Abstract
Nowadays, classifying electroencephalogram (EEG) signals based motor imagery tasks is extensively used to control brain-computer interface applications, as a communication bridge between humans and computers. In this paper, we propose signal-to-image transformation and feature extraction methods for the classification of motor imagery. Specifically, a continuous wavelet transform is applied to decompose EEG signals into five rhythms and generate time-frequency images. Then, a gray-level co-occurrence matrix is used to extract global texture features on time-frequency images. Finally, the SVM classification model is optimized by using a grid search algorithm to select optimal parameter pairs \((C,\sigma )\). To confirm the validity of the proposed methods, we experimented on self-collected data, which is obtained using a consumer-grade EEG device. The experimental result showed that this proposed method can achieve an acceptable classification accuracy of 90% for a two-class problem (left/right-hand motor imagery).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Daly, I., Scherer, R., Billinger, M., Müllerputz, G.: FORCe: fully online and automated artifact removal for brain-computer interfacing. IEEE Trans. Neural Syst. Rehabil. Eng. Publ. IEEE Eng. Med. Biol. Soc. 23(5), 725 (2014)
Corsi, M.C., Chavez, M., Schwartz, D.: Integrating EEG and MEG signals to improve motor imagery classification in brain-computer interfaces. Int. J. Neural Syst. 29(01), 1850014 (2019)
Lu, P., Yuan, D., Lou, Y., Liu, C., Huang, S.: Single-trial identification of motor imagery EEG based on HHT and SVM. In: Sun, Z., Deng, Z. (eds.) Proceedings of 2013 Chinese Intelligent Automation Conference. LNCS, vol. 256, pp. 681–689. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38466-0_75
Sahu, M., Shukla, S.: Impact of feature selection on EEG based motor imagery. In: Fong, S., Akashe, S., Mahalle, P.N. (eds.) Information and Communication Technology for Competitive Strategies. LNNS, vol. 40, pp. 749–762. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-0586-3_73
Kumar, S., Sharma, A.: A new parameter tuning approach for enhanced motor imagery EEG signal classification. Med. Biol. Eng. Comput. 56(10), 1861–1874 (2018)
Zhang, Y., Liu, B., Ji, X., Huang, D.: Classification of EEG signals based on autoregressive model and wavelet packet decomposition. Neural Process. Lett. 45(2), 365–378 (2017)
Han, D., Li, P., An, S., Shi, P.: Multi-frequency weak signal detection based on wavelet transform and parameter compensation band-pass multi-stable stochastic resonance. Mech. Syst. Signal Process. 70–71, 995–1010 (2016)
Shi, T., Ren, L., Cui, W.: Feature recognition of motor imaging EEG signals based on deep learning. Pers. Ubiquitous Compu. 23(3–4), 499–510 (2019)
Hsu, W.Y.: Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification. Expert Syst. Appl. 39(1), 1055–1061 (2012)
Sid, A.B., Nawal, B., Mohamed, D.K.: CSP features extraction and FLDA classification of EEG-based motor imagery for brain-computer interaction. In: International Conference on Electrical Engineering (2016)
Li, Y., Cui, W., Luo, M., Li, K., Wang, L.: Epileptic seizure detection based on time-frequency images of EEG signals using gaussian mixture model and gray level co-occurrence matrix features. Int. J. Neural Syst. 28(07), 1850003 (2018)
Boubchir, L., Al-Maadeed, S., Bouridane, A., Cherif, A.A.: Classification of EEG signals for detection of epileptic seizure activities based on LBP descriptor of time-frequency images. In: IEEE International Conference on Image Processing (2015)
Lotte, F., Guan, C.: Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Trans. Biomed. Eng. 58(2), 355–362 (2011)
Yger, F., Lotte, F., Sugiyama, M.: Averaging covariance matrices for EEG signal classification based on the CSP: an empirical study. In: European Signal Processing Conference (EUSIPCO), pp. 2721–2725 (2015)
Mishuhina, V., Jiang, X.: Feature weighting and regularization of common spatial patterns in EEG-based motor imagery BCI. IEEE Signal Process. Lett. 25(6), 783–787 (2018)
Singh, A., Lal, S., Guesgen, H.: Reduce calibration time in motor imagery using spatially regularized symmetric positives-definite matrices based classification. Sensors 19(2), 379 (2019)
Acknowledgment
This work was supported by the National Natural Science Foundation of China [U1809209, 61702376, 61972187, 61772254], the Major Project of Wenzhou Natural Science Foundation [ZY2019020], the Key Project of Zhejiang Provincial Natural Science Foundation [LSZ19F020001], Fujian Provincial Leading Project [2017H0030, 2019H0025], Government Guiding Regional Science and Technology Development [2019L3009], and Natural Science Foundation of Fujian Province [2017J01768, 2019J01756]. We acknowledge the efforts and constructive comments of respected editors and anonymous reviewers.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, Z., Hu, Z., Li, Z. (2020). Estimation of Motor Imagination Based on Consumer-Grade EEG Device. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12487. Springer, Cham. https://doi.org/10.1007/978-3-030-62460-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-62460-6_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62459-0
Online ISBN: 978-3-030-62460-6
eBook Packages: Computer ScienceComputer Science (R0)