Depression detection method based on combination of brain neuron spike potential and local field potential

Abstract

The invention discloses a cerebral neuron spike potential and local field potential combined depression detection method. The method comprises the following steps: respectively acquiring electroencephalogram data of a target object in a depression state and a non-depression state; performing feature fusion on the brain neuron spike potential data and the local field potential data corresponding to the same electroencephalogram data to obtain fused electroencephalogram data; training an ensemble learning network based on the training data, determining an optimal network parameter, and optimizing the ensemble learning network based on the optimal network parameter; and performing classification prediction on the current electroencephalogram data of the target object based on an integrated learning network, performing voting selection on each output classification prediction result, and determining the depression state of the target object based on a final classification result. According to the method, the final prediction result is comprehensively obtained through result voting selection of the three classifiers by utilizing the advantages of integrated learning in combination with different classifiers. The characteristics in the signals can be effectively extracted, and the depression state can be accurately judged.

Description

technical field [0001] The present application relates to the technical field of EEG data analysis, in particular, to a method for detecting depression by combining brain neuron spike potentials with local field potentials. Background technique [0002] EEG data signal is the information carrier carrying the state of the brain and an important tool for judging the state of the brain. Since EEG data are usually high-latitude complex signals, it is usually necessary to obtain effective information in EEG signals through EEG signal feature extraction technology. Based on the EEG signal extraction technology, the emotional state of the brain can be analyzed, which has important research and clinical application significance for the diagnosis and treatment of brain nervous system diseases such as depression and epilepsy. [0003] The invention with the application number 202111049290.5 discloses an analysis method of EEG signals, which uses a multi-band spatiotemporal convolutio...

AI Technical Summary

Problems solved by technology

[0005] Although the above method can realize the extraction of EEG features to a certain extent, for depression with complex EEG signals, the above method cannot make good use of the information in the EEG signals, resulting in the loss of some of the key points in the EEG signals. The problem that information, or extracted features are invalid in judging the state of depression

Images