Search results

Filters

  • Journals
  • Date

Search results

Number of results: 2
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

EEG signal-based sleep stage classification facilitates an initial diagnosis of sleep disorders. The aim of this study was to compare the efficiency of three methods for feature extraction: power spectral density (PSD), discrete wavelet transform (DWT) and empirical mode decomposition (EMD) in the automatic classification of sleep stages by an artificial neural network (ANN). 13650 30-second EEG epochs from the PhysioNet database, representing five sleep stages (W, N1-N3 and REM), were transformed into feature vectors using the aforementioned methods and principal component analysis (PCA). Three feed-forward ANNs with the same optimal structure (12 input neurons, 23 + 22 neurons in two hidden layers and 5 output neurons) were trained using three sets of features, obtained with one of the compared methods each. Calculating PSD from EEG epochs in frequency sub-bands corresponding to the brain waves (81.1% accuracy for the testing set, comparing with 74.2% for DWT and 57.6% for EMD) appeared to be the most effective feature extraction method in the analysed problem.

Go to article

Authors and Affiliations

Monika Prucnal
Adam G. Polak
Download PDF Download RIS Download Bibtex

Abstract

Studies of noise properties of thick-film conducting lines from Au or PdAg conductive pastes on LTCC or alumina substrates are reported. Experiments have been carried out at the room temperature on samples prepared in the form of meanders by traditional screen-printing or laser-shaping technique. Due to a low resistance of the devices under test (DUTs), low-frequency noise spectra have been measured for the dc-biased samples arranged in a bridge configuration, transformer-coupled to a low-noise amplifier. The detailed analysis of noise sources in the signal path and its transfer function, including the transformer, has been carried out, and a procedure for measurement setup self-calibration has been described. The 1/f noise component originating from resistance fluctuations has been found to be dominant in all DUTs. The analysis of experimental data leads to the conclusion that noise is produced in the bends of meanders rather than in their straight segments. It occurs that noise of Au-based laser-shaped lines is significantly smaller than screen-printed ones. PdAg lines have been found more resistive but simultaneously less noisy than Au-based lines.
Go to article

Authors and Affiliations

Adam Witold Stadler
Andrzej Kolek
Krzysztof Mleczko
Zbigniew Zawiślak
Andrzej Dziedzic
Damian Nowak

This page uses 'cookies'. Learn more