Remote fall detection method and system based on GA (genetic algorithm) and PNN (probabilistic neural network)

Abstract

The invention relates to a remote fall detection method based on a GA (genetic algorithm) and a PNN (probabilistic neural network). The method comprises the following steps: (1) acquisition of body information of old people: tri-axial acceleration and attitude angles of the old people are acquired, eigenvalues are calculated, and an eigenvector is formed; (2) classified detection: the PNN is constructed and optimized with the GA, and fall behaviors and fall-like behaviors of the old people are detected in a classified manner with the optimized PNN according to the eigenvector obtained in the step (1); (3) remote monitoring: the fall information, monitored in the step (2), of the old people is uploaded to a server and transmitted to a remote monitoring terminal by the server for monitoring.

Description

technical field [0001] The invention belongs to the technical field of medical health monitoring, and in particular relates to a remote fall detection method and system based on a genetic algorithm and a probabilistic neural network. Background technique [0002] At present, the aging phenomenon of the global population is becoming more and more serious. It is estimated that by 2050, my country will become one of the countries with the most aging population, which will bring many challenges to the development of our society, especially the health protection of the elderly has attracted much attention. Therefore, the health care of the elderly has become an urgent problem that the society needs to solve. Traditional elderly care requires nursing staff to monitor their physical health in real time, which consumes a lot of manpower and material resources, and the cost is relatively high. [0003] With the development of electronic technology, electronic information technology...

AI Technical Summary

Problems solved by technology

However, the traditional threshold detection algorithm has low accuracy and it is difficult to distinguish falls from normal activities similar to falls, such as lying down, squatting, bending over, etc., resulting in false positives and false negatives

[0005] In summary, there is still a lack of effective solutions to solve the problem of false positives and missed negatives in the detection of falls of the elderly in the existing health monitoring system for the elderly.

Images