Electroencephalo-graph (EEG) signal identification and detection method for measuring alertness of driver

Abstract

The invention relates to an electroencephalo-graph (EEG) signal identification and detection method for measuring the alertness of a driver, belonging to the technical field of information processing. After the minimum redundancy rate among characteristic values and the maximum correlation degree are calculated by dividing the frequency range of the frequency-domain sequence of a testing section of an EEG signal, the alertness state of each time period is classified by using the support vector machine method based on Gaussian kernel, and the identification of mild sleepiness is realized. In the invention, the mild sleepiness state of the human brain before entering sleepiness is identified through the EEG signal so as to predict and prevent alertness from further decreasing. The method effectively reduces the EEG characteristic data processed during the alertness classification stage, identifies the mild sleepiness state in a high accuracy rate and can overcome the interference of the signal acquisition stage to a certain extent.

Description

technical field [0001] The invention relates to a method in the technical field of information processing, in particular to an electroencephalogram signal recognition and detection method for measuring the driver's vigilance. Background technique [0002] Alertness refers to the degree of sensitivity that a person exhibits when concentrating on performing an operational task, including measures of fatigue and drowsiness. Many human-computer interaction systems require the operator to maintain a certain degree of vigilance. Some special jobs, such as controllers in air control centers, pilots and coach drivers on highways, require a high degree of vigilance. Accurate estimation and real-time monitoring of human alertness is a very important topic in the research of human-computer interaction systems, especially after driving for a long time, the driver will experience fatigue and decreased alertness. Vigilance analysis can effectively judge the driver's alertness. Fatigue l...

AI Technical Summary

Problems solved by technology

The features selected on the EEG signal usually have a greater impact on the final result. In order to obtain more information, many leads are usually selected to collect the EEG signal, which results in the EEG signal used for alertness recognition. The feature dimension of is usually very high, which has a negative impact on the real-time performance of later calculations and alertness discrimination.

Images