After verifying the correctness of the password, the keystroke dynamics‐based authentication (KDA) system will verify the corresponding keystroke features. It provides additional security verification for alphanumeric‐based and personal identification number‐based authentication schemes that suffer from guessing and shoulder surfing attacks. Except for the original time features in the KDA schemes, two novel keystroke features are found in touch screen handheld mobile devices, which are called “pressure” features and “size” features. A computation efficient statistical classifier is built for low‐power mobile devices to authenticate the user's identity. This paper analyzes the following combinations of features: (1) time features; (2) time features and pressure features; (3) time features and size features; and (4) all features combined. The result shows that the size features or the pressure features can effectively promote the utility of the KDA system in personal identification number‐based authentication schemes for touch screen handled mobile devices. The combination of time features and pressure features is the best one for authenticating users. Copyright © 2013 John Wiley & Sons, Ltd.

No abstract

Recent studies in scientific paper summarization have explored a new form of structured summary for a reference paper by grouping all cited and citing sentences together by facet. This involves three main tasks: (1) identifying cited text spans for citances (i.e., citing sentences), (2) classifying their discourse facets, and (3) generating a structured summary from the cited text spans and citances. This paper focuses on the first task, and approaches the task as binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. We propose a new method that integrates feature selection and classification techniques to enhance classification performance. The proposed method investigates combinations of six feature selection methods (χ2-Statistics, Information Gain, Gain Ratio, Relief-F, Significance Attribute Evaluation, and Symmetrical Uncertainty), and five classification algorithms (k-Nearest Neighbors, Decision Tree, Support Vector Machine, Naïve Bayes, and Random Forest). Additionally, to address imbalanced data during training, we apply SMOTE (Synthetic Minority Over-sampling Technique) to introduce synthetic biases towards the minority. Experiments are conducted using the CL-SciSumm corpora to compare the effect of feature selection applied to classification. The results reveal the benefits of feature selection in significantly boosting performance of F1 score metric, and show that our method is competitive to the state-of-the-art methods in the CL-SciSumm evaluations.