Upload
henry-levine
View
17
Download
0
Embed Size (px)
DESCRIPTION
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 - PowerPoint PPT Presentation
Citation preview
Biometric Data MiningBiometric Data Mining
“A Data Mining Study of Mouse Movement, Stylometry, and Keystroke Biometric Data”
Clara Eusebi, Cosmin Gilga, Deepa John, Andre Maisonave.
Presentation SummaryPresentation Summary
Project DescriptionExperiment StructureAlgorithms and TechniquesResults of ExperimentsFuture ResearchConclusions
Project DescriptionProject 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 ExperimentsStudy ExperimentsAuthentication
◦Dichotomy model
Identification◦Normalized data
Additional◦Normalized data
Algorithms and Algorithms and TechniquesTechniquesAuthentication
◦IBk with k = 1 on Dichotomy dataIdentification
◦IBk with k = 1 on Normalized dataAdditional
◦PredictiveApriori◦simpleKmeans◦IBk with k = 1 using leave-one-out
and percentage splits
ResultsResultsTrain Test Type Accuracy
1(5 samples
from each of 4 subjects)
2(5 samples
from each of 4 subjects)
Copy Desktop 95.79%
Free Desktop 96.32%
Copy Laptop 91.58%
Free Laptop 92.11%
1(5 samples
from each of 4 subjects)
3(5 samples
from each of 4 subjects)
Copy Desktop 88.95%
Free Desktop 98.42%
Copy Laptop 100.00%
Free Laptop 93.68%
Results of Longitudinal Authentication Experiments on new Keystroke Capture Data
ResultsResultsTrain Test Type Accuracy
1(5 samples
from each of 4 subjects)
2(5 samples
from each of 4 subjects)
Copy Desktop 95%
Free Desktop 100%
Copy Laptop 100%
Free Laptop 85%
1(5 samples
from each of 4 subjects)
3(5 samples
from each of 4 subjects)
Copy Desktop 80%
Free Desktop 100%
Copy Laptop 100%
Free Laptop 100%
Results of Longitudinal Identification Experiments on the new KeystrokeCapture Data.
Opportunities for Opportunities for ResearchResearchAuthentication 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.
ConclusionConclusionThe 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.