Abstract
Electroencephalogram (EEG) signals are possible biomarkers for person recognition. Biometric systems use an interdisciplinary approach for improving the accuracy of person identification. This paper describes different feature extraction schemes for the classification of EEG signals. Autoregressive model features come out best performing features among all. After feature extraction, feature selection techniques are applied to improve classification accuracy by reducing the dimensions of data, which help in reducing computation cost and chances of overfitting of data. Principal component analysis (PCA) and linear discriminant analysis (LDA) are used for dimensionality reduction. Furthermore, different machine learning algorithms are used for the classification of EEG signals. The outcomes of this study indicate that the higher classification accuracy of 99.80% is achieved with LDA as a feature selection and K-nearest-neighbour as a classifier. The findings of the study demonstrate that the proposed combination of feature extraction, feature selection, and classification technique has the potential to classify the EEG signals for person identification.




Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Availability of data and materials
Online available dataset published by UCI KDD (Hettich, S. and Bay 1999) is used in current study.
References
Kaliraman B, Vig R (2016) Iris recognition using hybrid transform. Commun Comput Syst. https://doi.org/10.1201/9781315364094
Poulos M, Rangoussi M, Chrissikopoulos V, Evangelou A (1999) Person identification based on parametric processing of the EEG. In: Electronics, circuits and systems. Proceedings of ICECS, vol 1, no 1, pp 283–286, 1999. https://doi.org/10.1109/ICECS.1999.813403
Kaliraman B, Singh P, Duhan M (2020) Use of EEG as a unique human biometric trait for authentication of an individual. In: Advances in communication and computational technology. pp 277–286. https://doi.org/10.1007/978-981-15-5341-7_5
Bhawna K, Priyanka, Duhan M (2020) Electroencephalogram based biometric system: a review. In: Advances in communication and computational technology. pp 57–77. https://doi.org/10.1007/978-981-15-5341-7_23
Coronato A, Cuzzocrea A (2020) An innovative risk assessment methodology for medical information systems. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2020.3023553
Nakra A, Duhan M (2020) Feature extraction and dimensionality reduction techniques with their advantages and disadvantages for EEG-Based BCI system: a review. IUP J Comput Sci 14(1):21–34
Nishimoto T, Higashi H, Morioka H, Ishii S (2020) EEG-Based Personal identification method using unsupervised feature extraction and its robustness against intra-subject variability. J Neural Eng 17(2):026007. https://doi.org/10.1088/1741-2552/ab6d89
Abed SS, Abed ZF (2020) User authentication system based specified brain waves. J Discrete Math Sci Cryptogr 23(5):1021–1024. https://doi.org/10.1080/09720529.2019.1700920
Chawla M, Duhan M (2014) Applications of recent metaheuristics optimisation algorithms in biomedical engineering: a review. Int J Biomed Eng Technol 16(3):268–278. https://doi.org/10.1504/IJBET.2014.065807
Kaewwit C, Lursinsap C, Sophatsathit P (2017) High accuracy EEG biometrics identification using ICA and AR model. J ICT 2(2):354–373
Thakur S, Dharavath R, Edla DR (2020) Spark and rule-KNN based scalable machine learning framework for EEG deceit identification. Biomed Signal Process Control 58:101886. https://doi.org/10.1016/j.bspc.2020.101886
Roushdy M, Salem AM, Abdulrahman SA (2019) Human Identification based on electroencephalography signals using sample entropy and horizontal visibility graphs. WSEAS Trans Signal Process 15, e-issn: 2224-3488.
Ullah H, Aamir A, Malik S, Fayyaz R (2015) Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques. Australas Phys Eng Sci Med. https://doi.org/10.1007/s13246-015-0333-x
Yazdani A, Roodaki A, Rezatofighi SH, Misaghian K, Setarehdan SK (2008) Fisher linear discriminant based person identification using visual evoked potentials. In: 9th international conference on signal processing, 2008. https://doi.org/10.1109/ICOSP.2008.4697459
Delpozo-banos M, Travieso CM, Weidemann CT, Alonso JB (2015) EEG biometric identification : a thorough exploration of the time-frequency domain. J Neural Eng 12:056019. https://doi.org/10.1088/1741-2560/12/5/056019
Hettich SD, Bay S (1999) The UCI KDD archive. http://kdd.ics.uci.edu. Accessed 17 June 2020
Snodgrass JG, Vanderwart M (1980) A standardized set of 260 pictures: norms for name agreement, image agreement, familiarity, and visual complexity. J Exp Psychol Hum Learn Mem 6(2):174–215. https://doi.org/10.1037/0278-7393.6.2.174
Hjorth B (1970) EEG analysis based on time domain properties. Electroencephalogr Clin Neurophysiol 29(3):306–310. https://doi.org/10.1016/0013-4694(70)90143-4
Akansu AN, Haddad RA (2001) Wavelet transform. Multiresolution signal decomposition. Elsevier, pp 391–442
Heideman M, Johnson D, Burrus CS (1984) Gauss and the History of the fast Fourier transform. IEEE Signal Process Mag 1(3):14–21
Contributors W (2020) Autoregressive model. Wikipedia, the free encyclopedia. https://en.wikipedia.org/w/index.php?title=Autoregressive_model&oldid=950903028. Accessed 03 Jul 2020
McLachlan GJ (2004) Discriminant Analysis And Statistical Pattern Recognition. Wiley
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794, 2016. https://doi.org/10.1145/2939672.2939785
Ho TK (1995) Random decision forests. In: Proceedings of the international conference on document analysis and recognition, ICDAR, vol 1, pp 278–282, 1995. https://doi.org/10.1109/ICDAR.1995.598994
Parekh M CNN. https://medium.com/nybles/a-brief-guide-to-convolutional-neural-network-cnn-642f47e88ed4
Das R, Maiorana E, Campisi P (2017) Visually evoked potential for EEG biometrics using convolutional neural network. In: 25th European signal processing conference, EUSIPCO 2017, vol 2017-January, pp 951–955, 2017. https://doi.org/10.23919/EUSIPCO.2017.8081348
Xu G et al (2019) A deep transfer convolutional neural network framework for EEG signal classification. IEEE Access 7:112767–112776. https://doi.org/10.1109/ACCESS.2019.2930958
Ozdenizci O, Wang Y, Koike-Akino T, Erdogmus D (2019) Adversarial deep learning in EEG biometrics. IEEE Signal Process Lett 26(5):710–714. https://doi.org/10.1109/LSP.2019.2906826
Acknowledgements
I would like to give a sincere thanks to my Ph.D. supervisor, Dr. Manoj Duhan, for his constant guidance as well as providing necessary information and for reviewing various drafts of this paper.
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kaliraman, B., Duhan, M. A new hybrid approach for feature extraction and selection of electroencephalogram signals in case of person recognition. J Reliable Intell Environ 7, 241–251 (2021). https://doi.org/10.1007/s40860-021-00148-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40860-021-00148-z