Fall detection method and device based on multi-sequential probability ratio test

Abstract

The invention discloses a tumble detection method and device based on multi-sequential probability ratio test, and relates to the technical field of medical instruments. The device includes an upper limb force sensor and a lower limb ultrasonic sensor array, wherein an upper limb force signal passes through an identified admittance control model to obtain a speed response signal, the lower limb ultrasonic sensor array solves the real-time coordinates of user motion, then displacement is obtained and multi-sensor data fusion is conducted through a Kalman filtering algorithm; and finally, multi-sequential probability ratio-based test is performed on the fused data to determine whether the user falls down or not. According to the invention, the falling detection problem of the walking aid is solved, the data processing amount of a processor is reduced, and the oneness and delay of the SPRT (Sequential Probability Ratio Test) are solved by a multi-SRP algorithm, so that the detection speed is higher, and the use safety of the walking aid is improved.

Description

technical field [0001] The invention relates to the technical field of medical devices, in particular to a fall detection method and device based on multiple sequential probability ratio tests. Background technique [0002] my country is the country with the largest elderly population, and the number of elderly people will continue to increase in the future. A series of problems brought about by aging will become the key issues that our country urgently needs to solve. The elderly usually suffer from muscle atrophy, osteoporosis, vision and hearing loss, and related diseases caused by organ degeneration, making it difficult for the elderly to complete basic daily activities alone, causing a lot of inconvenience. Smart walking aids are a kind of medical equipment that can help the elderly to perform daily walking and resume exercise. At present, there are few walking aids with fall detection function, and most of them use visual sensors and wearable sensors to detect falls. ...

AI Technical Summary

Problems solved by technology

[0003] The fall detection method based on the visual sensor is to use the depth camera to obtain real-time images of the user while walking, and to recognize the posture of the human body through neural network and other related image algorithms to determine whether a fall has occurred. The disadvantage of this method is that the related algorithms are relatively complicated. The processor requirements are high, and the camera is easily interfered by factors such as light; the fall detection method based on wearable sensors needs to install a posture sensor on the user to collect motion signals to identify the user's posture. The disadvantage of this method is that the user must wear a specific The sensor increases the difficulty of using the device, and the user's comfort is poor

Images