Triaxial MEMS Accelerometer for Activity Monitoring of Elderly Person

Activity classification system was developed using MEMS accelerometer and wireless sensor node to be operated in wireless sensor network environment. Three axes MEMS accelerometer measures body's acceleration and transmits measured data with a help of sensor node to base station attached to PC. On the PC, real time accelerometer data is processed for various classifications. Rest-Fall, Running-Fall and Walking-Running classification pairs are considered among the various Activities of Daily Living (ADL). To improve the discrimination ability of the detection algorithm between walking and running, frequency component of activity by FFT calculation is combined with normal monitoring algorithm which uses RMS threshold value and Z axis angle threshold value. The experimental results show an overall accuracy of 82.5%.