Volume 24, Issue 1, June 2016, Pages 202–209
S. Suganya1, G. Muthumari2, and C. Balasubramanian3
1 Department of Computer Science and Engineering, P.S.R.Renasamy College of Engineering for women, Sivakasi, Tamilnadu, India
2 Department of Computer Science and Engineering, P.S.R.Renasamy College of Engineering for women, Sivakasi, Tamilnadu, India
3 Prof. and head of Department of Computer Science and Engineering, P.S.R.Renasamy College of Engineering for women, Sivakasi, Tamilnadu, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
To diminish the behavioral variability of mouse dynamics, the machine learning algorithm was proposed. Mouse dynamics is the process of identifying the user based on their mouse operating behavior. The dataset includes co-ordinates values, time stamp value and mouse operation. From this dataset, the schematic features, holistic features and motor-skill features like average speed, average distance, mean, standard deviation and mouse silence ratio, velocity, slope angle, curvature were extracted to obtain feature vector. The obtained feature vector can be applied to the dimensionality reduction based approach, diffusion map to reduce the dimension of the feature vector that compared with ISOMAP (Isometric Feature Mapping). Without dimensionality reduction based method the classification process was difficult. The machine learning algorithm i.e.) hop field network to be used to identify whether the given input sample was authenticated user (or) unauthenticated.
Author Keywords: behavioral variability, mouse dynamics, feature vector, dimensionality reduction, diffusion map, hop field network.
S. Suganya1, G. Muthumari2, and C. Balasubramanian3
1 Department of Computer Science and Engineering, P.S.R.Renasamy College of Engineering for women, Sivakasi, Tamilnadu, India
2 Department of Computer Science and Engineering, P.S.R.Renasamy College of Engineering for women, Sivakasi, Tamilnadu, India
3 Prof. and head of Department of Computer Science and Engineering, P.S.R.Renasamy College of Engineering for women, Sivakasi, Tamilnadu, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
To diminish the behavioral variability of mouse dynamics, the machine learning algorithm was proposed. Mouse dynamics is the process of identifying the user based on their mouse operating behavior. The dataset includes co-ordinates values, time stamp value and mouse operation. From this dataset, the schematic features, holistic features and motor-skill features like average speed, average distance, mean, standard deviation and mouse silence ratio, velocity, slope angle, curvature were extracted to obtain feature vector. The obtained feature vector can be applied to the dimensionality reduction based approach, diffusion map to reduce the dimension of the feature vector that compared with ISOMAP (Isometric Feature Mapping). Without dimensionality reduction based method the classification process was difficult. The machine learning algorithm i.e.) hop field network to be used to identify whether the given input sample was authenticated user (or) unauthenticated.
Author Keywords: behavioral variability, mouse dynamics, feature vector, dimensionality reduction, diffusion map, hop field network.
How to Cite this Article
S. Suganya, G. Muthumari, and C. Balasubramanian, “Improving the Performance of Mouse Dynamics Based Authentication Using Machine Learning Algorithm,” International Journal of Innovation and Scientific Research, vol. 24, no. 1, pp. 202–209, June 2016.
