Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jun 28:13:45.
doi: 10.3389/fninf.2019.00045. eCollection 2019.

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

Wessam Al-Salman  1   2 , Yan Li  1   3 , Peng Wen  1
Affiliations

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

Wessam Al-Salman et al. Front Neuroinform. .

Abstract

K-complexes identification is a challenging task in sleep research. The detection of k-complexes in electroencephalogram (EEG) signals based on visual inspection is time consuming, prone to errors, and requires well-trained knowledge. Many existing methods for k-complexes detection rely mainly on analyzing EEG signals in time and frequency domains. In this study, an efficient method is proposed to detect k-complexes from EEG signals based on fractal dimension (FD) of time frequency (T-F) images coupled with undirected graph features. Firstly, an EEG signal is partitioned into smaller segments using a sliding window technique. Each EEG segment is passed through a spectrogram of short time Fourier transform (STFT) to obtain the T-F images. Secondly, the box counting method is applied to each T-F image to discover the FDs in EEG signals. A vector of FD features are extracted from each T-F image and then mapped into an undirected graph. The structural properties of the graphs are used as the representative features of the original EEG signals for the input of a least square support vector machine (LS-SVM) classifier. Key graphic features are extracted from the undirected graphs. The extracted graph features are forwarded to the LS-SVM for classification. To investigate the classification ability of the proposed feature extraction combined with the LS-SVM classifier, the extracted features are also forwarded to a k-means classifier for comparison. The proposed method is compared with several existing k-complexes detection methods in which the same datasets were used. The findings of this study shows that the proposed method yields better classification results than other existing methods in the literature. An average accuracy of 97% for the detection of the k-complexes is obtained using the proposed method. The proposed method could lead to an efficient tool for the scoring of automatic sleep stages which could be useful for doctors and neurologists in the diagnosis and treatment of sleep disorders and for sleep research.

Keywords: box counting and time frequency images; electroencephalogram; fractal dimensions; k-complexes; structural undirected graph.

PubMed Disclaimer

Figures

FIGURE 1
FIGURE 1
Typical EEG signals of 30 s belonging to sleep stages for a subject: awake stage, N1, N2, S3, N4, and REM stage.
FIGURE 2
FIGURE 2
EEG signal examples: (A) with k-complexes events. (B) without k-complexes.
FIGURE 3
FIGURE 3
The methodology of the proposed method for k-complexes detection.
FIGURE 4
FIGURE 4
An example of segmenting an EEG signal into windows using a sliding window technique.
FIGURE 5
FIGURE 5
Time-Frequency Image of an EEG segment by the STFT: (A) with k-complexes events. (B) without k-complexes.
FIGURE 6
FIGURE 6
An illustration of the box counting algorithm to create the size and the numbers of boxes.
FIGURE 7
FIGURE 7
A vector of fractal dimension is mapped into an undirected graph.
FIGURE 8
FIGURE 8
A graphical diagram of feature extraction.
FIGURE 9
FIGURE 9
Classification accuracy based on individual graph features.
FIGURE 10
FIGURE 10
Mean and standard deviation of undirected graph features.
FIGURE 11
FIGURE 11
Performance comparisons by the proposed method using different window sizes.
FIGURE 12
FIGURE 12
Performance evaluation of the proposed approach using the LS-SVM classifier based on the ROC curve.
FIGURE 13
FIGURE 13
The performance comparison between the proposed method and the k-means classifier.
FIGURE 14
FIGURE 14
Comparison of the execution time among the proposed method and k-means.
FIGURE 15
FIGURE 15
The boxplot of the classification accuracy based on 6-fold cross validation for k-means classifier.
FIGURE 16
FIGURE 16
The boxplot of the classification accuracy based on 6-fold cross validation for LS-SVM classifier.
FIGURE 17
FIGURE 17
Performance comparison of the proposed method for k-complex detection using different assessment measures.
See this image and copyright information in PMC

References

    1. Al Ghayab H. R., Li Y., Abdulla S., Diykh M., Wan X. (2016). Classification of epileptic EEG signals based on simple random sampling and sequential feature selection. Brain Inform. 3 85–91. 10.1007/s40708-016-0039-1 - DOI - PMC - PubMed
    1. Ali Z., Elamvazuthi I., Alsulaiman M., Muhammad G. (2016). Detection of voice pathology using fractal dimension in a multiresolution analysis of normal and disordered speech signals. J. Med. Syst. 40:20. 10.1007/s10916-015-0392-2 - DOI - PubMed
    1. Al-Salman W., Li Y., Wen P. (2019). Detecting sleep spindles in EEGs using wavelet fourier analysis and statistical features. Biomed. Signal Process. Control 48 80–92. 10.1016/j.bspc.2018.10.004 - DOI
    1. Al-Salman W., Li Y., Wen P., Diykh M. (2018). An efficient approach for EEG sleep spindles detection based on fractal dimension coupled with time frequency image. Biomed. Signal Process. Control 41 210–221. 10.1016/j.bspc.2017.11.019 - DOI
    1. Amzica F., Steriade M. (2002). The functional significance of K-complexes. Sleep Med. Rev. 6 139–149. 10.1053/smrv.2001.0181 - DOI - PubMed