A novel and efficient multi-scale feature extraction method for EEG classification

Ziling Lu; Jian Wang; Ziling Lu; Jian Wang

doi:10.3934/math.2024805

AIMS Mathematics

2024, Volume 9, Issue 6: 16605-16622. doi: 10.3934/math.2024805

Previous Article Next Article

Research article Special Issues

A novel and efficient multi-scale feature extraction method for EEG classification

Ziling Lu ¹,
Jian Wang ^{2,3,4
,
,}

1.
School of Teacher Education, Nanjing University of Information Science and Technology, Nanjing, 210044, China
2.
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing, 210044, China
3.
Jiangsu International Joint Laboratory on System Modeling and Data Analysis, Nanjing University of Information Science and Technology, Nanjing 210044, China
4.
Center for Applied Mathematics of Jiangsu Province, Nanjing University of Information Science and Technology, Nanjing 210044, China

Received: 08 March 2024 Revised: 15 April 2024 Accepted: 22 April 2024 Published: 13 May 2024
MSC : 92C55, 68U35

Electroencephalography (EEG) is essential for diagnosing neurological disorders such as epilepsy. This paper introduces a novel approach that employs the Allen-Cahn (AC) energy function for the extraction of nonlinear features. Drawing on the concept of multifractals, this method facilitates the acquisition of features across multi-scale. Features extracted by our method are combined with a support vector machine (SVM) to create the AC-SVM classifier. By incorporating additional measures such as Kolmogorov complexity, Shannon entropy, and Higuchi's Hurst exponent, we further developed the AC-MC-SVM classifier. Both classifiers demonstrate excellent performance in classifying epilepsy conditions. The AC-SVM classifier achieves 89.97% accuracy, 94.17% sensitivity, and 89.95% specificity, while the AC-MC-SVM reaches 97.19%, 97.96%, and 94.61%, respectively. Furthermore, our proposed method significantly reduces computational costs and demonstrates substantial potential as a tool for analyzing medical signals.
- Allen-Cahn energy function,
- EEG,
- multi-scale,
- epilepsy diagnosis,
- biosignal classification
Citation: Ziling Lu, Jian Wang. A novel and efficient multi-scale feature extraction method for EEG classification[J]. AIMS Mathematics, 2024, 9(6): 16605-16622. doi: 10.3934/math.2024805

Related Papers:

Abstract

Electroencephalography (EEG) is essential for diagnosing neurological disorders such as epilepsy. This paper introduces a novel approach that employs the Allen-Cahn (AC) energy function for the extraction of nonlinear features. Drawing on the concept of multifractals, this method facilitates the acquisition of features across multi-scale. Features extracted by our method are combined with a support vector machine (SVM) to create the AC-SVM classifier. By incorporating additional measures such as Kolmogorov complexity, Shannon entropy, and Higuchi's Hurst exponent, we further developed the AC-MC-SVM classifier. Both classifiers demonstrate excellent performance in classifying epilepsy conditions. The AC-SVM classifier achieves 89.97% accuracy, 94.17% sensitivity, and 89.95% specificity, while the AC-MC-SVM reaches 97.19%, 97.96%, and 94.61%, respectively. Furthermore, our proposed method significantly reduces computational costs and demonstrates substantial potential as a tool for analyzing medical signals.

