Machine learning-based falling discrimination method of intelligent carpet

Abstract

The invention discloses a machine learning-based falling discrimination method of an intelligent carpet. On the intelligent carpet designed according to reasonable human body walking rules, a machinelearning method is used to use data change situations of carpet stepping points on time and space in walking processes as input features of machine learning, information is stored into a database through repeated walking, matching is carried out on stored feature information and actual walking situations of users, and thus a feature environment based on machine learning is realized. A hidden Markov probability transfer model is established before a classification algorithm is carried out, the carpet is enabled to obtain a self-adaptive object discrimination function, invalid stepping point information on the carpet is removed, and target user information is retained. In a training process, an SVM (Support Vector Machine) is used for training, different kernel function feature data are selected for repeated training, two processes of walking and falling are repeated on the intelligent carpet according to different training results, a highly reliable falling discriminant model is established.

Description

Technical field [0001] Based on the machine learning perspective, the present invention comprehensively analyzes the differences of different walking units in the process of walking in the smart carpet environment, and uses the probability graph model (mainly hidden Markov model) in machine learning to adaptively remove invalid walking information from the carpet , And establish a supervised classification model based on support vector machines according to the changes in acceleration and center of gravity of the target object during walking. Background technique [0002] Smart carpet is an intelligent device used for fall detection during the walking process of the elderly, and it is mainly composed of a large number of sensor nodes of different forms. The main task of the smart carpet is to collect the footprint information of the walking people through the bottom sensor. When the sensor is strong enough, it can even directly obtain the information such as gravity and accelerat...

AI Technical Summary

Problems solved by technology

[0005] Technical problem: The purpose of this invention is to provide a smart carpet fall judgment method based on machine learning, using machine learning algorithms to solve the problem of fall judgment during walking, mainly to solve two problems, 1: how to design smart carpets, and solve the problem of carpet data Transmission methods and signal processing issues

Images