Method and device for monitoring tumble

Abstract

The invention discloses a method and a device for monitoring tumble. The method for monitoring tumble comprises: utilizing a mode recognition method, creating a human body tumble behavior recognition model based on a support vector machine to screen standard feature vectors capable of serving as human body tumble judge, and judging the tumble state of the human body through the joint judge of the mode recognition of the support vector machine and the inclination angle threshold. The device is composed of an acceleration sensor, a microcontroller, a GPS (Global Position System) module, a GSM (Global System for Mobile Communications) module, and the like. The method for monitoring tumble is used for monitoring the acceleration and inclination angle data in a tumble process in real time, correctly recognizing the human body tumble state and timely sending the tumble information and direction to family members of the user and nurses of a community hospital to rescue the user in time. According to the invention, tumble detection is more reliable, tumble judging accuracy is improved, individual difference error is effectively reduced and recognition capability of different tumble categories is greatly improved.

Description

technical field [0001] The invention belongs to the field of automatic detection, in particular to a method and device for monitoring falls. Background technique [0002] Falling is a common injury event for the elderly, and it is one of the main causes of disability, disability and death of the elderly. It poses a great threat to the health and life of the elderly, and brings a huge burden and loss to the family and society. It is the elderly An important health care issue, it is also a social issue that deserves attention. [0003] Falling is a common injury event for the elderly, and it is one of the main causes of disability, disability and death of the elderly. It poses a great threat to the health and life of the elderly, and brings a huge burden and loss to the family and society. It is the elderly An important health care issue, it is also a social issue that deserves attention. [0004] Due to the inconvenience of movement, the elderly often suffer from high blood...

AI Technical Summary

Problems solved by technology

At present, there are three basic methods for monitoring falls: (1) based on the analysis of video images, the real-time motion of the object is monitored by the camera. The camera monitoring range will not work

(2) Based on the analysis of the audio frequency signal, the fall event is judged by analyzing the frequency of the vibration caused by the impact, but the installation is more complicated and the capital investment is relatively large

(3) Based on wearable device detection, there are mainly two types: one is to measure the change of acceleration and inclination angle when falling by wearing an accelerometer and an inclinometer on the waist, and then set the threshold parameter setting according to the corresponding experiment and calculation. Judging whether the human body has fallen, but due to the asynchronous algorithm execution between the inclinometer and the accelerometer, it is easy to cause false positives or false positives

The algorithm design of the interpretation method is relatively intuitive, and it is relatively easy to realize the algorithm, so this method is the most common research method at present. Its shortcoming is that the setting of the threshold has a great impact on the recognition results. The acquisition is often based on experience or experimental data. If the empirical value is used, it is not easy to know the accuracy of the threshold. The fuzzy recognition of the empirical threshold method is likely to cause individual difference errors. The recognition model high complexity

Images