Personalized epileptic seizure detection device based on network parameter migration

Abstract

The invention relates to a personalized epileptic seizure detection device based on network parameter migration. The personalized epileptic seizure detection device comprises a memory, a processor anda computer program stored on the memory and capable of running on the processor. The detection device is characterized in that when the processor executes the program, the following method steps arerealized: step 1, an epilepsy patient electroencephalogram signal preprocessing module; step 2, a pre-training data set construction module; step 3, a convolutional autoencoder training module; 4, a personalized training data set construction module; a one-dimensional convolutional neural network initialization module; and step 6, a one-dimensional convolutional neural network training optimization module.

Description

technical field [0001] The invention relates to a personalized epileptic seizure detection device based on network parameter migration, which belongs to the technical field of biomedical signal processing and the field of clinical technical detection of epileptic seizures. Background technique [0002] Epilepsy is a chronic brain disease caused by abnormal discharge of brain neurons and affects all ages. Long-term frequent attacks will have a serious impact on the physical and mental conditions of patients, and will cause a certain degree of social discrimination. At present, the diagnosis of epilepsy mainly relies on neurophysiologists and neurologists to visually inspect the EEG records of patients. Manual inspection of EEG data records and identifying abnormal segments is a task that consumes a lot of time and energy, and due to subjective differences Existence often leads to misjudgment. Therefore, it is necessary to design an efficient and accurate automatic detection...

AI Technical Summary

Problems solved by technology

These traditional methods have shown good detection results on different patient data sets, but there are still cases of missed and wrong detections.

Moreover, feature extraction depends on certain prior knowledge, and the extracted features may be different for different data sets, and there is no guarantee that the extracted features are the most representative of the original EEG data.

Images