scholarly journals Independent Component Analysis for Source Localization of EEG Sleep Spindle Components

2010 ◽  
Vol 2010 ◽  
pp. 1-12 ◽  
Author(s):  
Erricos M. Ventouras ◽  
Periklis Y. Ktonas ◽  
Hara Tsekou ◽  
Thomas Paparrigopoulos ◽  
Ioannis Kalatzis ◽  
...  
Keyword(s):  
Independent Component Analysis ◽  
Visual Analysis ◽  
Activity Patterns ◽  
Current Source ◽  
Component Analysis ◽  
Independent Component ◽  
Source Analysis ◽  
Sleep Spindles ◽  
Electroencephalogram Eeg ◽  
Selection Of

Sleep spindles are bursts of sleep electroencephalogram (EEG) quasirhythmic activity within the frequency band of 11–16 Hz, characterized by progressively increasing, then gradually decreasing amplitude. The purpose of the present study was to process sleep spindles with Independent Component Analysis (ICA) in order to investigate the possibility of extracting, through visual analysis of the spindle EEG and visual selection of Independent Components (ICs), spindle “components” (SCs) corresponding to separate EEG activity patterns during a spindle, and to investigate the intracranial current sources underlying these SCs. Current source analysis using Low-Resolution Brain Electromagnetic Tomography (LORETA) was applied to the original and the ICA-reconstructed EEGs. Results indicated that SCs can be extracted by reconstructing the EEG through back-projection of separate groups of ICs, based on a temporal and spectral analysis of ICs. The intracranial current sources related to the SCs were found to be spatially stable during the time evolution of the sleep spindles.

Independent Component Analysis and Neural Networks Applied for Classification of Malignant, Benign and Normal Tissue in Digital Mammography

2007 ◽  
Vol 46 (02) ◽  
pp. 212-215 ◽  
Author(s):  
L. F. Campos ◽  
A. Silva ◽  
A. Barros
Keyword(s):  
Independent Component Analysis ◽  
Early Cancer ◽  
Component Analysis ◽  
Independent Component ◽  
Classification Rate ◽  
Normal Tissues ◽  
Early Cancer Diagnosis ◽  
Good Classification ◽  
Selection Of

Summary Objectives : This paper proposes an efficient method for the discrimination and classification of mammograms with benign, malignant and normal tissues. Methods : The proposed method consists of selection of tissues, feature extraction using independent component analysis, feature selection by the foiward- selection technique and classification of the tissue by the multilayer perceptron. Results : The method is tested for a mammogram set of the MIAS database, resulting in a 97.83% success rate, with 98.0% specificity and 97.5% sensitivity. Conclusion : The proposed method showed a good classification rate. The method will be useful for early cancer diagnosis.

Sign in / Sign up

Export Citation Format

Share Document