Computer mode recognition method for brain electrical signals of epilepsy patients

A computer model and EEG signal technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve the problems of different accuracy, inability to fully guarantee the optimal parameters of the model, and inapplicability, so as to improve accuracy and avoid Penalty function is too high and over-learning state, the effect of improving operating efficiency

CN109645990AActive Publication Date: 2019-04-19BEIHANG UNIV
2 Cites 13 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2019-04-19

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a computer mode recognition method for bran electrical signals of epilepsy patients, and relates to the technical field of brain science and epileptic seizure clinical data recognition. The method includes the steps that firstly, a random forest recognition model is constructed and then trained so that the optimal random forest recognition mode can be generated; mode recognition testing of the brain electrical signals of the epilepsy patients with different degrees of disease conditions is conducted on the optimized random forest model on a test set. Through the computer mode recognition method, the function that through a computer, the brain electrical signals of the epilepsy patients are automatically recognized is realized, and technical supports are provided when medical workers consumes time and labor for diagnosis. A grid search optimization method is introduced, a variable step size mode is adopted for repeatedly filtering parameters to accelerate optimalcombining of search parameters, the operation efficiency of the random forest model is improved, the trained random forest recognition model realizes the optimal effect, and the accuracy of mode recognition conducted on three kinds of epilepsy disease conditions can reach 96% or above.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical fields of brain science and epileptic seizure clinical data recognition, in particular to a computer pattern recognition method for EEG signals of epileptic patients. Background technique

[0002] The seizures of epilepsy are clinical manifestations of paroxysmal abnormal hypersynchronous electrical activity of neurons in the brain, which are characterized by repetition, suddenness and temporaryity. As an important tool for studying epilepsy, EEG signals can reflect seizure information in real time that cannot be provided by other physiological methods. At present, in the analysis and research of EEG signals of epileptic patients, machine learning is a powerful tool for the identification of EEG signals in epilepsy. However, most machine learning methods to identify EEG signals have a relatively complicated calculation process, and the accuracy of the recognition method cannot be guaranteed. and effectiveness. T...

Examples

Embodiment Construction

[0040] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0041] The invention provides a method for computer pattern recognition of EEG signals of epileptic patients. The method first conducts long-term, multiple Acquisition and sampling of channel EEG signals, and marking (labeling) the EEG signals of epilepsy patients with different degrees of conditions; performing preprocessing operations and EEG feature extraction operations on the EEG signals. Build a random forest recognition model based on machine learning technology, optimize the parameters generated by the random forest recognition model through the grid search optimization method, and at the same time, import the preprocessed EEG signals into the constructed and optimized random forest recognition model , the recognition process is performed. The optimized random forest recognition model provided by the present invention is based on machine lear...