Biometric Data Mining A Data Mining Study of
Biometric Data Mining “A Data Mining Study of Mouse Movement, Stylometry, and Keystroke Biometric Data” Clara Eusebi, Cosmin Gilga, Deepa John, Andre Maisonave.
Presentation Summary Project Description Experiment Structure Algorithms and Techniques Results of Experiments Future Research Conclusions
Project Description The study extends previous studies at Pace University on Biometric data by running previously obtained data sets through a data mining tool called Weka, using various algorithms and techniques.
Study Experiments Authentication ◦ Dichotomy model Identification ◦ Normalized data Additional ◦ Normalized data
Algorithms and Techniques Authentication ◦ IBk with k = 1 on Dichotomy data Identification ◦ IBk with k = 1 on Normalized data Additional ◦ Predictive. Apriori ◦ simple. Kmeans ◦ IBk with k = 1 using leave-one-out and percentage splits
Results Train Test 1 (5 samples from each of 4 subjects) 2 Copy Desktop (5 samples from Free Desktop each of 4 Copy Laptop subjects) Free Laptop 95. 79% 3 Copy Desktop (5 samples from Free Desktop each of 4 Copy Laptop subjects) Free Laptop 88. 95% 1 (5 samples from each of 4 subjects) Type Accuracy 96. 32% 91. 58% 92. 11% 98. 42% 100. 00% 93. 68% Results of Longitudinal Authentication Experiments on new Keystroke Capture Data
Results Train Test 1 (5 samples from each of 4 subjects) 2 Copy Desktop (5 samples from Free Desktop each of 4 Copy Laptop subjects) Free Laptop 1 (5 samples from each of 4 subjects) Type 3 Copy Desktop (5 samples from Free Desktop each of 4 Copy Laptop subjects) Free Laptop Accuracy 95% 100% 85% 80% 100% Results of Longitudinal Identification Experiments on the new Keystroke Capture Data.
Opportunities for Research Authentication based solely on subject in question. Separate sets of data holding only within and between class records for each subject, Rather than comparing a community of subjects to a community of records. Higher accuracies could be legitimately obtained in this manner.
Conclusion The study has furthered previous studies at Pace University through running experiments on Mouse Movement, Stylometry, and Keystroke Biometric data, new and previously obtained, using the data mining tool Weka. The data mining algorithms with which the experiments were conducted are widely used and provide an entry point for future researchers into the use of data mining with biometric data sets.
- Slides: 9