|
|
Detection of EEG signals in normal and epileptic seizures with multiscale multifractal analysis approach via weighted horizontal visibility graph |
Lu Ma(马璐)1,2, Yan-Lin Ren(任彦霖)3, Ai-Jun He(何爱军)4, De-Qiang Cheng(程德强)1, and Xiao-Dong Yang(杨小冬)3,† |
1 School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China; 2 Suzhou Vocational and Technical College, Suzhou 234000, China; 3 School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China; 4 School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China |
|
|
Abstract Electroencephalogram (EEG) signals contain important information about the regulation of brain system. Thus, automatic detection of epilepsy by analyzing the characteristics obtained from EEG signals has important research implications in the field of clinical medicine. In this paper, the horizontal visibility graph (HVG) algorithm is used to map multifractal EEG signals into complex networks. Then, we study the structure of the networks and explore the nonlinear dynamics properties of the EEG signals inherited from these networks. In order to better describe complex brain behaviors, we use the angle between two connected nodes as the edge weight of the network and construct the weighted horizontal visibility graph (WHVG). In our studies, fractality and multifractality of WHVG are innovatively used to analyze the structure of related networks. However, these methods only analyze the reconstructed dynamical system in general characterizations, they are not sufficient to describe the complex behavior and cannot provide a comprehensive picture of the system. To this effect, we propose an improved multiscale multifractal analysis (MMA) for network, which extends the description of the network dynamics features by focusing on the relationship between the multifractality and the measured scale-free intervals. Furthermore, neural networks are applied to train the above-mentioned parameters for the classification and identification of three kinds of EEG signals, i.e., health, interictal phase, and ictal phase. By evaluating our experimental results, the classification accuracy is 99.0%, reflecting the effectiveness of the WHVG algorithm in extracting the potential dynamic characteristics of EEG signals.
|
Received: 17 January 2023
Revised: 07 June 2023
Accepted manuscript online: 20 June 2023
|
PACS:
|
05.10.-a
|
(Computational methods in statistical physics and nonlinear dynamics)
|
|
87.18.-h
|
(Biological complexity)
|
|
87.85.Ng
|
(Biological signal processing)
|
|
87.19.X-
|
(Diseases)
|
|
Fund: Project supported by the Xuzhou Key Research and Development Program (Social Development) (Grant No. KC21304) and the National Natural Science Foundation of China (Grant No. 61876186). |
Corresponding Authors:
Xiao-Dong Yang
E-mail: xyang@cumt.edu.cn
|
Cite this article:
Lu Ma(马璐), Yan-Lin Ren(任彦霖), Ai-Jun He(何爱军), De-Qiang Cheng(程德强), and Xiao-Dong Yang(杨小冬) Detection of EEG signals in normal and epileptic seizures with multiscale multifractal analysis approach via weighted horizontal visibility graph 2023 Chin. Phys. B 32 110506
|
[1] Geneva:World Health Organization 2019 Global Epilepsy Report Licence CC BY-NC-SA 3.0 IGO [2] Mei Z N, Zhao X, Chen H Y and Chen W 2018 Sensors 18 1720 [3] Samiee K, Kovacs P and Gabbouj M 2015 IEEE Trans. Biomed Eng. 62 541 [4] Kiymik M K 2005 Comput. Biol. Med. 35 603 [5] Kumar Y, Dewal M L and Anand R S 2014 Neurocomputing 133 271 [6] Sanchez M A, Castanon-Puga M, Aguilar L and Rodriguez-Diaz A 2018 Computer Science and Engineering-Theory and Applications (Springer) p. 167 [7] Azami H A, Fernandez and Escudero J 2017 Med. Biol. Eng. Comput. 55 2037 [8] Wang S, Chaovalitwongse W A and Wong S 2013 IEEE Transactions on Knowledge and Data Engineering 25 2854 [9] Shayegh F 2014 Computer Methods and Programs in Biomedicine 113 323 [10] Sikdar D, Roy R and Mahadevappa M 2018 Biomedical Signal Processing and Contro 41 264 [11] Lacasa L 2008 Proc. Natl. Acad. Sci. USA 105 4972 [12] Luque B 2009 Phys. Rev. E 80 046103 [13] Zou Y 2019 Phys. Rep. 787 1 [14] Zhu G, Li Y and Wen P 2014 Computer Methods and Programs in Biomedicine 115 64 [15] Bhaduri S and Ghosh D 2015 Clin. EEG Neurosci 46 218 [16] Supriya S 2016 IEEE Access 4 6554 [17] Mohammadpoory Z, Nasrolahzadeh M and Haddadnia J 2017 Seizure 50 202 [18] Song C, Havlin S and Makse H A 2005 Nature 433 392 [19] Yu Z G, Zhang H, Huang D W, Lin Y and Anh V 2016 J. Stat. Mech-Theorey E 3 033206 [20] Furuya S and Yakubo K 2011 Phys. Rev. E 84 036118 [21] Wang D L, Yu Z G and Anh V 2012 Chin. Phys. B 21 080504 [22] Liu J L, Yu Z G and Anh V 2015 Chaos 25 023103 [23] Tél T, Fülöp Á and Vicsek T 1989 Physica A 159 155 [24] Pavón-Domínguez P and Moreno-Pulido S 2020 Physica A 541 123670 [25] Pavon-Dominguez P and Moreno-Pulido S Chaos, Solitons and Fractals 156 111836 [26] Gieral towski J, Żebrowski J J and Baranowski R 2012 Phys. Rev. E 85 021915 [27] Andrzejak R.G 2001 Phys. Rev. E 64 061907 [28] Sidorov S, Faizliev A and Balash V 2018 IAENG Int. J. Appl. Math. 48 90 [29] Diykh M, Li Y and Wen P 2017 Expert Systems with Applications 90 87 [30] Song Y and Lió P 2010 Journal of Biomedical Science and Engineering 03 556 [31] Orhan U, Hekim M and Ozer M 2011 Expert Systems with Applications 38 13475 [32] Guo L 2011 Expert Systems with Applications 38 10425 [33] Martis R J 2012 Int. J. Neural Syst. 22 1250027 [34] Martis R J 2013 Int. J. Neural Syst. 23 1350023 [35] Kaya Y 2014 Appl. Math. Comput. 243 209 [36] Abdulhay E 2020 Pattern Recognition Letters 139 174 [37] Liu Y, Jiang B, Feng J, Hu J Z and Zhang H B 2021 Multimed Tools Appl. 80 30261 [38] Liu H 2022 Mathematical Biosciences and Engineering 19 624 |
No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|