High frequency oscillation rhythm detection method based on quantization error optimization Gaussian mixture model

Abstract

The invention provides a high-frequency oscillation rhythm detection method based on quantization error optimization of Gaussian mixture model. The method based on cluster analysis detects the high-frequency oscillation rhythm, and selects fuzzy entropy, short-term energy, power ratio and spectral centroid as epilepsy EEG The characteristic of the signal, the eigenvector of which is used as the input of the clustering algorithm, the eigenvector is classified by the expectation-maximization Gaussian mixture model clustering algorithm, a quantitative error model is established, the number of clusters is optimized, and the epilepsy EEG signal is improved. The detection accuracy of high-frequency oscillation rhythm was determined, and the median and interquartile range were selected to analyze the statistical characteristics of each category, and the high-frequency oscillation rhythm was detected. A high-frequency oscillation rhythm detection device and storage device realize a high-frequency oscillation rhythm detection method. The beneficial effects of the invention are as follows: the detection accuracy of the high-frequency oscillation rhythm of the epilepsy EEG signal is improved, and the doctor can be helped to diagnose epilepsy and remove epileptogenic foci.

Description

technical field [0001] The invention relates to the field of epilepsy EEG signal processing, in particular to a high-frequency oscillation rhythm detection method based on quantization error optimization Gaussian mixture model. Background technique [0002] Epilepsy is a common neurological disorder affecting approximately 1% of the world's population. At present, there are more than 9 million epilepsy patients in my country, and the number is still increasing at a rate of 650,000-700,000 per year. Most people with epilepsy are treated with antiepileptic drugs. Since the discovery of phenobarbital in the treatment of epilepsy at the beginning of the last century, antiepileptic drugs such as phenytoin, ethosuximide, carbamazepine, and valproic acid have been continuously released, which can control the seizures of 70% of epileptic patients. Most patients can no longer get sick after conventional drug treatment. However, 30% of the patients are still diagnosed as intractabl...

AI Technical Summary

Problems solved by technology

However, the low-frequency frequency components detected by this method are easily interfered by other signals, which makes the positioning result wrong and leads to the failure of the resection operation.

At the same time, this method is very time-consuming, and the positioning time is about 24-72 hours, which increases the risk of surgery

Images