References

[1]	M. X. Cohen, Where does EEG come from and what does it mean, Trends Neurosci., 40 (2017), 208–218. https://doi.org/10.1016/j.tins.2017.02.004 doi: 10.1016/j.tins.2017.02.004
[2]	M. R. Nuwer, D. A. Hovda, L. M. Schrader, P. M. Vespa, Routine and quantitative EEG in mild traumatic brain injury, Clin. Neurophysiol, 116 (2005), 2001–2025. https://doi.org/10.1016/j.clinph.2005.05.008 doi: 10.1016/j.clinph.2005.05.008
[3]	R. W. Thatcher, D. M. North, R. T. Curtin, R. A. Walker, C. J. Biver, J. F. Gomez, et al., An EEG severity index of traumatic brain injury, J. Neuropsych. Clin. N., 13 (2001), 77–87. https://doi.org/10.1176/appi.neuropsych.13.1.77 doi: 10.1176/appi.neuropsych.13.1.77
[4]	R. Silipo, G. Deco, H. Bartsch, Brain tumor classification based on EEG hidden dynamics, Intell. Data Anal., 3 (1999), 287–306. https://doi.org/10.3233/IDA-1999-3404 doi: 10.3233/IDA-1999-3404
[5]	V. S. Selvam, S. S. Devi, Analysis of spectral features of EEG signal in brain tumor condition, Meas. Sci. Rev., 15 (2015), 219–225. https://doi.org/10.1515/msr-2015-0030 doi: 10.1515/msr-2015-0030
[6]	S. J. M. Smith, EEG in the diagnosis, classification and management of patients with epilepsy, J. Neuro. Neurosur. Ps., 76 (2005), ii2–ii7. https://doi.org/10.1136/jnnp.2005.069245 doi: 10.1136/jnnp.2005.069245
[7]	S. Kiranyaz, T. Ince, M. Zabihi, D. Ince, Automated patient-specific classification of long-term electroencephalography, J. Biomed. Inform., 49 (2014), 16–31. https://doi.org/10.1016/j.jbi.2014.02.005 doi: 10.1016/j.jbi.2014.02.005
[8]	L. Cui, S. S. Sahoo, S. D. Lhatoo, G. Garg, P. Rai, A. Bozorgi, et al., Complex epilepsy phenotype extraction from narrative clinical discharge summaries, J. Biomed. Inform., 51 (2014), 272–279. https://doi.org/10.1016/j.jbi.2014.06.006 doi: 10.1016/j.jbi.2014.06.006
[9]	R. G. Andrzejak, K. Lehnertz, F. Mormann, C. Rieke, P. David, C. E. Elger, Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state, Phys. Rev. E, 64 (2001), 061907. https://doi.org/10.1103/PhysRevE.64.061907 doi: 10.1103/PhysRevE.64.061907
[10]	World health organization, 2023. Available from: https://www.who.int/en/news-room/fact-sheets/detail/epilepsy.
[11]	D. Buck, G. A. Baker, A. Jacoby, D. F. Smith, D. W. Chadwick, Patients' experiences of injury as a result of epilepsy, Epilepsia, 38 (1997), 439–444. https://doi.org/10.1111/j.1528-1157.1997.tb01733.x doi: 10.1111/j.1528-1157.1997.tb01733.x
[12]	Y. Alotaibi, V. A. Veera, Electroencephalogram based face emotion recognition using multimodal fusion and 1-D convolution neural network (ID-CNN) classifier, AIMS Math., 8 (2023), 22984–23002. https://doi.org/10.3934/math.20231169 doi: 10.3934/math.20231169
[13]	A. M. Roy, Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain-computer interface, Eng. Appl. Artif. Intel., 116 (2022), 105347. https://doi.org/10.1016/j.engappai.2022.105347 doi: 10.1016/j.engappai.2022.105347
[14]	A. M. Roy, A multi-scale fusion CNN model based on adaptive transfer learning for multi-class MI-classification in BCI system, BioRxiv, 2022. https://doi.org/10.1101/2022.03.17.481909
[15]	S. Liu, X. Wang, L. Zhao, J. Zhao, Q. Xin, S. H. Wang, Subject-independent emotion recognition of EEG signal based on dynamic empirical convolutional neural network, IEEE ACM T. Comput. Bi., 18 (2020), 1710–1721. https://doi.org/10.1109/TCBB.2020.3018137 doi: 10.1109/TCBB.2020.3018137
