Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Nonlinear Feature Analysis for EEG-Based Biometric Authentication via Machine-Learning

Makine Öğrenmesi Yoluyla EEG Tabanlı Biyometrik Kimlik Doğrulama için Doğrusal Olmayan Özellik Analizi

How to cite: Özdemir MY, İşler Y. Nonlinear feature analysis for eeg-based biometric authentication via machine-learning. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2023; 6(2): 27-33. DOI: 10.54856/jiswa.202312237

Full Text: PDF, in English.

Total number of downloads: 58

Title: Nonlinear Feature Analysis for EEG-Based Biometric Authentication via Machine-Learning

Abstract: Among biometric recognition systems, a system using brain waves via EEG will hold a special place. The EEG signal, with its nonlinear structure, is unique to the individual and nearly impossible to replicate. In designing such a system, various signal processing and classification methods are considered. In this study, nonlinear features such as Fractal Dimension, Second Order Sample Entropy, Quantities Graph, and Visibility Graph were used, allowing the examination of the EEG signal independently of the amplitude scale. To reduce computational load, the resting state alpha waves, which are prominent features of the EEG, were focused on, and a low number (8) of electrodes were used. The obtained features were analyzed separately for each electrode, aiming to identify the most distinctive feature and electrode. The classification was performed using five different machine-learning methods. The highest accuracy was achieved by the Random Forest algorithm. The most distinctive electrode and features were identified as the Fractal Dimension of the F5 electrode and the Fractal Dimension of the Oz electrode.

Keywords: EEG, biometric, fractal dimension, quadratic sample entropy, quantiles graph, visibility graph


Başlık: Makine Öğrenmesi Yoluyla EEG Tabanlı Biyometrik Kimlik Doğrulama için Doğrusal Olmayan Özellik Analizi

Özet: Biyometrik tanıma sistemleri arasında EEG ile beyin dalgalarının kullanıldığı bir sistem özel bir yer teşkil edecektir. EEG sinyali nonlinear yapısıyla kişiye özgüdür ve taklit edilmesi neredeyse imkansızdır. Böyle bir sistemin tasarlanması aşamasında farklı sinyal işleme ve sınıflama yöntemleri ele alınmaktadır. Bu çalışmada EEG sinyalini genlik skalasından bağımsız bir şekilde incelemeye fırsat verecek doğrusal olmayan Fraktal Boyut, İkinci Dereceden Örnek Entropisi, Nicelikler Grafiği, Görünürlük Grafiği özellikleri kullanılmıştır. Hesaplama yükünü azaltmak için EEG'nin belirgin özelliklerinden olan resting state alfa dalgaları odağa alınmış ve düşük sayıda elektrot (8) kullanılmıştır. Elde edilen özellikler her bir elektrot için ayrı ayrı ele alınmış, sonuçta en büyük ayırt ediciliği gösteren özellik ve elektrotun saptanması amaçlanmıştır. 5 farklı makine öğrenmesi metoduyla sınıflama gerçekleştirilmiştir. En yüksek doğruluk Rastgele Orman algoritmasına aittir. En ayırt edici elektrot ve özellikler F5 elektrotu Fraktal Boyutu ve Oz elektrotu Fractal Boyutu özelliği olarak bulunmuştur.

Anahtar kelimeler: EEG, biometrik, fraktal boyut, ikinci dereceden örnek entropisi, nicelikler grafiği, görünürlük grafiği


