Child Detection by Utilizing Touchscreen Behavioral Biometrics on Mobile

Abstract

Studies show that young children are exposed to smart devices. Early stages of education, children’s internet safety, and children’s interactions with computers are all significantly impacted by mobile usage. With the significant increase in average daily smartphone use, preschoolers’, school-going children’s, and teenagers’ health is ruptured both mentally and physically. This research presents an extensive point of reference for investigating the operation of artificial neural networks and several machine learning algorithms in postulating the classification problem regarding the age of a smartphone user based on their touch. Hence, our work will become a reliable component to forecast the age range and effectively help parents control the time spent on smartphones by their children. Out of a variety of models that were examined, we propose the top five for simulating the behavioral differences between children and adults when using mobile devices. The first approach is based on using artificial neural networks for classification. Next, we used gradient boosting algorithms like XgBoost classifier and LightGBM classifier. Finally, we also analyzed support vector machines and K-nearest neighbors model.