[16]	H. Altaheri, G. Muhammad, M. Alsulaiman, M. Amin, S. U. Altuwaijri, G. A. Abdul, et al., Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: A review, Neural Comput. Appl., 35 (2023), 14681–14722. https://doi.org/10.1007/s00521-021-06352-5 doi: 10.1007/s00521-021-06352-5
[17]	V. Bajaj, R. B. Pachori, Classification of seizure and nonseizure EEG signal using empirical mode decomposition, IEEE T. Inf. Technol. B., 16 (2011), 1135–1142. https://doi.org/10.1109/TITB.2011.2181403 doi: 10.1109/TITB.2011.2181403
[18]	Q. Xin, S. Hu, S. Liu, L. Zhao, S. Wang, WTRPNet: An explainable graph feature convolutional neural network for epileptic EEG classification, ACM T. Multim. Comput., 17 (2021), 1–18. https://doi.org/10.1145/3460522 doi: 10.1145/3460522
[19]	A. Akan, H. S. Ture, Classification of epileptic and psychogenic nonepileptic seizures via time-frequency features of EEG data, Int. J. Neural Syst., 2023. https://doi.org/10.1142/S0129065723500454
[20]	U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, H. Adeli, Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signal, Comput. Biol. Med., 100 (2018), 270–278. https://doi.org/10.1016/j.cmpb.2018.04.012 doi: 10.1016/j.cmpb.2018.04.012
[21]	Q. Xin, S. Hu, S. Liu, L. Zhao, Y. D. Zhang, An attention-based wavelet convolution neural network for epilepsy EEG classification, IEEE T. Neur. Sys. Reh., 30 (2022), 957–966. https://doi.org/10.1016/j.cej.2019.123775 doi: 10.1016/j.cej.2019.123775
[22]	A. M. Roy, An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces, Biomed. Signal Proces., 74 (2022) 103496. https://doi.org/10.1016/j.bspc.2022.103496
[23]	D. Zhang, L. Yao, K. Chen, J. Monaghan, A convolutional recurrent attention model for subject-independent EEG signal analysis, IEEE Signal Proc. Let., 26 (2019), 715–719. https://doi.org/10.1109/LSP.2019.2906824 doi: 10.1109/LSP.2019.2906824
[24]	T. Dissanayake, T. Fernando, S. Denman, S. Sridharan, C. Fookes, Geometric deep learning for subject independent epileptic seizure prediction using scalp EEG signal, IEEE J. Biomed. Health, 26 (2021), 527–538. https://doi.org/10.1109/JBHI.2021.3100297 doi: 10.1109/JBHI.2021.3100297
[25]	M. Qiyas, M. Naeem, N. Khan, Fractional orthotriple fuzzy Choquet-Frank aggregation operators and their application in optimal selection for EEG of depression patients, AIMS Math., 8 (2023), 6323–6355. https://doi.org/10.3934/math.2023320 doi: 10.3934/math.2023320
[26]	S. Siuly, Y. Li, Y. Zhang, EEG signal analysis and classification, IEEE T. Neur. Sys. Reh., 11 (2016), 141–144. https://doi.org/10.1007/978-3-319-47653-7 doi: 10.1007/978-3-319-47653-7
[27]	A. Craik, Y. He, J. L. C. Vidal, Deep learning for electroencephalogram (EEG), classification tasks: A review, J. Neural Eng., 16 (2019). https://doi.org/10.1088/1741-2552/ab0ab5
[28]	T. Mondéjar, R. Hervás, E. Johnson, C. Gutierrez, J. M. Latorre, Correlation between videogame mechanics and executive functions through EEG analysis, J. Biomed. Inform., 63 (2016), 131–140. https://doi.org/10.1016/j.jbi.2016.08.006 doi: 10.1016/j.jbi.2016.08.006
[29]	D. Zhang, K. Chen, D. Jian, L. Yao, Motor imagery classification via temporal attention cues of graph embedded EEG signals, IEEE J. Biomed. Health, 24 (2020). https://doi.org/10.1109/JBHI.2020.2967128
[30]	Q. Yuan, W. Zhou, S. Li, D. Cai, Epileptic EEG classification based on extreme learning machine and nonlinear features, Epilepsy Res., 96 (2011), 29–38. https://doi.org/10.1016/j.eplepsyres.2011.04.013 doi: 10.1016/j.eplepsyres.2011.04.013
