AccScience Publishing / IJOSI / Volume 7 / Issue 5 / DOI: 10.6977/IJoSI.202303_7(5).0004
Submit to IJOSI
Cite this article
1
Download
7
Citations
24
Views
Journal Browser
Volume | Year
Issue
Search
Forthcoming Issue
Current Issue
View All
News and Announcements
View All
ARTICLE

Robustified principal component analysis for feature selection in EEG signal classification

R. John Martin 1
Show Less
1 Jazan University, SA
IJOSI null , 7(5), 46–55; https://doi.org/10.6977/IJoSI.202303_7(5).0004
Submitted: 5 January 2022 | Revised: 19 December 2022 | Accepted: 5 January 2022 | Published: 19 December 2022
© by the Authors. Licensee AccScience Publishing, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Download PDF
Cite
XML
HTML
Abstract

Feature engineering is an important step in data analysis especially for machine learning applications. Wide range of feature selection methods are being used in EEG signal processing applications. Principal Component Analysis (PCA) is considered as an ideal method for feature selection whenever high dimensional data obtained. PCA is a method to identify patterns in data streams and reproduce them in a way to highlight their similarities with unique features. The proposed work exhibits how PCA is robustified for an Electroencephalography (EEG) signal processing application by applying kernel functions. Statistical features are extracted from EEG data after preprocessing by Desecrate Wavelet Transform (DWT). Initially PCA algorithm is applied for feature selection by reducing the dimensionality. Later the algorithm is robustified by applying Gaussian kernel in a nonlinear high dimensional feature space. The research work reports that the robustified PCA produce 0.7% elevated performance than traditional PCA in an EEG classification of epileptic seizure detection.

Keywords
PCA
Dimensionality Reduction
Electroencephalography (EEG)
Feature Engineering
Signal Processing
References
  1. Ahmad, Mohammad, Sarhan. (2017). A Low Complexity Algorithm for Epileptic Seizure Detection using Statistical Moments and Support Vector Machines. Biomedical Letters, 3(2), 79-86.
  2. Aminian, Masoud., Aminian, F., Schetino, L., and Ameli, A. (2010). Electroencephalogram (EEG) signal classification using neural networks with wavelet packet analysis, principal component analysis and data normalization as preprocessors. Proceedings of the 21st Midwest Artificial Intelligence and Cognitive Science Conference, MAICS 2010, 55-62.
  3. Benzy, V, K., and Jasmin, E, A. (2015). A Combined Wavelet and Neural Network Based Model for Classifying Depth of Anaesthesia. Procedia Computer Science, 46, 1610-1617.
  4. Bugli, C., and Lambert, P. (2007). Comparison between Principal Component Analysis and Independent Component Analysis in Electroencephalograms Modeling. Biometrical Journal, 49(2), 312-327.
  5. Cao, H., Wang, G., Sun, J., Deng, F., & Chen, J. (2022). Deep Contrastive Principal Component Analysis Adaptive to Nonlinear Data. IEEE Transactions on Signal Processing, 70, 5738–5750. https://doi.org/10.1109/tsp.2022.3224647
  6. Chenouri, S., Liang, J., and Small, C.G. (2015). Robust dimension redution. WIREs Comput Stat., 7, 63-69.
  7. Chunchu, Rambabu., and B, Rama, Murthy. (2014). EEG Signal with Feature Extraction using SVM and ICA Classifiers. International Journal of Computer Applications, 85(3), 0975–8887.
  8. Edras., Pacola., Veronica Quandt., Paulo Liberalesso., Sérgio Pichorim., Fábio, Schneider., and Humberto Gamba. (2017). A versatile EEG spike detector with multivariate matrix of features based on the linear discriminant analysis, combined wavelets, and descriptors. Pattern Recognition Letters, 86, 31-37.
  9. Elahi, Z., Boostani, R., and Motie, Nasrabadi, A. (2013). Estimation of hypnosis susceptibility based on electroencephalogram signal features. Scientia Iranica, 20(3), 730–737.
  10. Esma, Sezer., Isik, Hakan., and Saracoğlu, Esra. (2012). Employment and Comparison of Different Artificial Neural Networks for Epilepsy Diagnosis from EEG Signals. Journal of Medical Systems, 36,(1). 347–362.
