No abstract

No abstract

No abstract

Abstract:Computer users have motionless periods of time while performing computer-based tasks. Do these pauses relate to the mental and perceptual actions required to perform tasks? Do users essentially pause while they think, wait to retrieve the next step to perform, or search the location of something on the screen? How do the pauses change as the users gain experience and progress from novice to skilled? To answer these questions, we conducted user studies to investigate the link between the pauses observed in users' interactions with computer-based applications and their skill levels. In this paper, we introduce a set of pause-related attributes that can distinguish among different levels of skills in performing Graphical User Interface (GUI) tasks. We employ machine learning algorithms to build skill classifi ers based on these attributes. These skill classifi ers can be used to create skill-adaptive applications.

ECG (Electrocardiogram) data analysis is one of the most widely used and important tools in cardiology diagnostics. In recent years the development of advanced deep learning techniques and GPU hardware have made it possible to train neural network models that attain exceptionally high levels of accuracy in complex tasks such as heart disease diagnoses and treatments. We investigate the use of ECGs as biometrics in human identification systems by implementing state-of-the-art deep learning models. We train convolutional neural network models on approximately 81k patients from the US, Germany and China. Currently, this is the largest research project on ECG identification. Our models achieved an overall accuracy of 95.69%. Furthermore, we assessed the accuracy of our ECG identification model for distinct groups of patients with particular heart conditions and combinations of such conditions. For example, we observed that the identification accuracy was the highest (99.7%) for patients with both ST changes and supraventricular tachycardia. We also found that the identification rate was the lowest for patients diagnosed with both atrial fibrillation and complete right bundle branch block (49%). We discuss the implications of these findings regarding the reidentification risks of patients based on ECG data and how seemingly anonymized ECG datasets can cause privacy concerns for the patients.