A Novel Personal Health Assessment Based on Mobile Telecom Data

This paper focuses on the mobile telecom data to assess personal health. By stepping up data-mining efforts, fascinatedly we can see the inner relationships between the telecom data and personal health. In this paper, we also introduce a new learning framework called Extreme Learning Machine (ELM), the ELM utilizes mobile telecom data features to distinguish the health states. The superiority of this algorithm lies in the random choices of hidden nodes and the fact that it determines the output weights analytically, which results in lower complexity. In theory, this algorithm tends to provide good generalization performance at extremely fast learning speed. The simulation results demonstrate that the ELM can classify features extracted from the mobile telecom data successfully.