Comparison of t-test ranking with PCA and SEPCOR feature selection for wake and stage 1 sleep pattern recognition in multichannel electroencephalograms
详细信息 查看全文
- 作者：T.K. Padma Shri ; PhD research studenta ; b ; padma.shri@manipal.edu" class="auth_mail" title="E-mail the corresponding author (Senior Associate Professor) ; N. Sriraamc ; sriraam@msrit.edu" class="auth_mail" title="E-mail the corresponding author ; natarajan.sriraam@gmail.com" class="auth_mail" title="E-mail the corresponding author (Professor ; Head of the Department of Medical Electronics)
- 关键词：Electroencephalogram (EEG) ; Spectral entropy ; t-Test ; Principal component analysis (PCA) ; Separability & correlation (SEPCOR) ; Multilayer perceptron (MLP) neural network ; k-Nearest neighbor (k-NN) classifiers
- 刊名：Biomedical Signal Processing and Control
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：31
- 期：Complete
- 页码：499-512
- 全文大小：2516 K
文摘
- class="listitem" id="list_lis0005">
- class="label">•
Characterization of wake and stage1 sleep architecture is done using multidimensional Spectral entropy (SE) feature ranking.
- class="label">•
A wake/stage1sleep scoring model is proposed using SE computed per second unlike 30 sec interval used in manual scoring.
- class="label">•
The classifier models are built on a robust training method that randomly selects 60% of the dataset for training.
- class="label">•
The proposed methods show F4 region with high discrimination between groups linked to reduced activity in stage1 as reported in medical literature.