Touch Analysis: An Empirical Evaluation of Machine Learning Classification Algorithms on Touch Data

Our research aims at classifying individuals based on their unique interactions on the touchscreen-based smartphones. In this research, we use ‘TouchAnalytics’ dataset, which include 41 subjects and 30 different behavioral features. Furthermore, we derived new features from the raw data to improve the overall authentication performance. Previous research has already been done on the TouchAnalytics dataset with the state-of-the-art classifiers, including Support Vector Machine (SVM) and k-nearest neighbor (kNN) and achieved equal error rates (EERs) between 0% to 4%. In this paper, we propose a Deep Neural Net (DNN) architecture to classify the individuals correctly. When we combine the new features with the existing ones, SVM and k-NN achieved the classification accuracies of 94.7% and 94.6%, respectively. This research explored seven other classifiers and out of them, decision tree and our proposed DNN classifiers resulted in the highest accuracies with 100%. The others included: Logistic Regression (LR), Linear Discriminant Analysis (LDA), Gaussian Naive Bayes (NB), Neural Network, and VGGNet with the accuracy scores of 94.7%, 95.9%, 31.9%, 88.8%, and 96.1%, respectively.