Research Article
BibTex RIS Cite

Analyzing of EEG Signals with Deep Learning and Discrete Wavelet Transform

Year 2022, Issue: 35, 514 - 521, 07.05.2022
https://doi.org/10.31590/ejosat.953576

Abstract

In this study, the capability to study the effect of each feature on the accuracy of the classification, whereby in the mixture of features with the Convolutional Neural Networks (CNNs) to identify epilepsy seizure in EEGs was searched. The EEG signals were first analyzed within 5 subsignals at specific frequencies bands by using Discrete Wavelet Transforms (DWT) at 5 levels, and then features were extracted from each sub signal. Finally, there was convolutional neural network classification. The best classification accuracies obtained when extracted eight features from EEG signals 96.5%. That means these features are strong to catch epilepsy seizure. Usually, the smart methods could be utilized within a more broad range of identification model problems that are also relevant to humans, such as the epilepsy diseases discovery and judgment.

References

  • Siegelbaum, Steven A., A. James Hudspeth. Principles of neural science.In: Eds. Eric R. Kandel, James H. Schwartz, Thomas M. Jessell. editors .Vol. 4. New York: McGraw-hill, 2000. pp. 1227-1246.
  • Chen, Duo, Suiren Wan, Forrest Sheng Bao. Epileptic Focus Localization Using Discrete Wavelet Transform Based on Interictal Intracranial EEG. IEEE Trans-actions on Neural Systems and Rehabilitation Engineering 2016.
  • Riaz, F., Hassan, A., Rehman, S., Niazi, I. K., & Dremstrup, K. EMD-based tem-poral and spectral features for the classification of EEG signals using supervised learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2016; 24(1): 28-35.
  • Singh, Gurwinder, Manpreet Kaur, Dalwinder Singh. Detection of an epileptic seizure using wavelet transformation and spike based features.Recent Advances in Engineering & Computational Sciences (RECS) ; 2015. In: IEEE Interna-tional Conference ; 21 December 2015 ; USA: IEEE. pp.1- 4.
  • Abualsaud, K., Mahmuddin, M., Saleh, M., Mohamed, A. Ensemble classifier for epileptic seizure detection for imperfect EEG data. The Scientific World Journal; 2015
  • Kumar, Yatindra, M. L. Dewal, R. S. Anand. Epileptic seizures detection in EEG using DWT-based ApEn and Convolutional neural network. Signal, Image and Video Processing 2014; 8, no. 7: 1323-1334.
  • Nanthini, B. Suguna, B. Santhi. Different approaches to analyzing EEG signals for seizure detection. International Journal of Signal and Imaging Systems En-gineering 2015; 8.1-2 : 28-38.
  • Nunes, Thiago M., André LV Coelho, Clodoaldo AM Lima, João P. Papa, Victor Hugo C. de Albuquerque. EEG signal classification for epilepsy diagnosis via op-timum path forest–A systematic assessment. Neurocomputing 2014;136: 103-123.
  • Fathima, T., Bedeeuzzaman, M., Joseph, P. K. . Wavelet based features for clas-sification of normal, ictal and interictal EEG signals. Journal of Medical Imaging and Health Informatics 2013; 3(2): 301-305.
  • Omerhodzic, I., Avdakovic, S., Nuhanovic, A., Dizdarevic, K.. Energy distribu-tion of EEG signals: EEG signal wavelet-neural network classifier. arXiv preprint arXiv :1307.789 (2013).
  • Übeyli, Elif Derya. Combined neural network model employing wavelet coeffi-cients for EEG signals classification. Digital Signal Processing (2009); 19.2: 297-308.
  • Subasi, Abdulhamit. EEG signal classification using wavelet feature extraction and a mixture of expert model.Expert Systems with Applications (2007); 32.4: 1084-1093.
  • Mohseni, H. R., Maghsoudi, A., Kadbi, M. H., Hashemi, J., Ashourvan, A.. Au-tomatc Detection of Epileptic Seizure using Time-Frequency Distributions.In: Advances in Medical, Signal and Information Processing, 2006. MEDSIP 2006. IET 3rd International Conference;, 17-19 July 2006; Glasgow, UK : IET. pp. 1- 4.
  • Adeli, Hojjat, Samanwoy Ghosh-Dastidar, Nahid Dadmehr. A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epi-lepsy. IEEE Transactions on Biomedical Engineering Feb. 2007; 54.2: 205-211.
  • Merzagora, A. C., Bunce, S., Izzetoglu, M., Onaral, B. Wavelet analysis for EEG feature extraction in deception detection. In : Engineering in Medicine and Biol-ogy Society, 2006. EMBS'06. 28th Annual International Conference of the IEEE; 30 Aug.- 3 Sept. 2006; New York, NY, USA: IEEE. pp. 2434-2437.
  • Kalaivani, M., V. Kalaivani, and V. Anusuya Devi. "Analysis of EEG Signal for the Detection of Brain Abnormalities." at International Journal of Computer Applications® year (2014).
  • EEG time series data (Department of Epileptology University of Bonn). http:// www.meb.uni-bonn.de/epileptologie/science/physik/eegdata.html. (Accessed October 2016).
  • Hazarika, Neep, Jean Zhu Chen, Ah Chung Tsoi, and Alex Sergejew. Classifica-tion of EEG signals using the wavelet transform. Signal processing (1997); 59, no. 1 : 61-72.
  • Übeyli, Elif Derya. Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines. Computers in Biology and Medicine 2008 ; 38 , no. 1 : 14 - 22.
  • Daubechies, Ingrid. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory 1990 ; 36.5: 961-1005.
  • Soltani, Skander. On the use of the wavelet decomposition for time series predic-tion. Neurocomputing 2002; 48, no. 1: 267-277.
  • Akay, Metin. Wavelet applications in medicine. IEEE spectrum May 1997; 34, no. 5: 50-56.
  • Unser, M., Aldroubi, A. (1996). A review of wavelets in biomedical applica-tions. Proceedings of the IEEE 1996 , 84(4) : 626-638.
  • Wu, Yi-Leh, Divyakant Agrawal, and Amr El Abbadi. A comparison of DFT and DWT based similarity search in time-series databases. In :Proceedings of the ninth international conference on Information and knowledge management; November 06 - 11 2000 ; McLean, Virginia, USA: ACM. pp.488 -495.
  • Karpathy, Andrej. “Convolutional Neural Networks (CNNs/ConvNets).” CS231n Convolutional Neural Networks for Visual Recognition, Stanford University, 2019, cs231n.github.io/convolutional-networks/.
  • Britz, Denny. “Recurrent Neural Networks Tutorial, Part 1 - Introductions to RNNs.” WILDML, 17 Sept. 2015, www.wildml.com/2015/09/recurrent-neuralnetworks-tutorial-part-1-introduction-to-rnns/.

