Method of neural network analysis of keystroke dynamics.

  • L. Tereikovska Kyiv National University of Civil Engineering and Architecture
Keywords: emotion recognition, authentication, keystroke dynamics, convolutional neural network, input parameter, recognition method.


The article is devoted to the issues of improving the means of recognizing the emotions and personalities of users of information management systems. The possibility of introducing modern neural network solutions based on convolutional neural networks into the recognition tools has been substantiated. A method of neural network analysis of keyboard handwriting has been developed, which, due to the proposed adaptation principles and the procedure for coding keyboard handwriting parameters, allows the convolutional neural network, the architecture of which is adapted to the expected conditions of use, to be incorporated into recognition tools. Experimental studies have shown that the use of the developed method makes it possible to ensure error recognition of the user's emotions and personality at the level of the best modern recognition systems.


S. J. Alghamdi and L. A. Elrefaei. Dynamic user verification using touch keystroke based on medians vector proximity. In Computational Intelligence, Communication Systems and Networks (CICSyN), 2015 7th International Conference on, pages 121–126. IEEE, 2015.

Berik Akhmetov, Igor Tereykovsky, Aliya Doszhanova, Lyudmila Tereykovskaya (2018) Determination of input parameters of the neural network model, intended for phoneme recognition of a voice signal in the systems of distance learning. International Journal of Electronics and Telecommunications. Vol 64, No 4 (2018), 425-432. DOI: 10.24425/123541.

C. Bo, L. Zhang, T. Jung, J. Han, X.-Y. Li, and Y. Wang. Continuous user identification via touch and movement behavioral biometrics. In 2014 IEEE 33rd International Performance Computing and Communications Conference (IPCCC), pages 1–8. IEEE, 2014.

Yunbin Deng and Yu Zhong Keystroke Dynamics Advances for Mobile Devices Using Deep Neural Network GCSR Vol. 2, pp. 59-70, 2015 DOI: 10.15579/gcsr.vol2.ch4.

Liu, M., Guan, J. User keystroke authentication based on convolutional neural network, Communications in Computer and Information Science 2019, 971, pp. 157-168.

Lin, C.-H., Liu, J.-C., Lee, K.-Y. On neural networks for biometric authentication based on keystroke dynamics. Sensors and Materials, 2018, 30(3), pp. 385-396.

Saket Maheshwary, Soumyajit Ganguly, Vikram Pudi, Deep Secure: A Fast and Simple Neural Network based approach for User Authentication and Identification via Keystroke Dynamics Conference: IWAISe, International Joint Conference on Artificial Intelligence (IJCAI) - 2017At: Melbourne, Australia pp. 34-40.

Tereykovska L., Tereykovskiy I., Aytkhozhaeva E., Tynymbayev S., Imanbayev A. Encoding of neural network model exit signal, that is devoted for distinction of graphical images in biometric authenticate systems (2017). // News of the national academy of sciences of the republic of kazakhstan series of geology and technical sciences. Volume 6, Number 426 (2017), 217 – 224.

Xiaofeng, L., Shengfei, Z., Shengwei, Y. Continuous authentication by free-text keystroke based on CNN plus RNN Procedia Computer Science 147, 2019, pp. 314-318.

Abstract views: 19
PDF Downloads: 8
How to Cite
Tereikovska, L. (2019). Method of neural network analysis of keystroke dynamics . COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (37), 53-59.
Computer science and computer engineering