Polygraph method based on multi-channel EEG signal waveform factor

Abstract

The invention provides a polygraph method based on a multi-channel EEG signal waveform factor. The method comprises the following steps: performing real-time collecting of EEG signals of multiple parts of the heads of both honest and lying subjects through a multi-channel EEG electrode, and performing pre-processing on the collected EEG signals; calculating the waveform factor of each of the EEG data, and extracting the waveform factor of the electrode with significant difference between the two types of subjects as the classification feature; constructing the feature vector by using the waveform factor index of the electrode of the two types of subjects with significant difference as sample data, and verifying an initial machine learning classifier model by the sample data to obtain a classifier having the best parameter combination; and performing lie detection on a tester by using the classifier. The method for calculating the waveform factor of the multi-conducting EEG signal is applied to the field of EEG lie detection, can well distinguish the EEG signals of the honest and lying groups, thereby achieves the purpose of detecting lies and improving the polygraph detection efficiency and accuracy.

Description

technical field [0001] The invention relates to the field of electroencephalogram lie detection, in particular to a lie detection method based on multi-conductor electroencephalogram signal waveform factors. Background technique [0002] Lying is a common social and psychological phenomenon in human society. Lies have become a factor affecting social stability and unity, and pose a serious threat to the property and life safety of the people. Therefore, psychophysiologists and other related experts have been working hard to find effective lie detection methods. The effectiveness of lie detection has been confirmed in long-term and extensive application practice at home and abroad. First of all, polygraph technology has important application value for the detection of criminal investigation cases. In addition, lie recognition is also of great significance to the treatment of mental illness and mental disorders. In addition, the current international anti-terrorism situati...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a polygraphy method based on the shape factor of EEG signals, which is intended to solve the problems of large amount of stimulation and low accuracy in the existing ERP-based polygraphy technology

Images