A Fall Detection Method Based on Multi-Threshold Value and EML Learning Machine.

Autor: Jia Yang, Tongyue Gao, Kaida Huang
Předmět:
Zdroj: AIP Conference Proceedings; 2019, Vol. 2073 Issue 1, p020051-1-020051-9, 9p
Abstrakt: In recent years, fall injuries have not only caused serious harm to the health of the elderly in China, but also occupied a large amount of social medical resources. The most important reason for the fall injury is the rescue not timely after the fall. In view of this phenomenon, this paper realizes the fusion of multi-threshold detection algorithm and EML learning machine classification algorithm, and proposes a two-layer fall detection algorithm based on weight discrimination. Experiments show that the algorithm has high accuracy of fall alarm detection and low false alarm rate [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index