EEG Signal Processing and Its Classification for Rehabilitation Device Control
At this present technology-based world, electroencephalography (EEG) instruments have become a tool for various research and diagnoses of different human health disorders. The brain-computer interface (BCI) is an area which is a very much emerging technology that uses the human brain signals to control external devices. For excellent and accurate results, BCI has recognized the need for systems that makes it more user-friendly, real time, manageable, and suited for people like clinical and disabled patients. Thus, this chapter will refer to the processing of the EEG signal and different classification techniques which will further be used to control the rehabilitation devices through BCI system.
A medical diagnostic technique that reads the electrical activity of the scalp which is generated by a human brain is known as electroencephalography, and the recording is called electroencephalogram (EEG). The electrical activity from the scalp of the brain is mainly picked up using metal electrodes having a conductive media. An EEG recording system is a combination of a couple of instruments. They are electrodes consisting of a conductive media, amplifiers and filters, analog-to-digital converters, and recording device/printer. Feature extraction and classification of electroencephalograph signals for human subjects is a challenge for both the engineers and scientists. Mainly fast Fourier transform (FFT), Lyapunov exponent, correlation dimension, and wavelet transformation are the tools for EEG signal processing. There are also various signal processing techniques for classification of nonlinear and nonstationary signals like EEG. Some of the signal processing techniques are support vector machine (SVM) and multilayer perceptron (MLP)-based classifier, back-propagation neural network, self-organizing feature maps followed by an autoregressive modeling and artificial neural network, etc. The classification rate calculated using the various classification techniques can further be used to control the rehabilitation devices like artificial limbs (hand and leg). The advances in brain-computer interface (BCI) research and its applications have given a significant impact to biomedical research. This would be a boon for the person with disability so that they can interact and go through their day-to-day work smoothly with the help of the rehabilitation devices.
KeywordsElectroencephalograph (EEG) Rehabilitation Signal processing Signal classification
This study has been ethically approved by the Institutional Ethical Committee, NEHU, Shillong, vide no: IECHSP/2017/42 and also from the collaborating institute: “North Eastern Indira Gandhi Regional Institute of Health & Medical Science,” Shillong, vide no: NEIGR/IEC/M6/F13/18.
- 3.Atwood HL, MacKay WA (1989) Essentials of neurophysiology. Decker, TorontoGoogle Scholar
- 4.Azlan WAW, Low YF (2014) Feature extraction of electroencephalogram (EEG) signal – a review. Paper presented at the 2014 IEEE conference on Biomedical Engineering and Sciences (IECBES), December 8–10Google Scholar
- 9.Guerrero-Mosquera C, Vazquez AN (2009) New approach in features extraction for EEG signal detection. In: Conference proceedings : Annual international conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual conference, 2009, 13–16. https://doi.org/10.1109/iembs.2009.5332434
- 11.Hsin HC, Li CC, Sun M, Sclabassi RJ (1992) An adaptive training algorithm for back-propagation neural networks. Paper presented at the [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics, October 18–21Google Scholar
- 12.Ince NF, Tewfik A, Arica S (2005). Classification of movement EEG with local discriminant bases. Paper presented at the proceedings. (ICASSP ‘05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005, March 18–23Google Scholar
- 14.Jian-Zhong X, Hui Z, Chong-Xun Z, Xiang-Guo Y (2003) Wavelet packet transform for feature extraction of EEG during mental tasks. Paper presented at the proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693), November 2–5Google Scholar
- 15.Kalpakam NV, Venkataramanan S (2004) Haar wavelet decomposition of EEG signal for ocular artifact de-noising: a mathematical analysisGoogle Scholar
- 17.Kotsiantis SB (2007) Supervised machine learning: a review of classification techniques. Paper presented at the proceedings of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive TechnologiesGoogle Scholar
- 18.Li K, Sun G, Zhang B, Wu S, Wu G (2009) Correlation between forehead EEG and sensorimotor area EEG in motor imagery task. Paper presented at the 2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing, December 12–14Google Scholar
- 19.Makeig S, Jung T-P (1996) Changes in alertness is principal component of variance in the EEG spectrum, vol 7Google Scholar
- 20.Maki H, Toda T, Sakti S, Neubig G, Nakamura S (2015) EEG signal enhancement using multi-channel wiener filter with a spatial correlation prior. Paper presented at the 2015 IEEE international conference on Acoustics, Speech and Signal Processing (ICASSP), 19–24 April 2015Google Scholar
- 26.Panahi N, Shayesteh MG, Mihandoost S, Varghahan BZ (2011) Recognition of different datasets using PCA, LDA, and various classifiers. Paper presented at the 2011 5th international conference on Application of Information and Communication Technologies (AICT), 12–14 Oct 2011Google Scholar
- 27.Petersen SE, Posner MI (2012) The attention system of the human brain: 20 years after. Annu Rev Neurosci 35:73–89. https://doi.org/10.1146/annurev-neuro-062111-150525CrossRefPubMedPubMedCentralGoogle Scholar
- 29.Roman-Gonzalez A (2010) Communication technologies based on brain activity. Paper presented at the 2010 World Congress in Computer Science, Computer Engineering and Applied Computing – WORLDCOMP 2010, July 26, Las VegasGoogle Scholar
- 31.Sarma P, Tripathi P, Sarma MP, Sarma KK (2016) Pre-processing and feature extraction techniques for EEG-BCI applications-a review of recent research. ADBU J Eng Technol 5(1)Google Scholar
- 32.Schomer DL, Lopes da Silva FH (2018) Niedermeyer’s electroencephalography: basic principles, clinical applications, and related fieldsGoogle Scholar
- 33.Tan L (2008) Digital signal processing fundamentals and applications. From http://www.books24x7.com/marc.asp?bookid=28057
- 37.Zurada JM (1992) Introduction to artificial neural systems. West Publishing Company, St. PaulGoogle Scholar