Analyzing of EEG Signals with Deep Learning and Discrete Wavelet Transform

Year 2022, Issue: 35, 514 - 521, 07.05.2022
https://doi.org/10.31590/ejosat.953576

Abstract

In this study, the capability to study the effect of each feature on the accuracy of the classification, whereby in the mixture of features with the Convolutional Neural Networks (CNNs) to identify epilepsy seizure in EEGs was searched. The EEG signals were first analyzed within 5 subsignals at specific frequencies bands by using Discrete Wavelet Transforms (DWT) at 5 levels, and then features were extracted from each sub signal. Finally, there was convolutional neural network classification. The best classification accuracies obtained when extracted eight features from EEG signals 96.5%. That means these features are strong to catch epilepsy seizure. Usually, the smart methods could be utilized within a more broad range of identification model problems that are also relevant to humans, such as the epilepsy diseases discovery and judgment.

References

  • Siegelbaum, Steven A., A. James Hudspeth. Principles of neural science.In: Eds. Eric R. Kandel, James H. Schwartz, Thomas M. Jessell. editors .Vol. 4. New York: McGraw-hill, 2000. pp. 1227-1246.
  • Chen, Duo, Suiren Wan, Forrest Sheng Bao. Epileptic Focus Localization Using Discrete Wavelet Transform Based on Interictal Intracranial EEG. IEEE Trans-actions on Neural Systems and Rehabilitation Engineering 2016.
  • Riaz, F., Hassan, A., Rehman, S., Niazi, I. K., & Dremstrup, K. EMD-based tem-poral and spectral features for the classification of EEG signals using supervised learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2016; 24(1): 28-35.
  • Singh, Gurwinder, Manpreet Kaur, Dalwinder Singh. Detection of an epileptic seizure using wavelet transformation and spike based features.Recent Advances in Engineering & Computational Sciences (RECS) ; 2015. In: IEEE Interna-tional Conference ; 21 December 2015 ; USA: IEEE. pp.1- 4.
  • Abualsaud, K., Mahmuddin, M., Saleh, M., Mohamed, A. Ensemble classifier for epileptic seizure detection for imperfect EEG data. The Scientific World Journal; 2015
  • Kumar, Yatindra, M. L. Dewal, R. S. Anand. Epileptic seizures detection in EEG using DWT-based ApEn and Convolutional neural network. Signal, Image and Video Processing 2014; 8, no. 7: 1323-1334.
  • Nanthini, B. Suguna, B. Santhi. Different approaches to analyzing EEG signals for seizure detection. International Journal of Signal and Imaging Systems En-gineering 2015; 8.1-2 : 28-38.
  • Nunes, Thiago M., André LV Coelho, Clodoaldo AM Lima, João P. Papa, Victor Hugo C. de Albuquerque. EEG signal classification for epilepsy diagnosis via op-timum path forest–A systematic assessment. Neurocomputing 2014;136: 103-123.
  • Fathima, T., Bedeeuzzaman, M., Joseph, P. K. . Wavelet based features for clas-sification of normal, ictal and interictal EEG signals. Journal of Medical Imaging and Health Informatics 2013; 3(2): 301-305.
  • Omerhodzic, I., Avdakovic, S., Nuhanovic, A., Dizdarevic, K.. Energy distribu-tion of EEG signals: EEG signal wavelet-neural network classifier. arXiv preprint arXiv :1307.789 (2013).
  • Übeyli, Elif Derya. Combined neural network model employing wavelet coeffi-cients for EEG signals classification. Digital Signal Processing (2009); 19.2: 297-308.
