Exploring multi-view learning for activity inferences on smartphones

Inferring activities on smartphones is a challenging task. Prior works have elaborated on using sensory data from built-in hardware sensors in smartphones or taking advantage of location information to understand human activities. In this paper, we explore two types of data on smartphones to conduct activity inference: 1) Spatial-Temporal: reflecting daily routines from the combination of spatial and temporal patterns, 2) Application: perceiving specialized apps that assist the user's activities. We employ multi-view learning model to accommodate both types of data and use weighted linear kernel model to aggregate the views. Note that since resources of smartphones are limited, activity inference on smartphones should consider the constraints of resources, such as the storage, energy consumption, and computation power. Finally, we compare our proposed method with several classification methods on a real dataset to evaluate the effectiveness and performance of our method. The experimental results show that our approach outperforms other methods regarding the balance between accuracy, running time, and storage efficiency.