access icon free EEG-based biometric authentication modelling using incremental fuzzy-rough nearest neighbour technique

This paper proposes an Incremental Fuzzy-Rough Nearest Neighbour (IncFRNN) technique for biometric authentication modelling using feature extracted visual evoked. Only small training set is needed for model initialisation. The embedded heuristic update method adjusts the knowledge granules incrementally to maintain all representative electroencephalogram (EEG) signal patterns and eliminate those rarely used. It reshapes the personalized knowledge granules through insertion and deletion of a test object, based on similarity measures. A predefined window size can be used to reduce the overall processing time. This proposed algorithm was verified with test data from 37 healthy subjects. Signal pre-processing steps on segmentation, filtering and artefact rejection were carried out to improve the data quality before model building. The experimental paradigm was designed in three different conditions to evaluate the authentication performance of the IncFRNN technique against the benchmarked incremental K-Nearest Neighbour (KNN) technique. The performance was measured in terms of accuracy, area under the Receiver Operating Characteristic (ROC) curve (AUC) and Cohen's Kappa coefficient. The proposed IncFRNN technique is proven to be statistically better than the KNN technique in the controlled window size environment. Future work will focus on the use of dynamic data features to improve the robustness of the proposed model.

Inspec keywords: pattern classification; fuzzy set theory; medical signal processing; electroencephalography; rough set theory; biometrics (access control); visual evoked potentials; feature extraction

Other keywords: incremental fuzzy-rough nearest neighbour technique; electroencephalogram electrodes; EEG signal patterns; EEG-based biometric authentication; feature extraction; personalised knowledge granules; visual evoked potential; IncFRNN technique

Subjects: Biology and medical computing; Combinatorial mathematics; Signal processing and detection; Combinatorial mathematics; Bioelectric signals; Digital signal processing; Algebra, set theory, and graph theory; Electrodiagnostics and other electrical measurement techniques

