The Fall Detection Method Based on the Wireless Acceleration Sensor

Abstract

To judge whether the alone elderly fall or not is an important need in the elderly health supervision. This paper puts forward a method based on three axis acceleration data and pattern recognition has been presented to judge the situation of falling for old men. The method was based on an acceleration transducer named MMA7260Q. Due to the characteristic that the three-axis signal divers in a huge area during the progress of old men falling, it combined the peak value of acceleration and acceleration energy curve to proceed three axis acceleration data for detecting the falling, it could avoid outputting errors due to the changing of angle of old men. According to the result of the experiment, the accuracy rate of the method of detection proposed in the report could run up to 93 percent.

Intelligent Monitoring System for the Elderly based on Posture Recognition

“…With the development of computer vision, sensor technology, remote communication technology, the use of intelligent technology to realize the function of elderly guardianship has become a hot spot. Chen Xiang [2] proposed a study on fall detection based on acceleration sensors, which utilizes a three-axis acceleration sensor to collect velocity data and detects whether an elderly person falls by determining whether the velocity exceeds an advance threshold. Xin Hu [3] et al studied an OpenPose-based fall detection algorithm for the elderly, and based on the OpenPose human skeleton information recognition network, they proposed to replace some of its convolutional layers with depth-separable convolutional neural network types.…”