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


Sleep Spindle Detection and Prediction Using a Mixture of Time Series and Chaotic Features

Amin Hekmatmanesh, Mohammad Mikaeili, Khosrow Sadeghniiat-Haghighi, Huapeng Wu, Heikki Handroos, Radek Martinek, Homer Nazeran

DOI: 10.15598/aeee.v15i3.2174


Abstract

It is well established that sleep spindles (bursts of oscillatory brain electrical activity) are significant indicators of learning, memory and some disease states. Therefore, many attempts have been made to detect these hallmark patterns automatically. In this pilot investigation, we paid special attention to nonlinear chaotic features of EEG signals (in combination with linear features) to investigate the detection and prediction of sleep spindles. These nonlinear features included: Higuchi's, Katz's and Sevcik's Fractal Dimensions, as well as the Largest Lyapunov Exponent and Kolmogorov's Entropy. It was shown that the intensity map of various nonlinear features derived from the constructive interference of spindle signals could improve the detection of the sleep spindles. It was also observed that the prediction of sleep spindles could be facilitated by means of the analysis of these maps. Two well-known classifiers, namely the Multi-Layer Perceptron (MLP) and the K-Nearest Neighbor (KNN) were used to distinguish between spindle and non-spindle patterns. The MLP classifier produced a~high discriminative capacity (accuracy = 94.93%, sensitivity = 94.31% and specificity = 95.28%) with significant robustness (accuracy ranging from 91.33% to 94.93%, sensitivity varying from 91.20% to 94.31%, and specificity extending from 89.79% to 95.28%) in separating spindles from non-spindles. This classifier also generated the best results in predicting sleep spindles based on chaotic features. In addition, the MLP was used to find out the best time window for predicting the sleep spindles, with the experimental results reaching 97.96% accuracy.

Keywords


Chaotic features; discriminative capacity; fractal dimension; intensity map; sleep EEG; spindle.

Full Text:

PDF