[31]	Y. Zhang, Y. Guo, P. Yang, W. Chen, B. Lo, Epilepsy seizure prediction on EEG using common spatial pattern and convolutional neural network, IEEE J. Biomed. Health, 24 (2019), 465–474. https://doi.org/10.1109/JBHI.2019.2933046 doi: 10.1109/JBHI.2019.2933046
[32]	T. Tuncer, A new stable nonlinear textural feature extraction method based EEG signal classification method using substitution Box of the Hamsi hash function: Hamsi pattern, Appl. Acoust., 172 (2021), 107607. https://doi.org/10.1016/j.apacoust.2020.107607 doi: 10.1016/j.apacoust.2020.107607
[33]	P. K. Sethy, M. Panigrahi, K. Vijayakumar, S. K. Behera, Machine learning based classification of EEG signal for detection of child epileptic seizure without snipping, Int. J. Speech Technol., 26 (2023). https://doi.org/10.1007/s10772-021-09855-7
[34]	M. Varlı, H. Yılmaz, Multiple classification of EEG signal and epileptic seizure diagnosis with combined deep learning, J. Comput. Sci.-Neth., 67 (2023), 101943. https://doi.org/10.1016/j.jocs.2023.101943 doi: 10.1016/j.jocs.2023.101943
[35]	W. Chen, Y. Wang, Y. Ren, H. Jiang, G. Du, J. Zhang, et al., An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy, BMC. Med. Inform. Decis., 23 (2023), 96. https://doi.org/10.1186/s12911-023-02180-w doi: 10.1186/s12911-023-02180-w
[36]	L. Jiang, J. He, H. Pan, D. Wu, T. Jiang, J. Liu, Seizure detection algorithm based on improved functional brain network structure feature extraction, Biomed. Signal Proces., 79 (2023), 104053. https://doi.org/10.1016/j.bspc.2022.104053 doi: 10.1016/j.bspc.2022.104053
[37]	J. W. Kantelhardt, S. A. Zschiegner, E. K. Bunde, S. Havlin, A. Bunde, H. E. Stanley, Multifractal detrended fluctuation analysis of nonstationary time series, Physica A, 316 (2002), 81–91. https://doi.org/10.1016/S0378-4371(02)01383-3 doi: 10.1016/S0378-4371(02)01383-3
[38]	F. Wang, H. Wang, X. Zhou, R. Fu, A driving fatigue feature detection method based on multifractal theory, IEEE Sens. J., 22 (2022), 19046–19059. https://doi.org/10.1109/JSEN.2022.3201015 doi: 10.1109/JSEN.2022.3201015
[39]	V. Matic, P. J. Cherian, N. Koolen, A. H. Ansari, G. Naulaers, P. Govaert, et al., Objective differentiation of neonatal EEG background grades using detrended fluctuation analysis, Front. Hum. Neurosci., 9 (2015), 189. https://doi.org/10.3389/fnhum.2015.00189 doi: 10.3389/fnhum.2015.00189
[40]	T. Zorick, M. A. Mandelkern, Multifractal detrended fluctuation analysis of human EEG: Preliminary investigation and comparison with the wavelet transform modulus maxima technique, PLoS One, 8 (2013), e68360. https://doi.org/10.1371/journal.pone.0068360 doi: 10.1371/journal.pone.0068360
[41]	Z. Zhang, T. Wen, W. Huang, M. Wang, C. Li, Automatic epileptic seizure detection in EEGs using MF-DFA, SVM based on cloud computing, J. X-ray Sci. Technol., 25 (2017), 261–272. https://doi.org/10.3233/XST-17258 doi: 10.3233/XST-17258
[42]	J. Wang, W. Jiang, J. Kim, A novel ECG and EEG classification system based on nonlinear statistical features, Fractals, 31 (2023), 2350096. https://doi.org/10.1142/S0218348X23500962 doi: 10.1142/S0218348X23500962
[43]	J. Wang, H. Xu, J. Yang, J. Kim, Fractal feature analysis based on phase transitions of the Allen-Cahn and Cahn-Hilliard equations, J. Comput. Sci., 72 (2023), 102114. https://doi.org/10.1016/j.jocs.2023.102114 doi: 10.1016/j.jocs.2023.102114
