Smartphone Sensors for Modeling Human-Computer Interaction: General Outlook and Research Datasets for User Authentication

In this paper we list the sensors commonly available in modern smartphones\nand provide a general outlook of the different ways these sensors can be used\nfor modeling the interaction between human and smartphones. We then provide a\ntaxonomy of applications that can exploit the signals originated by these\nsensors in three different dimensions, depending on the main information\ncontent embedded in the signals exploited in the application: neuromotor\nskills, cognitive functions, and behaviors/routines. We then summarize a\nrepresentative selection of existing research datasets in this area, with\nspecial focus on applications related to user authentication, including key\nfeatures and a selection of the main research results obtained on them so far.\nThen, we perform the experimental work using the HuMIdb database (Human Mobile\nInteraction database), a novel multimodal mobile database that includes 14\nmobile sensors captured from 600 participants. We evaluate a biometric\nauthentication system based on simple linear touch gestures using a Siamese\nNeural Network architecture. Very promising results are achieved with\naccuracies up to 87% for person authentication based on a simple and fast touch\ngesture.\n