EEG Signal Analysis and Classification by Siuly Siuly Yan Li & Yanchun Zhang

Author:Siuly Siuly, Yan Li & Yanchun Zhang
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

7.2 Principal Component Analysis-Based Optimum Allocation Scheme

This study develops a new framework for classifying epileptic EEG signals as presented in Fig. 7.1. The research work investigates and explores whether the OA based PCA features, (named OA_PCA) are suitable for epileptic EEG signal classification, evaluates which classifier is more suitable for the feature set. From Fig. 7.1, it can be seen that the proposed methodology is divided into six major parts: sample size determination (SSD), data segmentation, sample selection by OA (denoted as OA_Sample), dimension reduction by PCA, OA based PCA features (named as OA_PCA) and classification by the LS-SVM, NB, KNN and LDA. Brief explanations of these six parts are provided below.

Fig. 7.1Architecture of the proposed system for the classification of epileptic EEG signals. Note OA i = optimum allocation in the ith window; OA_Sample: selected sample by the OA together from each window; OA_PCA: feature vector set obtained by optimum allocation and principal component analysis; SSD = n; n(1) = sample size by OA1 from window 1; n(2) = sample size by OA2 from window 2 and n(k) = sample size by OA k from window k

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.