval grey QFD method for new product development: integrate with LDA topic model to analyze online reviews. Eng Appl Artif Intell. 2022;114.
20.
go back to reference Li Z, Nie F, Wu D, et al. Sparse trace ratio LDA for supervised feature selection. IEEE Trans Cybern. 2023. Li Z, Nie F, Wu D, et al. Sparse trace ratio LDA for supervised feature selection. IEEE Trans Cybern. 2023.
21.
go back to reference Han X, Su J, Hong Y, et al. Mid-to long-term electric load forecasting based on the EMD-Isomap-Adaboost Model. Sustainability. 2022;14(13):7608.CrossRef Han X, Su J, Hong Y, et al. Mid-to long-term electric load forecasting based on the EMD-Isomap-Adaboost Model. Sustainability. 2022;14(13):7608.CrossRef
22.
go back to reference Yang B, Xiang M, Zhang Y. Multi-manifold discriminant Isomap for visualization and classification. Pattern Recogn. 2016;55:215–30.CrossRef Yang B, Xiang M, Zhang Y. Multi-manifold discriminant Isomap for visualization and classification. Pattern Recogn. 2016;55:215–30.CrossRef
23.
go back to reference Liu C, Jaja J, Pessoa L. LEICA: Laplacian eigenmaps for group ICA decomposition of fMRI data. Neuroimage. 2017;169:363–73.CrossRef Liu C, Jaja J, Pessoa L. LEICA: Laplacian eigenmaps for group ICA decomposition of fMRI data. Neuroimage. 2017;169:363–73.CrossRef
24.
go back to reference Ward JL, Lumsden SL. Locally linear embedding: dimension reduction of massive protostellar spectra. Mon Not R Astron Soc. 2016;461(2). Ward JL, Lumsden SL. Locally linear embedding: dimension reduction of massive protostellar spectra. Mon Not R Astron Soc. 2016;461(2).
25.
go back to reference Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9(Nov):2579-2605. Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9(Nov):2579-2605.
26.
go back to reference Lee JA, Peluffo-Ordoñez DH, Verleysen M. Multiscale stochastic neighbor embedding: towards parameter-free dimensionality reduction. ESANN. 2014. Lee JA, Peluffo-Ordoñez DH, Verleysen M. Multiscale stochastic neighbor embedding: towards parameter-free dimensionality reduction. ESANN. 2014.
27.
go back to reference Richhariya B, Tanveer M. EEG signal classification using universum support vector machine. Expert Syst Appl. 2018. Richhariya B, Tanveer M. EEG signal classification using universum support vector machine. Expert Syst Appl. 2018.
28.
go back to reference Kasun LLC, Zhou H, Huang G, et al. Representational learning with ELMs for big data. Intelligent Systems IEEE. 2013;28(6):31–4. Kasun LLC, Zhou H, Huang G, et al. Representational learning with ELMs for big data. Intelligent Systems IEEE. 2013;28(6):31–4.
29.
go back to reference Huang GB, Zhu Q, Siew C. Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings of the 2004 International Joint Conference on Neural Networks; 2004. vol. 2, pp. 985-990. Huang GB, Zhu Q, Siew C. Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings of the 2004 International Joint Conference on Neural Networks; 2004. vol. 2, pp. 985-990.
30.
go back to reference Tang J, Deng C, Huang GB. Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst. 2016;27(4):809–21.MathSciNetCrossRef Tang J, Deng C, Huang GB. Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst. 2016;27(4):809–21.MathSciNetCrossRef
31.
go back to reference Zhu WT, Miao J, Qing LY (2014) Constrained extreme learning machine: a novel highly discriminative random feedforward neural network, 2014 International Joint Conference on Neural Networks (IJCNN2014). Beijing, July 6-11, 2014. United Stated, IEEE. Zhu WT, Miao J, Qing LY (2014) Constrained extreme learning machine: a novel highly discriminative random feedforward neural network, 2014 International Joint Conference on Neural Networks (IJCNN2014). Beijing, July 6-11, 2014. United Stated, IEEE.
32.
go back to reference Duan L, Bao M, Cui S, et al. Motor imagery EEG classification based on kernel hierarchical extreme learning machine. Cogn Comput. 2017;9(6):1–8.CrossRef Duan L, Bao M, Cui S, et al. Motor imagery EEG classification based on kernel hierarchical extreme learning machine. Cogn Comput. 2017;9(6):1–8.CrossRef
34.
go back to reference Mensh BD, Werfel J, Seung HS. BCI competition 2003-data set Ia: combining gamma-band power with slow cortical potentials to improve single-trial classification of electroencephalographic signals. IEEE Trans Biomed Eng. 2004;51(6):1052–6.CrossRef Mensh BD, Werfel J, Seung HS. BCI competition 2003-data set Ia: combining gamma-band power with slow cortical potentials to improve single-trial classification of electroencephalographic signals. IEEE Trans Biomed Eng. 2004;51(6):1052–6.CrossRef
35.
go back to reference Sun S, Zhang C. Assessing features for electroencephalographic signal categorization. IEEE International Conference on Acoustics, Speech, and Signal Processing. 2005. Proceedings. IEEE, 2005:v/417-v/420 Vol. 5. Sun S, Zhang C. Assessing features for electroencephalographic signal categorization. IEEE International Conference on Acoustics, Speech, and Signal Processing. 2005. Proceedings. IEEE, 2005:v/417-v/420 Vol. 5.
36.
go back to reference Wang B, Jun L, Bai J, et al. EEG recognition based on multiple types of information by using wavelet packet transform and neural networks. Engineering in Medicine and Biology Society, 2005. IEEE-Embs 2005. International Conference of the. IEEE. 2005:5377-5380. Wang B, Jun L, Bai J, et al. EEG recognition based on multiple types of information by using wavelet packet transform and neural networks. Engineering in Medicine and Biology Society, 2005. IEEE-Embs 2005. International Conference of the. IEEE. 2005:5377-5380.
37.
go back to reference Wu T, Yan GZ, Yang BH, et al. EEG feature extraction based on wavelet packet decomposition for brain computer interface. Measurement. 2008;41(6):618–25.CrossRef Wu T, Yan GZ, Yang BH, et al. EEG feature extraction based on wavelet packet decomposition for brain computer interface. Measurement. 2008;41(6):618–25.CrossRef
38.
go back to reference Kayikcioglu T, Aydemir O. A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data. Elsevier Science Inc. 2010. Kayikcioglu T, Aydemir O. A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data. Elsevier Science Inc. 2010.
39.
go back to reference Abdel-Basset M, Manogaran G, El-Shahat D, et al. A hybrid whale optimization algorithm based on local search strategy for the permutation flow shop scheduling problem. Futur Gener Comput Syst. 2018;85:129–45.CrossRef Abdel-Basset M, Manogaran G, El-Shahat D, et al. A hybrid whale optimization algorithm based on local search strategy for the permutation flow shop scheduling problem. Futur Gener Comput Syst. 2018;85:129–45.CrossRef
Metadata
Title
A Novel Feature Fusion Approach for Classification of Motor Imagery EEG Based on Hierarchical Extreme Learning Machine
Authors
Lijuan Duan
Zhaoyang Lian
Yuanhua Qiao
Juncheng Chen
Jun Miao
Mingai Li
Publication date
10-11-2023
Publisher
Springer US
Published in
Cognitive Computation / Issue 2/2024
Print ISSN: 1866-9956
Electronic ISSN: 1866-9964
DOI
https://doi.org/10.1007/s12559-023-10217-5

Other articles of this Issue 2/2024

Cognitive Computation 2/2024 Go to the issue

Premium Partner