Emotional feature representation method based on electroencephalogram signal space-time power spectrogram
The invention discloses an emotional feature representation method based on an electroencephalogram signal space-time power spectrogram. The method comprises the following steps: acquiring an electrode location map according to a 10-20 system electrode placement method, and graying the electrode loc...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
06.08.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses an emotional feature representation method based on an electroencephalogram signal space-time power spectrogram. The method comprises the following steps: acquiring an electrode location map according to a 10-20 system electrode placement method, and graying the electrode location map to obtain an electrode location grey-scale map; acquiring electroencephalogram signals collected by all the electrodes, and performing filtering processing; dividing the filtered electroencephalogram signals according to time periods to obtain time domain feature data of the electroencephalogram signals; calculating the power spectral density of a corresponding frequency band in the electroencephalogram signals in each time period, extracting the logarithm of the power spectral density as a characteristic value, and normalizing the characteristic value to a color value being 0-255; assigning the normalized characteristic values to the locations of corresponding electrodes in the electrode location grey-sc |
---|---|
Bibliography: | Application Number: CN202110518743 |