References

    1. 1)
      • 29. McHugh, M.L.: ‘Inter-rater reliability: the Kappa statistic’, Biochem. Medica, 2012, 22, (3), pp. 276282.
    2. 2)
      • 10. Švogor, I., Kišasondi, T.: ‘Two factor authentication using EEG augmented passwords’, in 34th International Conference on Information Technology Interfaces, 2012, pp. 373378.
    3. 3)
      • 22. Teplan, M.: ‘Fundamentals of EEG measurement’, Meas. Sci. Rev., 2002, 2, (2), pp. 111.
    4. 4)
      • 20. Baker, D.: ‘Arduino sound to TTL trigger for EEG’, 2013. Available at https://bakerdh.wordpress.com/2013/10/22/arduino-sound-to-ttl-trigger-for-eeg/, accessed 09 April 2014.
    5. 5)
      • 17. Jensen, R., Cornelis, C.: ‘Fuzzy-rough nearest neighbour classification and prediction’, Theor. Comput. Sci., 2011, 412, (42), pp. 58715884.
    6. 6)
      • 23. Liew, S.H., Choo, Y.H., Low, Y.F., et al: ‘Comparing features extraction methods for person authentication using EEG signals’. Pattern Analysis, Intelligent Security and the Internet of Things, 2015, pp. 225235.
    7. 7)
      • 14. Liu, D., Liang, D.: ‘Incremental learning researches on rough set theory: status and future’, Int. J. Rough Sets Data Anal., 2014, 1, (1), pp. 99112.
    8. 8)
      • 3. Marcel, S., Millán, J.D.R.: ‘Person authentication using brainwaves (EEG) and maximum a posteriori model adaptation’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (4), pp. 743752.
    9. 9)
      • 25. Hall, M.A.: ‘Correlation-based feature selection for discrete and numeric class machine learning’. Proceeding ICML ‘00 Proc. 17th Int. Conf. Machine Learning, 2000, pp. 359366.
    10. 10)
      • 16. Hassani, K., Lee, W.: ‘An incremental framework for classification of EEG signals using quantum particle swarm optimization’. in IEEE Int. Conf. Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), 2014, pp. 4045.
    11. 11)
      • 28. Yazdani, A., Roodaki, A., Rezatofighi, S.H., et al: ‘Fisher linear discriminant based person identification using visual evoked potentials’. 2008 Ninth Int. Conf. Signal Processing, 2008, pp. 16771680.
    12. 12)
      • 24. Hu, D.Y., Li, W., Chen, X.: ‘Feature extraction of motor imagery EEG signals based on wavelet packet decomposition’. The 2011 IEEE/ICME Int. Conf. Complex Medical Engineering, 2011, pp. 694697.
    13. 13)
      • 12. Giraud-Carrier, C.: ‘A note on the utility of incremental learning’, AI Commun., 2000, 13, (4), pp. 19.
    14. 14)
      • 18. Qu, Y., Shen, Q., Mac Parthaláin, N., et al: ‘Fuzzy similarity-based nearest-neighbour classification as alternatives to their fuzzy-rough parallels’, Int. J. Approx. Reason., 2013, 54, (1), pp. 184195.
    15. 15)
      • 8. Liew, S.H., Choo, Y.H., Low, Y.F.: ‘Fuzzy-rough nearest neighbour classifier for person authentication using EEG signals’. iFUZZY 2013–2013 Int. Conf. Fuzzy Theory and its Applications, 2013, pp. 316321.
    16. 16)
      • 21. Kisakye, H.S.: ‘Brain computer interfaces: OpenViBE as a platform for a p300 speller’ (Heilbronn University, 2012).
    17. 17)
      • 27. Hassanat, A.B., Abbadi, M.A., Alhasanat, A.A.: ‘Solving the problem of the K parameter in the KNN classifier using an ensemble learning approach’, Int. J. Comput. Sci. Inf. Secur., 2014, 12, (8), pp. 3339.
    18. 18)
      • 2. Cauwenberghs, G., Poggio, T.: ‘Incremental and decremental support vector machine learning’, Adv. Neural Inf. Process. Syst., 2001, 13, pp. 409415.
    19. 19)
      • 11. Olesen, H., Klonovs, J., Petersen, C.K.: ‘Development of a mobile EEG-based feature extraction and classification system for biometric authentication’ (Aalborg University, Copenhagen, 2012).
    20. 20)
      • 13. Geng, X., Smith-Miles, K.: ‘Incremental learning’, in Encycl. Biometrics, Springer US Publishers, 2015, pp. 912917.
    21. 21)
      • 4. Hema, C.R., Paulraj, M.P., Kaur, H.: ‘Brain signatures: a modality for biometric authentication’. 2008 Int. Conf. Electronic Design, 2008, pp. 14.
    22. 22)
      • 19. Brainard, D.H.: ‘The psychophysics toolbox’, Spatial Vis., 1997, 10, pp. 433436.
    23. 23)
      • 15. Yang, S.: ‘The use of EEG signals for biometric person recognition’, 2015.
    24. 24)
      • 6. Palaniappan, R., Ravi, K.V.R.: ‘Improving visual evoked potential feature classification for person recognition using PCA and normalization’, Pattern Recognit. Lett., 2006, 27, pp. 726733.
    25. 25)
      • 9. Liew, S.H., Choo, Y.H., Low, Y.F.: ‘Identifying visual evoked potential (VEP) electrodes setting for person authentication’, Int. J. Adv. Soft Comput. Appl., 2015, 7, (3), pp. 8599.
    26. 26)
      • 26. Witten, I.H., Frank, E.: ‘WEKA Machine learning algorithms in java’, in Data Mining: Prac. Mach. Learn. Tools and Tech. with Java Imple., Morgan Kaufmann Publishers, 2000, pp. 265320.
    27. 27)
      • 5. He, C.: ‘Person authentication using EEG brainwave Signals’ (The University of British Columbia, 2007).
    28. 28)
      • 7. Zuquete, A., Quintela, B., Silva Cunha, J.P.: ‘Biometric authentication using brain responses to visual stimuli’. Int. Conf. Bio-inspired Systems and Signal Processing, 2010, pp. 103112.
    29. 29)
      • 1. Albert, M. K.: ‘Instance-based learning algorithms’, Mach. Learn., 1991, 6, (1), pp. 3766.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2017.0044
Loading

Related content

content/journals/10.1049/iet-bmt.2017.0044
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading