(44-5) 18 * << * >> * Russian * English * Content * All Issues

An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics
A.E. Sulavko 1

1 Omsk State Technical University, Mira, h. 11 Omsk, Russian Federation, 644050

 PDF, 1393 kB

DOI: 10.18287/2412-6179-CO-717

Pages: 830-842.

Full text of article: Russian language.

Abstract:
An abstract model of an artificial immune network (AIS) based on a classifier committee and robust learning algorithms (with and without a teacher) for classification problems, which are characterized by small volumes and low representativeness of training samples, are proposed. Evaluation of the effectiveness of the model and algorithms is carried out by the example of the authentication task using keyboard handwriting using 3 databases of biometric metrics. The AIS developed possesses emergence, memory, double plasticity, and stability of learning. Experiments have shown that AIS gives a smaller or comparable percentage of errors with a much smaller training sample than neural networks with certain architectures.

Keywords:
biometric authentication, bagging, boosting, feature subspaces, machine learning on small samples, ensembles of models.

Citation:
Sulavko AE. An abstract model of an artificial immune network based on a classifiers committee for biometric pattern recognition by the example of keystroke dynamics. Computer Optics 2020; 44(5): 830-842. DOI: 10.18287/2412-6179-CO-717.

Acknowledgements:
The work was financially supported by the Russian Foundation for Basic Research under RFBR research project No. 18-37-00399.

References:
  1. Ivanov AI, Lozhnikov PS, Sulavko AE. Evaluation of signature verification reliability based on artificial neural networks, Bayesian multivariate functional and quadratic forms, Computer Optics 2017; 41(5): 765-774. DOI: 10.18287/2412-6179-2017-41-5-765-774.
  2. Timmis J. Challenges for artificial immune systems. In Book: Neural Nets. WIRN 2005, NAIS 2005. Berlin, Heidelberg: Springer, 2005: 335-367. DOI: 10.1007/11731177_42.
  3. Mishra PK, Bhusry M. Artificial immune system: State of the art approach. Int J Comput Appl 2015; 120(20): 25-32. DOI: 10.5120/21344-4357.
  4. Sulavko AE, Shalina EV, Stadnikova DG, Choban AG. Immune algorithms for pattern recognition and their application in biometric systems (Review) [In Russian]. Information Security Issues 2019; 1: 38-46.
  5. Corus D, Oliveto PS, Yazdani D. Fast artificial immune systems. In Book: Auger A, Fonseca C, Lourenço N, Machado P, Paquete L, Whitley D, eds. Parallel Problem Solving from Nature – PPSN XV. PPSN 2018. Cham: Springer, 2018: 67-78. DOI: 10.1007/978-3-319-99259-4_6.
  6. Zhang C, Ma Y. Ensemble machine learning. Methods and applications, Boston, MA: Springer; 2012.
  7. Sulavko AE. Computer user's recognition based on keyboard handwriting dynamics with using of additional features from special sensors [In Russian]. Sensors and Systems 2017; 11: 19-30.
  8. Kobojek P, Saeed K. Application of recurrent neural networks for user verification based on keystroke dynamics. J Telecommun Inf Technol 2016; 3: 80-90.
  9. Hellström E. Feature learning with deep neural networks for keystroke biometrics: A study of supervised pre-training and autoencoders. Computer Science and Engineering, master's level. Luleå: Luleå University of Technology; 2018.
  10. Killourhy KS, Maxion RA. Comparing anomaly detectors for keystroke dynamics, Proc 39th Annual Int Conf on Dependable Systems and Networks 2009; 125-134.
  11. Mulionoa Y, Hamb H, Darmawan D. Keystroke dynamic classification using machine learning for password authorization. Procedia Comput Sci 2018; 135: 564-569.
  12. Antal M, Szabó LZ, Laszlo I. Keystroke dynamics on Android platform. Proc 8th Int Conf Interdisciplinarity in Engineering 2014; 820-826.
  13. Sulavko AE. Highly reliable two-factor biometric authentication based on handwritten and voice passwords using flexible neural networks. Computer Optics 2020; 44(1): 82-91. DOI: 10.18287/2412-6179-CO-567.
  14. Sulavko AE, Volkov DA, Zhumazhanova SS, Borisov RV. Subjects authentication based on secret biometric patterns using wavelet analysis and flexible neural networks. XIV International Scientific-Technical Conference on Actual Problems of Electronics Instrument Engineering (APEIE) 2018; 218-227. DOI: 10.1109/APEIE.2018.8545676.
  15. Ivanov AI, Kuprianov EN, Tureev SV. Neural network integration of classical statistical tests for processing small samples of biometrics data [In Russian]. Dependability 2019; 19(2): 22-27. DOI: 10.21683/1729-2646-2019-19-2-22-27.
  16. Sulavko AE. Testing of neurons based on statistical functionals for verifying biometric images in feature space with different informativeness [In Russian]. Applied Informatics 2018; 1: 128-143.
  17. Protasov V, Potapova Z, Melnikov E. A method for evolutionary decision reconciliation, and expert theorems. 3rd Int Conf on Intelligent Systems and Applications (INTELLI 2014) 2014: 43-47.
  18. Sulavko AE, Shalina EV. Biometric authentication of users of information systems by keyboard handwriting based on immune network algorithms [In Russian]. Applied Informatics 2018; 3(81): 128-143.
  19. Ivanov AI, Lozhnikov PS, Serikova YI. Reducing the size of a sample sufficient for learning due to the symmetrization of correlation relationships between biometric data. Cybern Syst Anal 2016; 52(3): 379-385. DOI: 10.1007/s10559-016-9838-x.
  20. Schapire RE, Freund Y, Bartlett P, Lee WS. Boosting the margin: A new explanation for the effectiveness of voting methods. Ann Stat 1998; 26(5): 1651-1686.
  21. Bersini H, Varela F. The immune learning mechanisms: Recruitment reinforcement and their applications. In Book: Patton R, ed. Computing with biological metaphors. L.: Chapman and Hall, 1994. ISBN: 978-0-412-54470-5.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20