Fatigue classification method for constructing brain function network and correlation vector machine based on generalized consistency

Abstract

The invention provides a fatigue classification method for constructing a brain function network and a correlation vector machine based on generalized consistency. Compared with the prior art, the method has higher reliability and accuracy, an effective fatigue classification network is constructed through information flowing direction and a causal relationship to classify connection characteristics of a brain network under different mental states, thereby effectively verifying results of topological structure research and improving the detection ability of driving fatigue. The fatigue classification method has the advantages that the brain network is constructed by using a generalized consistency algorithm method, the brain is regarded as a multi-regional cooperative network, informationcirculation direction and causal relationship between nodes of the brain are researched, topological structure changes of the brain network are analyzed under different mental states, the fatigue generation mechanism is disclosed, and a new perspective is provided for fatigue-related research; the correlation vector machine is used for classifying the connection characteristics, 90% or above classification accuracy can be achieved, the reliability of topological structure analysis is verified, and a new method is provided for fatigue detection.

Description

Technical field [0001] The invention relates to a fatigue classification method based on generalized consistency to construct a brain function network and a correlation vector machine. Background technique [0002] With the rapid economic development, automobiles have become the main means of transportation in people's lives. However, traffic safety has also become a problem that society urgently needs to solve. Fatigue driving is one of the important causes of major traffic accidents. Therefore, by studying the mechanism of the generation and induction of driving fatigue, detecting the physiological, psychological, and behavioral status of the driver, and making judgments on the fatigue degree of the subjects, it is beneficial to improve driving safety and reduce traffic accidents caused by fatigue. [0003] The physiological characteristics of the driver in a normal state are different from those in a fatigue state. Therefore, it is possible to determine whether the driver is i...

AI Technical Summary

Problems solved by technology

However, the driving fatigue detection method based on power spectrum and entropy does not involve brain regional information, and cannot comprehensively and systematically study the mechanism of driving fatigue

However, in the construction of brain functional networks, functional connection networks (such as: phase lag index method, phase lock value method, etc.) cannot reflect the flow of information and the causal relationship between nodes.

In the existing fatigue-related technologies, there is little research on the topological structure of brain functional networks under fatigue and waking states, and there is no classification of brain networks under waking and fatigue states to study the reliability of related methods

Images