Helpdesk

Top image

Editorial board

Darius Andriukaitis
Kaunas University of Technology, Lithuania

Alexander Argyros
The University of Sydney, Australia

Radu Arsinte
Technical University of Cluj Napoca, Romania

Ivan Baronak
Slovak University of Technology, Slovakia

Khosrow Behbehani
The University of Texas at Arlington, United States

Mohamed El Hachemi Benbouzid
University of Brest, France

Dalibor Biolek
University of Defence, Czech Republic

Klara Capova
University of Zilina, Slovakia

Erik Chromy
UPC Broadband Slovakia, Slovakia

Milan Dado
University of Zilina, Slovakia

Petr Drexler
Brno University of Technology, Czech Republic

Eva Gescheidtova
Brno University of Technology, Czech Republic

Ray-Guang Cheng
National Taiwan University of Science and Technology, Taiwan, Province of China

Gokhan Hakki Ilk
Ankara University, Turkey

Janusz Jezewski
Institute of Medical Technology and Equipment, Poland

Rene Kalus
VSB - Technical University of Ostrava, Czech Republic

Ivan Kasik
Academy of Sciences of the Czech Republic, Czech Republic

Jan Kohout
University of Defence, Czech Republic

Ondrej Krejcar
University of Hradec Kralove, Czech Republic

Miroslaw Luft
Technical University of Radom, Poland

Stanislav Marchevsky
Technical University of Kosice, Slovakia

Byung-Seo Kim
Hongik University, Korea

Valeriy Arkhin
Buryat State University, Russia

Rupak Kharel
University of Huddersfield, United Kingdom

Fayaz Hussain
Ton Duc Thang University, Vietnam

Peppino Fazio
Ca’ Foscari University of Venice, Italy

Fazel Mohammadi
University of New Haven, United States of America

Thang Trung Nguyen
Ton Duc Thang University, Vietnam

Le Anh Vu
Ton Duc Thang University, Vietnam

Miroslav Voznak
VSB - Technical University of Ostrava, Czech Republic

Zbigniew Leonowicz
Wroclaw University of Science and Technology, Poland

Wasiu Oyewole Popoola
The University of Edinburgh, United Kingdom

Yuriy S. Shmaliy
Guanajuato University, Mexico

Lorand Szabo
Technical University of Cluj Napoca, Romania

Tran Trung Duy
Posts and Telecommunications Institute of Technology, Ho Chi Minh City, Vietnam

Xingwang Li
Henan Polytechnic University, China

Huynh Van Van
Ton Duc Thang University, Vietnam

Lubos Rejfek
University of Pardubice, Czech Republic

Neeta Pandey
Delhi Technological University, India

Huynh The Thien
Ho Chi Minh City University of Technology and Education, Vietnam

Mauro Tropea
DIMES Department of University of Calabria, Italy

Gaojian Huang
Henan Polytechnic University, China

Nguyen Quang Sang
Ho Chi Minh City University of Transport, Vietnam

Anh-Tu Le
Ho Chi Minh City University of Transport, Vietnam

Phu Tran Tin
Ton Duc Thang University, Vietnam


Home Search Mail RSS


Comparative Analysis of the Discriminative Capacity of EEG, Two ECG-Derived and Respiratory Signals in Automatic Sleep Staging

Farideh Ebrahimi, Seyed Kamaledin Setarehdan, Radek Martinek, Homer Nazeran

DOI: 10.15598/aeee.v15i3.2182


Abstract

Highly accurate classification of sleep stages is possible based on EEG signals alone. However, reliable and high quality acquisition of these signals in the home environment is difficult. Instead, electrocardiogram (ECG) and Respiratory (Res) signals are easier to record and may offer a practical alternative for home monitoring of sleep. Therefore, automatic sleep staging was performed using ECG, Res (thoracic excursion) and EEG signals from 31 nocturnal recordings of the Sleep Heart Health Study (SHHS) polysomnography Database. Feature vectors were extracted from 0.5 min (standard) epochs of sleep data by time-domain, frequency domain, time-frequency and nonlinear methods and optimized by using the Support Vector Machine-Recursive Feature Elimination (SVM-RFE) method. These features were then classified by using a SVM. Classification based upon EEG features produced a Correct Classification Ratio CCR=0.92. In comparison, features derived from ECG signals alone, that is the combination of Heart Rate Variability (HRV), and ECG-Derived Respiration (EDR) signals produced a CCR=0.54, while those features based on the combination of HRV and (thoracic) Res signals resulted in a CCR=0.57. Overall comparison of the results based on standard epochs of EEG signals with those obtained from 5-minute (long) epochs of cardiorespiratory signals, revealed that acceptable CCR=0.81 and discriminative capacity (Accuracy=89.32%, Specificity=92.88% and Sensitivity=78.64%) were also achievable when using optimal feature sets derived from long epochs of the latter signals in sleep staging. In addition, it was observed that the presence of some artifacts (like bigeminy) in the cardiorespiratory signals reduced the accuracy of automatic sleep staging more than the artifacts that contaminated the EEG signals.

Keywords


Automatic sleep staging; ECG-derived respiration signals; Electroencephalogram (EEG) signal; Heart Rate Variability (HRV) signal; Res (thoracic excursion) signal.

Full Text:

PDF