Human body behavior identification method based on inertial sensor

Abstract

The invention provides a human body behavior identification method based on an inertial sensor. The method comprises the steps of acquiring human body behavior data of testees by means of the inertial sensor, conducting sliding window segmentation on the acquired human body behavior data, conducting feature extraction on a triaxial accelerated speed subsequence and a triaxial angular speed subsequence which are obtained after sliding window segmentation, conducting feature fusion on a feature vector to form a sample set of the human body behaviors of the testees, conducting feature selection on the sample set by means of the least correlated maximum redundant algorithm and the Bayes regularization sparse polynomial logistic regression algorithm, obtaining the classification feature vectors of all human body behaviors of all the testees, obtaining a classifier model of each human body behavior by means of a fuzzy least square support vector machine, and obtaining a human body behavior identification result after the human body behavior data are tested by means of the fuzzy least square support vector machine. By means of the human body behavior identification method, self-adaptation and identification efficiency can be improved.

Description

technical field [0001] The invention relates to the technical field of behavior recognition, in particular to a human behavior recognition method based on an inertial sensor. Background technique [0002] In the past 10 years, with the rapid development of MEMS (Micro-Electro-Mechanical System, MEMS) technology, sensors and mobile devices have unprecedented characteristics such as high computing power, small size and low cost, making these mobile devices Information interaction between equipment and people has become a part of daily life. The main purpose of pervasive sensing is to obtain data from sensors all over the place and extract useful information from them. In this field, the analysis and recognition of human behavior has become a hot research topic, which has an important role in promoting medical treatment, sports competition, military affairs, security, etc. [0003] Commonly used human behavior recognition has two different implementation forms, one is to use ...

AI Technical Summary

Problems solved by technology

However, although the simple dimensionality reduction method in the prior art has high execution efficiency, its classification accuracy is low. Although the sequence forward selection algorithm has high classification accuracy, its calculation process is more complicated.

The classifier model method for obtaining human behavior in the prior art generally adopts a support vector machine (Support Vector Machine, SVM). Although the support vector machine of the prior art has high recognition accuracy, when the amount of training sample data is large, due to the need to Solving time-consuming quadratic programming problems requires a lot of computing resources, resulting in long training time

Images