Energy Consumption and Efficiency Issues in Human Activity Monitoring System

As people get interested in health issues, different types of human activity trackers or monitoring systems are emerging these days. Therefore, many researchers have been interested in this issue and have proposed various monitoring systems based on accelerometer sensors. However, few systems focus on energy consumption of sensor devices. In this paper, we focus on an application-level solution for saving energy consumption of a human daily activity monitoring system using a wireless wearable sensor. We propose an on-board data processing mechanism for monitoring daily activity in humans. This technique focuses on reducing the size of processed data and transmission rate to save the energy of the sensors. In addition, we develop an activity classification algorithm based on both an inclination angle and a standard deviation value. The proposed system is capable of monitoring most daily activities of the human body: standing, sitting, walking, lying, running, and so on. Furthermore, one of our key contributions is that all functionalities including data processing, activity classification, wireless communication, and storing classified activities were achieved in a single sensor node without compromising the accuracy of activity classification. Our experimental results show that the accuracy of our classification system is over 95 %.