Fatigue detection method based on multi-information fusion

Abstract

The invention relates to a fatigue detection method based on multi-information fusion. The fatigue detection method comprises the following steps: 1) acquiring an electromyographic signal EMGRAW1 of arm biceps brachii muscle of a user to be detected and an electromyographic signal EMGRAW2 of arm radialis brachii muscle of the user to be detected, and performing filtering processing to obtain filtered signals EMGF1 and EMGF2; 2) respectively calculating a first myoelectricity fatigue index FIEMG and a second myoelectricity fatigue index FMPF; (3) electroencephalogram signals of a user to be detected are collected and preprocessed; 4) respectively calculating a first electroencephalogram fatigue index F (delta + theta) / beta and a second electroencephalogram fatigue index FPSI; and 5) carrying out feature fusion on the electromyographic signal and the electroencephalogram signal, calculating a human body fatigue index F, and judging the fatigue state of the user to be detected according to the human body fatigue index F. Compared with the prior art, the method has the advantages that fatigue detection of multiple environment states is more comprehensive, individual differences are considered, personalized setting is supported and the like.

Description

technical field [0001] The invention relates to the technical field of fatigue detection, in particular to a fatigue detection method based on multi-information fusion. Background technique [0002] Fatigue is mainly divided into physical fatigue and mental fatigue. Physical fatigue, that is, muscle fatigue, refers to the fatigue of body muscles under work activities. Mental fatigue, also known as mental fatigue, refers to mental fatigue caused by heavy mental work, excessive nervous system tension, or long-term monotonous and boring work. Existing fatigue detection methods ignore the types of fatigue, and the detection is single and one-sided, unable to comprehensively represent a person's fatigue, and even some are unreliable. [0003] Most of the existing methods use fatigue detection methods based on pulse signals and EMG signals, which can only detect fatigue caused by muscle activity, but cannot detect fatigue in the brain and nerves; fatigue based on EEG signals and...

AI Technical Summary

Problems solved by technology

Existing fatigue detection methods ignore the types of fatigue, and the detection is single and one-sided, unable to comprehensively express a person's fatigue, and some are even unreliable

[0003] Most of the existing methods use fatigue detection methods based on pulse signals and electromyographic signals, which can only detect fatigue caused by muscle activity, but cannot detect fatigue in the brain and nerves; fatigue based on EEG signals and ECG signals The detection method can only judge the fatigue of the brain and nerves, but cannot detect the fatigue of the muscles

[0004] In addition, the signals collected by fatigue detection sensors such as EMG sensors and EEG sensors will be affected by subcutaneous fat, muscle rate, hair volume, etc. Therefore, there are often differences in the signals collected by different people. Most of the existing methods , often using a unified algorithm and index, and does not take into account the differences in signal characteristics of different people

Images