Advertisement

A Method of Feature Vector Modification in Keystroke Dynamics

  • Miroslaw OmieljanowiczEmail author
  • Mateusz Popławski
  • Andrzej Omieljanowicz
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 889)

Abstract

The aim of this paper is to conduct research which will investigate the impact of diverse features in vector on the identification and verification results. The selection of the features was based on the knowledge gained from scientific articles publish recently. One of the main goals of this paper is to probe the impact factor of weights in feature vector which will later serve in biometric authentication system based on keystroke dynamics. The unique application allows end-user to customize the vector parameters, such as: type of the feature and weight of the feature, additionally finding optimization for each custom feature vector.

Keywords

Biometrics Keystroke dynamics Feature extraction Human recognition Security 

Notes

Acknowledgements

The research has been done in the framework of the grant S/WI/3/2018 Bialystok University of Technology.

References

  1. 1.
    Ríha, Z., Matyáš, V.: Biometric Authentication Systems, Faculty of Informatics Masaryk University (2000)Google Scholar
  2. 2.
    Liakat, A. Md., Monaco, J.V., Tappert, C.C., Qiul, M.: Keystroke Biometric Systems for User Authentication. Springer Science Business Media, New York (2016)Google Scholar
  3. 3.
    Wankhede, S.B., Verma, S.: Keystroke dynamics authentication system using neural network. Int. J. Innovative Res. Dev. 3(1), 157–164 (2014)Google Scholar
  4. 4.
    Bours, P., Masoudian, E: Applying keystroke dynamics on one-time pincodes. In: International Workshop on Biometrics and Forensics (IWBF) (2014)Google Scholar
  5. 5.
    Szymkowski, M., Saeed, K.: A multimodal face and fingerprint recognition bio-metrics system. In: Lecture Notes in Computer Science, vol. 10244, pp. 131–140 (2017)Google Scholar
  6. 6.
    Panasiuk, P., Saeed, K.: Influence of database quality on the results of keystroke dynamics algorithms. In: Chaki, N., Cortesi, A. (eds.) Computer Information Systems – Analysis and Technologies. Communications in Computer and Information Science, vol. 245. Springer, Berlin, Heidelberg (2011)Google Scholar
  7. 7.
    Hayreddin, Ç., Upadhyaya, S.: Adaptive techniques for intra-user variability in keystroke dynamics. In: IEEE 8th International Conference Biometrics Theory. Applications and Systems (BTAS) (2016)Google Scholar
  8. 8.
    Patil, R.A., Renke, A.L.: Keystroke Dynamics for User Authentication and Identification by using Typing Rhythm. International Journal of Computer Applications (0975 – 8887), vol. 144 – No. 9, June 2016Google Scholar
  9. 9.
    Payam, R.Z., Lei, T., Huan, L.: Cross-Validation. In: Encyclopedia of Database Systems, pp. 532–538. Arizona State University, Springer, USA (2009)Google Scholar
  10. 10.
    Zack, R.S., Tappert, C.C., Cha, S.-H.: Performance of a long-text- input keystroke biometric authentication system using an improved k-nearest-neighbor classification method. In: Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems, pp. 1–6 (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Miroslaw Omieljanowicz
    • 1
    Email author
  • Mateusz Popławski
    • 2
  • Andrzej Omieljanowicz
    • 3
  1. 1.Faculty of Computer ScienceBialystok University of TechnologyBialystokPoland
  2. 2.BialystokPoland
  3. 3.Faculty of Mechanical EngineeringBialystok University of TechnologyBialystokPoland

Personalised recommendations