[44]	S. M. Allen, J. W. Cahn, A microscopic theory for antiphase boundary motion and its application to antiphase domain coarsening, Acta. Metall., 27 (1979), 1085–1095. https://doi.org/10.1016/0001-6160(79)90196-2 doi: 10.1016/0001-6160(79)90196-2
[45]	J. Neumann, C. Schnörr, G. Steidl, Combined SVM-based feature selection and classification, Mach. Learn., 61 (2005), 129–150. https://doi.org/10.1007/s10994-005-1505-9 doi: 10.1007/s10994-005-1505-9
[46]	C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn., 20 (1995), 273–297. https://doi.org/10.1007/BF00994018
[47]	A. Kampouraki, G. Manis, C. Nikou, Heartbeat time series classification with support vector machines, IEEE T. Inf. Technol. Biomed., 13 (2008), 512–518. https://doi.org/10.1109/TITB.2008.2003323 doi: 10.1109/TITB.2008.2003323
[48]	C. S. Lo, C. M. Wang, Support vector machine for breast MR image classification, Comput. Math. Appl., 64 (2012), 1153–1162. https://doi.org/10.1016/j.camwa.2012.03.033 doi: 10.1016/j.camwa.2012.03.033
[49]	M. Varlı, H. Yılmaz, Multiple classification of EEG signal and epileptic seizure diagnosis with combined deep learning, J. Comput. Sci., 67 (2023), 101943. https://doi.org/10.1016/j.jocs.2023.101943 doi: 10.1016/j.jocs.2023.101943
[50]	C. E. Shannon, A mathematical theory of communication, Bell Syst. Tech. J., 27 (1948) 379–423. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
[51]	A. N. Kolmogorov, Combinatorial foundations of information theory and the calculus of probabilities, Russ. Math. Surv.+, 38 (1983), 29. https://doi.org/10.1070/RM1983v038n04ABEH004203 doi: 10.1070/RM1983v038n04ABEH004203
[52]	A. Lempel, J. Ziv, On the complexity of finite sequences, IEEE T. Inform. Theory, 22 (1976), 75–81. https://doi.org/10.1109/TIT.1976.1055501 doi: 10.1109/TIT.1976.1055501
[53]	T. Higuchi, Approach to an irregular time series on the basis of the fractal theory, Physica D, 31 (1988), 277–283. https://doi.org/10.1016/0167-2789(88)90081-4 doi: 10.1016/0167-2789(88)90081-4
[54]	U. R. Acharya, R. Yanti, J. W. Zheng, M. M. R. Krishnan, J. H. Tan, R. J. Martis, et al., Automated diagnosis of epilepsy using CWT, HOS and texture parameters, Int. J. Neural Syst., 23 (2013), 1350009. https://doi.org/10.1142/S0129065713500093 doi: 10.1142/S0129065713500093
[55]	Z. Brari, S. Belghith, A new algorithm for largest Lyapunov exponent determination for noisy chaotic signal studies with application to electroencephalographic signals analysis for epilepsy and epileptic seizures detection, Chaos Soliton. Fract., 165 (2022), 112757. https://doi.org/10.1016/j.chaos.2022.112757 doi: 10.1016/j.chaos.2022.112757
[56]	Ö. Türk, M. S. Özerdem, Epilepsy detection by using scalogram based convolutional neural network from EEG signal, Brain Sci., 9 (2019), 115. https://doi.org/10.3390/brainsci9050115 doi: 10.3390/brainsci9050115
[57]	R. Bajpai, R. Yuvaraj, A. A. Prince, Automated EEG pathology detection based on different convolutional neural network models: Deep learning approach, Comput. Biol. Med., 133 (2021), 104434. https://doi.org/10.1016/j.compbiomed.2021.104434 doi: 10.1016/j.compbiomed.2021.104434
[58]	M. Li, W. Chen, T. Zhang, Automatic epileptic EEG detection using DT-CWT-based non-linear features, Biomed. Signal Proces., 34 (2017), 114–125. https://doi.org/10.1016/j.bspc.2017.01.010 doi: 10.1016/j.bspc.2017.01.010

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)