Method and system for detecting tumble of old people in real environment based on big data

Abstract

The invention discloses a method and system for detecting tumble of old people in a real environment based on big data. The system is characterized in that a wearable unit comprises a sensor module, an on-site processing single-chip microcomputer and an on-site storage module, the sensor module is arranged on an old man, the sensor module and the on-site storage module are correspondingly and electrically connected with the on-site processing single-chip microcomputer, a remote service unit comprises a tumble condition database, a support vector machine, a tumble data processing module and a remote service control chip, the remote service control chip is correspondingly and electrically connected with the tumble condition database, the support vector machine and the tumble data processing module, the on-site processing single-chip microcomputer is correspondingly and electrically connected with a communication unit, the communication unit is correspondingly and electrically connected with the remote service unit and a tumble alarm unit, and the communication unit is correspondingly and electrically connected with the remote service control chip. According to the invention, self-learning can be carried out by using big data, whether the elderly fall down or not is accurately and intelligently judged, and the pain point of high misjudgment rate in the prior art is solved.

Description

technical field [0001] The invention relates to the field of fall detection of the elderly, in particular to a method and system for detecting falls of the elderly in a real environment based on big data. Background technique [0002] As our country gradually enters an aging society, the safety precautions in the daily life of the elderly have increasingly become a hot spot of social concern. According to reports in Shanghai, in 2010 alone, 1,983 people died of falls, of which 87.1% were elderly people over the age of 65. In addition, more than half of the cases of hospitalization due to injuries among the elderly are falls; more than 80% of the cases of hospitalization due to injuries are falls. [0003] Through investigation, research finds that the rescue within 20 minutes after the elderly falls can minimize the injury, which is the golden time for rescue. Therefore, an accurate fall detection technology is bound to exert huge social and economic benefits in my country...

AI Technical Summary

Problems solved by technology

[0004] 1. It is difficult to obtain real fall data of the elderly as the basic data for the design and verification of fall detection methods; 2. The data obtained by existing sensors overlaps between falls and non-falls, making it difficult to distinguish, which is likely to cause misjudgments and omissions 3. In the whole world, there is no data sample for the verification of the fall algorithm, which virtually increases the difficulty of algorithm verification, which is a groundbreaking work; 4. The differences in individual characteristics of each person, such as gender, Height, weight, etc. will cause some data differences in the fall monitoring process, thus increasing the difficulty of developing and verifying the fall algorithm

Images