  11. Gajic, D., Djurovic, Z., Di, Gennaro, S., and Fredrik, Gustafsso. (2014). Classification of EEG signals for detection of epileptic seizures based on wavelets and statistical pattern recognition. Biomedical Engineering: Applications, Basis and Communications, 26(2).
  12. Gajic, D., Djurovic, Z., Gligonjevic, J., Gennaro, S, D., Gajic, I, S. (2015). Detection of Epileptiform Activity in EEG Signals Based on Time-Frequency And Non-Linear Analysis. Front. Comput. Neurosci., 9, 38.
  13. Ghayab, HRA., Li, Y., Abdulla, S., Diykh, M., and Wan, X. (2016). Classification Of Epileptic EEG Signals Based On Simple Random Sampling And Sequential Feature Selection. Brain Informatics, 3(2), 85-91.
  14. Gopika, Gopan, K., Neelam, Sinha., and Dinesh, Babu, J. (2015). EEG Signal Classification In Non-Linear Framework With Filtered Training Data. IEEE 23rd European Signal Processing Conference (EUSIPCO), 624–628.
  15. Harikumar, R., and Sunil, Kumar, P. (2015). Dimensionality Reduction Techniques for Processing Epileptic Encephalographic Signals. Biomedical & Pharmacology Journal, 8(1), 103-106.
  16. Harikumar, R., and Sunil, Kumar, P. (2015). Principal Component Analysis as a Dimensionality Reduction Technique and Sparse Representation Classifier as a Post Classifier for the Classification of Epilepsy Risk Levels from EEG Signals. J. Pharm. Sci. & Res., 7(6), 282-284.
  17. Hashem, Kalbkhani., and Mahrokh, G, Shayesteh (2017). Stockwell transform for epileptic seizure detection from EEG signals. Biomedical Signal Processing and Control., 38, 108–118.
  18. Heydarpour, F., Abbasi, E., Ebadi, M. J., & Karbassi, S. M. (2020). Solving an Optimal Control Problem of Cancer Treatment by Artificial Neural Networks. International Journal of Interactive Multimedia and Artificial Intelligence, 6(4), 18. https://doi.org/10.9781/ijimai.2020.11.011
  19. Jihun, Ham., Daniel, D, Lee., Sebastian, Mika., and Bernhard, Schölkopf. (2004). A kernel view of the dimensionality reduction of manifolds. In Proceedings of the twenty-first international conference on Machine learning (ICML '04), ACM, NY, USA, 47.
  20. John, Martin, R., and Swapna, S, L. (2022). A Machine Learning Framework for Epileptic Seizure Detection by Analyzing EEG Signals. Int. J. Com. Dig. Sys., 11(1), 1383-1391.
  21. John, Martin, R., Sujatha, S., and Swapna, S,L. (2018). Multiresolution Analysis in EEG Signal Feature Engineering for Epileptic Seizure Detection. International Journal of Computer Applications, 180(17), 14-20.
  22. John, Martin, R., Swapna, S,L., and Sujatha, S. (2018). Adopting Machine Learning Models for Data Analytics-A Technical Note. International Journal of Computer Sciences and Engineering, 6(10), 360-365.
  23. John, Martin, R., Uttam, Sharma., Kiranjeet, Kaur., Noor Mohammed, Kadhim., Madonna, Lamin., Collins Sam, Ayipeh. (2022). Multi-Dimensional CNN Based Deep Segmentation Method for Tumor Identification. BioMed Research International. Hindawi. Article ID 5061112. Vol. 2022.
  24. Katayama, H., Mori, Y., & Kuroda, M. (2022). Variable Selection in Nonlinear Principal Component Analysis. Advances in Principal Component Analysis. https://doi.org/10.5772/intechopen.103758.
  25. Kavita, Mahajan., M, R, Vargantwar., and Sangita, M, Rajput.. (2011). Classification of EEG using PCA, ICA and Neural Network. International Conference in Computational Intelligence (ICCIA). Proceedings published in International Journal of Computer Applications® (IJCA).
  26. Li-Chen, Shi., Ruo-Nan, Duan., and Bao-Liang, Lu. (2013). A Robust Principal Component Analysis Algorithm for EEG-Based Vigilance Estimation. Conf. Proc IEEE Eng Med Biol Soc., 6623-6626.
  27. Manisha, Chandani., and Arun, Kumar. (2017). Classification of EEG Physiological Signal for the Detection of Epileptic Seizure by Using DWT Feature Extraction and Neural Network. American Journal of Information Management, 2(3), 37-42.
