The mRMR-CNN based influential support decision system approach to classify EEG signals. (May 2020)

• Record Type: Journal Article
• Authors: Kaya, Duygu
• Is Part Of: Measurement. Volume 156(2020)
• Publication Date: 2020-05
• Subjects: CNN -- Deep learning -- Feature selection -- k-NN -- mRMR; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2020.107602
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: This study applied deep learning models to classify Normal-Epileptic states through the EEG Signals. The features extracted from the equivalent layers of the AlexNet and VGG16 CNN models were combined. The combined features have reduced with a feature selection method that is called mRMR. The significant results are achieved by using k-NN. Abstract: Signal analysis methods are important to extract significant information from signals. In this study, it is aimed to develop an efficient and a reliable EEG signal analysis system based on mRMR-CNN structure used selected features. AlexNet and VGG16 pre-trained network are used to extract feature from the data. Four different Models (Model 1, Model 2, Model 3, Model 4) is examined. In addition, a feature selection algorithm namely mRMR was applied to create a more effective feature vector. Filtering with mRMR allows the concentration of related features and minimization of irrelevant features. The deep features are obtained from the fc6 and fc7 layers. To get high performance, the mRMR algorithm is applied to obtain efficient features and the proposed Model 4 is created. The selected properties with mRMR gave the best results for fine and weighted k-NN. With Model 4, more successful results obtained 98.78%, 98.56%, respectively for fine and weighted k-NN.