Machine learning algorithm for sleep staging by applying prefrontal lobe single-channel electroencephalogram signals

Abstract

The invention discloses a machine learning algorithm for sleep staging by applying prefrontal lobe single-channel electroencephalogram signals. The machine learning algorithm comprises training model establishment and final output prediction, the training model establishment comprises the four stages of Fp1-Fp2 electroencephalogram data acquisition, filtering and artifact removal, 30s segmentation processing and feature extraction, and finally the training model is established; and Fp1-Fp2 electroencephalogram data collection, filtering and artifact removal, 30s segmentation processing and feature extraction are also needed for final output prediction, finally, the extracted features are sent into the established training model to obtain final output prediction, and the collection of the Fp1-Fp2 electroencephalogram data is to place a flexible patch electrode at the Fp1-Fp2 position of the forehead lobe of the human brain to collect electroencephalogram signals. The machine learning algorithm has the advantages that the Fp1-Fp2 forehead lobe single-channel electroencephalogram adopted by the device is located at the forehead of the human brain, a flexible patch electrode is used as an acquisition electrode, acquisition and wearing are very convenient, and night sleep of a wearer cannot be affected by nearly non-inductive wearing.

Description

technical field [0001] The invention relates to a machine learning algorithm for sleep staging, in particular to a machine learning algorithm for sleep staging by applying a prefrontal lobe single-channel electroencephalogram signal, and belongs to the technical field of sleep staging. Background technique [0002] Sleep monitoring, like heart rate, blood oxygen, and blood pressure and other daily physiological indicators, is one of the very important daily monitoring items. Sleep monitoring is not only needed by people with sleep disorders, but also by many ordinary people and some patients with chronic diseases. Sleep staging based on EEG will be much more accurate than methods based on ECG or pulse rate, body movement, etc. Currently, sleep monitoring methods based on EEG signals are mainly based on multiple channels, such as EEG, EOG, and EMG, or a single channel based on the position of the central axis of the head, such as Fpz-Oz, Pz-Cz and other single-channel EEG si...

AI Technical Summary

Problems solved by technology

These two methods will cause a lot of inconvenience for ordinary people's sleep monitoring, and the wearing method is also relatively cumbersome, and even affect sleep

Images