Wearable sensors network for activity recognition using inertial sensors

Abstract—The aim of this paper is to present the implementation of an activity recognition system based on a data acquisition system with inertial sensors. One of the requirement of data acquisition systems used in human activity recognition is their level of acceptability or their level of obstruction [2, 4]. Starting from this important requirement, we designed a few wearable data acquisition systems using inertial sensors. The idea from which we started, takes into account the need to obtain more complete information about the studied human subject, in complex activities recognition systems. In our experiment we used inertial sensor built into so called “9DOF inertial module”. Our systems contain, on the wearable side, a maximum of three inertial sensors, a microcontroller module, and a communication module which can be one of the three solutions. For data reception, on the fixed part of the system, we have a communication module corresponding to the one on wearable parts and a microcontroller module connected to a PC through a serial port. For activity recognition, data files are transferred to a PC, and data is processed in Matlab using artificial neural networks as classifier. The networks have been configured according to the number of sensors that acquired data and the number of activities that we want to recognize