A Novel Biometric Authentication System using Keystroke Dynamics and Optimized Multilayer Perceptron Neural Network
Priya C. V1, K. S. Angel Viji2
1Priya C. V, Department of Computer Science and Engineering, Noorul Islam Centre for Higher Education, Kumaracoil (Tamil Nadu), India.
2K.S. Angel Viji, Department of Computer Science and Engineering, College of Engineering, Kidangoor, Kottayam (Kerala), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 57-64 | Volume-8 Issue-6, April 2019 | Retrieval Number: E3320038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Keystroke dynamics is a peculiar and typical case of biometrics that can be employed to verify the user’s individuality. This paper proposes a novel biometric authentication system based on the keystroke dynamics, multilayer perceptron neural network and most valuable player algorithm. The major challenge in machine learning of artificial neural networks is the network training. Due to the nonlinear behavior of the neural network and unknown set of network parameters such as weights and biases, it is more difficult to train the neural network. The most valuable player algorithm is a better alternative to overcome the disadvantages such as local optimum minimum solution and slower convergence speed of the conventional training algorithms. Rapid convergence, proficiency, practicality, and safety are the benefits of the most valuable player algorithm. Hence in this paper, the most valuable player algorithm is proposed to train the multilayer perceptron neural network to overcome the drawbacks in the conventional training process. The proposed biometric authentication system is developed and validated using MATLAB software on different users. The experimental results depict that the proposed method has an authentication accuracy of 99.5917%, which is considered more suitable and efficient for real-time implementation.
Keyword: Authentication, Biometrics, Keystroke Dynamics, Most Valuable Player Algorithm, Neural Network.
Scope of the Article: Neural Information Processing