Bibliography:
  • Sayilgan E, Yuce YK, Isler Y. Prediction of evoking frequency from steady-state visual evoked frequency. Natural and Engineering Sciences 2019; 4(3): 91–99.
  • Sayilgan E, Yuce YK, Isler Y. Estimation of three distinct commands using fourier transform of steady-state visual-evoked potentials. Duzce Universitesi Bilim ve Teknoloji Dergisi 2020; 8(4): 2337–2343.
  • Sayilgan E, Yuce YK, Isler Y. Frequency recognition from temporal and frequency depth of the brain-computer interface based on steady-state visual evoked potentials. Journal of Intelligent Systems with Applications 2021; 4(1): 68–73.
  • Degirmenci M, Yuce YK, Isler Y. Motor imaginary task classification using statistically significant time domain and frequency domain EEG features. Journal of Intelligent Systems with Applications 2022; 5(1): 49–54.
  • Jain AK, Bolle R, Pankanti S. Biometrics: Personal Identification in Networked Society. Vol. 479. Springer Science & Business Media, 2006.
  • Matsumoto T, Matsumoto H, Yamada K, Hoshino S. Impact of artificial gummy fingers on fingerprint systems. In Optical security and counterfeit deterrence techniques IV, vol. 4677, pp. 275–289, SPIE, 2002.
  • Maiorana E, Campisi P. Longitudinal evaluation of eeg-based biometric recognition. IEEE Transactions on Information Forensics and Security 2017; 13(5): 1123–1138.
  • Paranjape R, Mahovsky J, Benedicenti L, Koles Z. The elec-troencephalogram as a biometric. In Canadian Conference on Elec-trical and Computer Engineering 2001. Conference Proceedings (Cat. No. 01TH8555), vol. 2, pp. 1363–1366, IEEE, 2001.
  • Nakanishi I, Baba S, Miyamoto C. EEG based biometric authen-tication using new spectral features. In 2009 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 651–654, IEEE, 2009.
  • Wang M, Hu J, Abbass HA. Brainprint: EEG biometric identification based on analyzing brain connectivity graphs. Pattern Recognition 2020; 105: 107381.
  • Castellanos NP, Makarov VA. Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis. Journal of Neuroscience Methods 2006; 158(2): 300–312.
  • Kothe CA, Makeig S. BCILAB: A platform for brain–computer interface development. Journal of Neural Engineering 2013; 10(5): 056014.
  • Delorme A, Makeig S. EEGLAB: An open source toolbox for analysis of single-trial eeg dynamics including independent component analysis. Journal of Neuroscience Methods 2004; 134(1): 9–21.
  • Katz MJ. Fractals and the analysis of waveforms. Computers in Biology and Medicine 1988; 18(3): 145–156.
  • Richman JS, Moorman JR. Physiological time-series anal-ysis using approximate entropy and sample entropy,” American Journal of Physiology-Heart and Circulatory Physiology 2000; 278(6): H2039–H2049.
  • Delgado-Bonal A, Marshak A. Approximate entropy and sample entropy: A comprehensive tutorial. Entropy 2019; 21(6): 541.
  • Lake DE, Moorman JR. Accurate estimation of entropy in very short physiological time series: the problem of atrial fibrillation detec-tion in implanted ventricular devices. American Journal of Physiology-Heart and Circulatory Physiology 2011; 300(1): H319–H325.
  • Simons S, Abasolo D, Escudero J. Classification of alzheimer's disease from quadratic sample entropy of electroencephalogram. Healthcare Technology Letters 2015; 2(3): 70–73.
  • Campanharo AS, Doescher E, Ramos FM. Automated eeg signals analysis using quantile graphs. In Advances in Computational Intelligence: 14th International Work-Conference on Artificial Neural Networks, IWANN 2017, Cadiz, Spain, June 14-16, 2017, Proceedings, Part II 14, pp. 95–103, Springer, 2017.
  • Pineda AM, Ramos FM, Betting LE, Campanharo AS. Quantile graphs for EEG-based diagnosis of alzheimer's disease. Plos One 2020; 15(6): e0231169.
  • Lacasa L, Luque B, Ballesteros F, Luque J, Nuno JC. From time series to complex networks: The visibility graph. Proceedings of the National Academy of Sciences 2008; 105(13): 4972–4975.
  • Ahmadlou M, Adeli H, Adeli A. New diagnostic eeg markers of the alzheimer’s disease using visibility graph. Journal of Neural Transmission 2010; 117: 1099-1109.
  • Lanczos C. An iteration method for the solution of the eigenvalue problem of linear differential and integral operators. Journal of Research of the National Bureau of Standards, 1950.
  • Alpaydin E. Introduction to Machine Learning. MIT press, 2020.
  • Vapnik VN. The support vector method. In International conference on artificial neural networks, pp. 261–271, Springer, 1997.
  • Wu X, Kumar V, Ross Quinlan J, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Yu PS, et al. Top 10 algorithms in data mining. Knowledge and Information Systems 2008; 14: 1–37.
  • Hastie T, Tibshirani R, Friedman JH, Friedman JH. The elements of statistical learning: data mining, inference, and prediction, vol. 2. Springer, 2009.
  • Breiman L. Random forests. Machine Learning 2001; 45: 5–32.
  • Smith NB, Webb A. Introduction to Medical Imaging: Physics, Engineering and Clinical Applications. Cambridge university press, 2010.