The Impact of Personalization on Smartphone-Based Activity Recognition
Smartphones incorporate many diverse and powerful sensors, which creates exciting new opportunities for data mining and human-computer interaction. In this paper, the authors show how standard classification algorithms can use labeled smartphone-based accelerometer data to identify the physical activity a user is performing. Their main focus is on evaluating the relative performance of impersonal and personal activity recognition models. Their impersonal (i.e., universal) models are built using training data from a panel of users and are then applied to new users, while their personal models are built with data from each user and then applied only to new data from that user.