EEG Signal Classification Automation using Novel Modified Random Forest Approach

Abstract

Digitalization and automation are the two aspects in the medical industry that define compliance with industry 4.0. Automation is essential for speeding up the diagnosis process, while digitalization leads to smart medicine and efficient diagnosis. Epilepsy is one such disease that can use these automation techniques. The automatic monitoring of epilepsy EEG is of great significance in clinical medicine. Aiming at the non-stationary characteristics of EEG signals, the classification of EEG signals is based on the combination of overall empirical mode. It is proposed using the random forest method. The EEG signal data set has an epileptic interval over 200 single-channel signals with a seizure period. A total of 819,400 data are used as samples. First, the overall epileptic EEG signal modal is decomposed into multiple intrinsic modal functions. The effective features are extracted from the first-order intrinsic modal function. Finally, random forest and Least Square SVM (LS-SVM) are considered to classify the EEG signals characteristics. The correct recognition rate of random forest and LS-SVM is compared. The results show that random forest classification method has an ideal classification effect on epilepsy EEG signals during and between seizures. The recognition accuracy is 99% and 60%, which is higher than the accuracy of the LS-SVM. The proposed method improves clinical epilepsy. The efficiency of EEG signals analysis.