Non-interference self-adaptive sleeping posture recognition method based on pillow finite element analysis

Abstract

The invention provides a non-interference self-adaptive sleeping posture recognition method based on pillow finite element analysis. The method comprises the following steps: S1, acquiring pressure distribution or indentation shape of a human-pillow interface through a pillow system; S2, analyzing the acquired human-pillow interface pressure distribution or indentation shape by using a finite element, and constructing human-pillow interface pressure matrix or indentation amount matrix data; S3, carrying out the corresponding training of the human-pillow interface pressure or depression matrix sample data through a support vector machine multi-classifier, and constructing an accurate recognition criterion; S4, identifying and classifying the to-be-predicted human body sleeping posture data through an identification criterion to obtain a classification result. According to the method, the sleeping postures are accurately recognized under the condition that real sleep is not affected, the sleeping postures are effectively recognized and classified by using human-pillow interface pressure distribution or depression shapes, finite element analysis and optimal classification hyperplane analysis in multiple classifiers of a support vector machine, and a technical support is provided for evaluating the sleep quality of the human body and achieving intelligent design and customized production of the pillow.

Description

technical field [0001] The invention relates to the technical field of smart home, in particular to a non-interference adaptive sleeping posture recognition method based on pillow finite element analysis. Background technique [0002] Sleep is an essential physiological need of human beings, occupies one-third of people's life time, and is very important to people's physical and mental health. During sleep, people adjust their sleeping posture by turning over at an appropriate frequency, which can adjust the pressure distribution of the human body, avoid local long-term pressure, benefit blood circulation and nerve conduction, and relieve muscle fatigue. Therefore, a good sleep process must be accompanied by changes in various sleeping positions, and different sleeping positions will produce different pressure and shape interfaces of person-bed, person-pillow, and have different requirements for support conditions. Unsuitable support conditions will cause excessive local pr...

AI Technical Summary

Problems solved by technology

The former attaches various monitors such as electrode sheets and infrared light to the head and body of the person, which is an intrusive monitoring method that directly affects the comfort of sleep, and the operation is complicated and requires high professional skills; the latter needs to shoot and record people. sleep process, it is difficult to protect the user's privacy

Therefore, none of the existing methods are suitable for daily sleeping posture recognition at home, and are not conducive to commercial application and promotion.

Images