  28. Ming-ai, Li., Xin-yong, Luo., and Jin-fu, Yang. (2016). Extracting the nonlinear features of motor imagery EEG using parametric t-SNE. Neurocomputing, 218, C, 371–381.
  29. Ozan, Kocadagl.,i and Reza, Langari.. (2017). Classification of EEG signals for epileptic seizures using hybrid artificial neural networks based wavelet transforms and fuzzy relations. Expert Systems with Applications, 88, 419-434.
  30. Paulo, Amorim., Thiago, Moraes., Dalton, Fazanaro., Jorge, Silva., and Helio, Pedrini. (2017). Electroencephalogram signal classification based on shearlet and contourlet transforms. Expert Systems with Applications, 67, 140-147.
  31. Rahiminasab, Atefeh, Peyman Tirandazi, M. J. Ebadi, Ali Ahmadian, and Mehdi Salimi. 2020. An Energy-Aware Method for Selecting Cluster Heads in Wireless Sensor Networks. Applied Sciences. 10(21), 7886.
  32. Rajendra, Acharya, U., Vinitha, Sree, S., Ang, Peng, Chuan, Alvin., and Jasjit, S, Suri. (2012). Use of principal Component Analysis for automatic classification of epileptic EEG activities in wavelet framework. Expert Systems with Applications, 39, 9072–9078.
  33. Sabeti, M.., Katebi, S, D., R, Boostani., and G, W, Price. (2011). A new approach for EEG signal classification of schizophrenic and control participants. Expert Systems with Applications, 38, 2063–2071.
  34. Satchidanada, Dehuri., Alok, Kumar, Jagadev., and Sung-Bae, Cho. (2013). Epileptic Seizure Identification from Electroencephalography Signal Using DE-RBFNs Ensemble. Procedia Computer Science, 23, 84-95.
  35. Schölkopf, Bernhard., Smola, Alex., and Müller, Klaus-Robert. (1998). Nonlinear component analysis as a kemel eigenvalue problem. Neural Comput., 10, 1299-1319.
  36. Sharmila., and Mahalakshmi, P. (2017). Wavelet-based feature extraction for classification of epileptic seizure EEG signal. Journal of Medical Engineering & Technology, 41(8).
  37. Siswandari, Noertjahjani., Adhi, Susanto., Risanuri, Hidayat., and Samekto, Wibowo. (2016). Ictal Epilepsy And Normal EEG Feature Extraction Based On PCA, KNN And SVM Classification. Journal of Theoretical and Applied Information Technology, 83(1).
  38. Trambaiolli, L, R.., N. Spolaôr., A, C, Lorena., R. Anghinah., J, R, Sato. (2017). Feature selection before EEG classification supports the diagnosis of Alzheimer’s disease. Clinical Neurophysiology, 128(10), 2058-2067.
  39. Wang, L., Xue, W., Li, Y., Luo, M., Huang, J., Cui, W., and Huang, C. (2017). Automatic Epileptic Seizure Detection in EEG Signals Using Multi-Domain Feature Extraction and Nonlinear Analysis. Entropy, 19(6).
  40. Williamson, JR., Bliss, DW., Browne, DW., and Narayanan, JT. (2012). Seizure prediction using EEG spatiotemporal correlation structure. Epilepsy Behav., 25(2),.230-238.
  41. Xiao-WeiWang., DanNie., and Bao-LiangLu. (2014). Emotional state classification from EEG data using machine learning approach. Neurocomputing, 129, 94–106.
  42. Xie, S., and Krishnan, S. (2011). Signal decomposition by multi-scale PCA and its applications to long-term EEG signal classification. The 2011 IEEE/ICME International Conference on Complex Medical Engineering. Harbin Heilongjiang, 532-537.
  43. Xie, S., and Krishnan, S. (2014). Dynamic Principal Component Analysis with Nonoverlapping Moving Window and Its Applications to Epileptic EEG Classification. Hindawi Scientific World Journal, 2014(6), 419308.
  44. Zarei, R., He, J., Siuly, S., and Zhang, Y. (2017). A PCA Aided Cross-Covariance Scheme For Discriminative Feature Extraction From EEG Signals. Comput Methods Programs Biomed, 146, 47-57.
Previous article in this issue
Share
Back to top
International Journal of Systematic Innovation, Electronic ISSN: 2077-8767 Print ISSN: 2077-7973, Published by AccScience Publishing
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here
Accept