  • Subasi, Abdulhamit. EEG signal classification using wavelet feature extraction and a mixture of expert model.Expert Systems with Applications (2007); 32.4: 1084-1093.
  • Mohseni, H. R., Maghsoudi, A., Kadbi, M. H., Hashemi, J., Ashourvan, A.. Au-tomatc Detection of Epileptic Seizure using Time-Frequency Distributions.In: Advances in Medical, Signal and Information Processing, 2006. MEDSIP 2006. IET 3rd International Conference;, 17-19 July 2006; Glasgow, UK : IET. pp. 1- 4.
  • Adeli, Hojjat, Samanwoy Ghosh-Dastidar, Nahid Dadmehr. A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epi-lepsy. IEEE Transactions on Biomedical Engineering Feb. 2007; 54.2: 205-211.
  • Merzagora, A. C., Bunce, S., Izzetoglu, M., Onaral, B. Wavelet analysis for EEG feature extraction in deception detection. In : Engineering in Medicine and Biol-ogy Society, 2006. EMBS'06. 28th Annual International Conference of the IEEE; 30 Aug.- 3 Sept. 2006; New York, NY, USA: IEEE. pp. 2434-2437.
  • Kalaivani, M., V. Kalaivani, and V. Anusuya Devi. "Analysis of EEG Signal for the Detection of Brain Abnormalities." at International Journal of Computer Applications® year (2014).
  • EEG time series data (Department of Epileptology University of Bonn). http:// www.meb.uni-bonn.de/epileptologie/science/physik/eegdata.html. (Accessed October 2016).
  • Hazarika, Neep, Jean Zhu Chen, Ah Chung Tsoi, and Alex Sergejew. Classifica-tion of EEG signals using the wavelet transform. Signal processing (1997); 59, no. 1 : 61-72.
  • Übeyli, Elif Derya. Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines. Computers in Biology and Medicine 2008 ; 38 , no. 1 : 14 - 22.
  • Daubechies, Ingrid. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory 1990 ; 36.5: 961-1005.
  • Soltani, Skander. On the use of the wavelet decomposition for time series predic-tion. Neurocomputing 2002; 48, no. 1: 267-277.
  • Akay, Metin. Wavelet applications in medicine. IEEE spectrum May 1997; 34, no. 5: 50-56.
  • Unser, M., Aldroubi, A. (1996). A review of wavelets in biomedical applica-tions. Proceedings of the IEEE 1996 , 84(4) : 626-638.
  • Wu, Yi-Leh, Divyakant Agrawal, and Amr El Abbadi. A comparison of DFT and DWT based similarity search in time-series databases. In :Proceedings of the ninth international conference on Information and knowledge management; November 06 - 11 2000 ; McLean, Virginia, USA: ACM. pp.488 -495.
  • Karpathy, Andrej. “Convolutional Neural Networks (CNNs/ConvNets).” CS231n Convolutional Neural Networks for Visual Recognition, Stanford University, 2019, cs231n.github.io/convolutional-networks/.
  • Britz, Denny. “Recurrent Neural Networks Tutorial, Part 1 - Introductions to RNNs.” WILDML, 17 Sept. 2015, www.wildml.com/2015/09/recurrent-neuralnetworks-tutorial-part-1-introduction-to-rnns/.
There are 26 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Khaled Abukhettala 0000-0003-2554-9350

Oğuz Ata 0000-0003-2554-9350

Publication Date May 7, 2022
Published in Issue Year 2022 Issue: 35

Cite

APA Abukhettala, K., & Ata, O. (2022). Analyzing of EEG Signals with Deep Learning and Discrete Wavelet Transform. Avrupa Bilim Ve Teknoloji Dergisi(35), 514-521. https://doi.org/10.31590/ejosat.953576