Fall detection algorithm based on the feature of body′s acceleration
Gao Xiaojua · Xi'an Gongcheng Keji Xueyuan xuebao · 2015
The real-time fall detection system can provide help in time for old people and patient.A fall detection algorithm based on a single triaxial accelerometer mesurement is introduced.The feature of the sensor data about body′s action is analyzed,the feature vector is constructed,and the threshold value is obtained by machine leaning method.In detection process,if the feature vector of the accelerometer measurement is bigger than the threshold value,maybe fall happened,then the acceleration in every direction should be analyzed to determine whether a fall is happening.The experimental results show that the algorithm is valid.