An Efficient Seizure detection from EEG Signals Using Machine Learning Algorithms
DOI:
https://doi.org/10.63682/jns.v14i31S.7060Keywords:
N\AAbstract
In order to provide care and intervention to patients with epilepsy, the detection and classification of epileptic seizures using EEG signals is an important task in medical diagnosis. In this study, the use of deep learning techniques to classify seizure disorders from EEG signals is investigated, specifically using two pseudo convolutional neural network (CNN) architectures: VGG and LeNet. The plan will involve preprocessing raw EEG data to extract relevant features and then feeding these features into deep learning models. VGG, known for its deep learning models, and LeNet, a simple but effective approach, are evaluated for their ability to detect seizure events. The architecture of the book is designed to address the special challenges of EEGsignalclassification,includingnoiseand variability in various types of epilepsy. The results of this study demonstrate the potential ofCNNbasedmodelstoimprovetheaccuracy and performance of epilepsy diagnosis, providing valuable information for the development of automated medical systems
Downloads
Metrics
References
L. Hussain, W.Aziz,A. S. Khan,A. Q.Abbasi, and S. Z. Hassan, Classification of electroencephlography(EEG)alcoholicandcontrol subjectsusingmachinelearningensemble methods, J. Multidiscip. Eng. Sci. Technol., vol. 2, no. 1, pp. 126131, Jan. 2015.
A.Hamad,E.H.Houssein,A.E.Hassanien,and A. A. Fahmy, Feature extraction of epilepsy EEG using discrete wavelet transform, inProc.12th Int. Comput. Eng. Conf. (ICENCO), Dec. 2016, pp. 190195.
U.R.Acharya,S.VinithaSree,G.Swapna,R.J. Martis, and J. S. Suri, Automated EEG analysis of epilepsy:Areview,Knowl.-BasedSyst.,vol.45,pp. 147165, Jun. 2013.
P. Sarma, P. Tripathi, M. P. Sarma, and K. K. Sarma, Pre-processing and feature extraction techniques for EEGBCI applications-a review of recent research,ADBU J. Eng.Technol., vol. 5, no. 1, pp. 18, 2016.
C. Umale,A. Vaidya, S. Shirude, andA. Raut, Feature extraction techniques and classification algorithmsforEEGsignalstodetecthumanstress-a review, Int. J. Comput.Appl. Technol. Res., vol. 5, no. 1, pp. 814,Jan. 2016.
K. Polat and S. Güne , Artificial immune recognition system with fuzzy resource allocation mechanismclassifier,principalcomponentanalysis and FFT method based new hybrid automated identification system for classification of EEG signals, Expert Syst. Appl., vol. 34, no. 3,pp. 20392048, Apr. 2008.
O. Salem, A. Naseem, and A. Mehaoua, Epileptic seizure detection from EEG signal using discretewavelettransformandantcolonyclassifier, inProc.IEEEInt.Conf.Commun.(ICC),Jun.2014, pp.35293534.
S.A.Aljawarneh,V.Radhakrishna,andA. Cheruvu,VRKSHA:Anoveltreestructurefortime- proledtemporalassociationmining,inNeural ComputingandApplications.Cham,Switzerland: Springer,2017, pp. 129. [Online].Available: https://link.springer.com/article/10.1007%2Fs00521-018-3776-7
S. A. Aljawarneh, R. Vangipuram, V. K. Puligadda, and J. Vinjamuri, G-SPAMINE: An approach to discover temporal association pattern and trends in Internet of Things, Future Gener. Comput. Syst., vol. 74, pp. 430443, Sep. 2017.
V. Radhakrishna, S. A. Aljawarneh, P. VeereswaraKumar,andV.Janaki,ASTRAAnovel interest measure for unearthing latent temporal associations and trends through extending basic Gaussian membership function, Multimedia Tools Appl., vol. 78, no. 4, pp. 42174265, Feb. 2019.
V. Radhakrishna, S.A.Aljawarneh, V. Janaki, and P. Kumar, Looking into the possibility for designing normal distribution based dissimilarity measure to discover time pro led association patterns, in Proc. Int. Conf. Eng. MIS (ICEMIS), May 2017, pp. 15.
MD.Rashed-al-mahfuz,MohammadAliMoni, Shahadat Uddin, Salem A. Alyami, Matthew A. Summers, and ValsammaEapen, A Deep convolutional neural network method to detect seizures and characteristic frequencies using EpilepticElectroencephalogram(EEG)Data,vol.9, Jan 2021.
Mehdi Hosseinzadeh, ParisaKhoshvaght, Samira Sadeghi, ParvanehAsghari, AmirhosseinNorooziVarzeghani,andSang-WoongLee,AModel for Epileptic Seizure Diagnosis using the Combination ofEnsemble Learning and Deep learning, vol. 12, Oct. 2024.
Shasha Yuan, Jianwei Mu, Weidong Zhou, Ling-YunDai,Jin-XingLiu,JuanWang,andXiang Liu, Automatic Epileptic Seizure Detection Using Graph-Regularized Non-negative Matrix FactorizationandKernel-basedRobustProbabilistic Collaborative Representation, vol. 30, 2022.
Shufeng Liang, Xin Zhang, Hulin Zhao, Yuanyuan Dang, RuiHui, and Jianning Zhang, Double Discrete variationalAutoencoder for Epileptic EEG signals classification, vol. 12, Aug, 2024.
HepseebaKode, Khaled Elleithy, and LaialiAlmazaydeh, Epileptic Seizure Detection in EEG signalsUsingMachineLearningandDeepLearning techniques, vol. 12, June 2024.
ZhenxiSong,BinDeng,JiangWang,GuoshengYi,andWeiYue,EpilepticSeizureDetectionusing Brain-rhythmic Recurrence Biomarkers and ONASNet-based Transfer learning, vol. 30, 2022.
Manuel J. Rivera, Javier Sanchis, Oscar Corcho, Miguel A. Teruel, and Juan Trujillo, Evaluating CNN Methods for Epileptic Seizure Type classification using EEG data, vol 12, May 2024.
JianLian, Yan Zhang, RongLuo, Guoyong Han, WeikuanJia, and Chengjiang Li, Pair-wise MatchingofEEGsignalsforEpilepticIdentification via Convolutional Neural Network, vol. 8, March 2020.
T. Premavathi, Madhu Shukla, and RajendrasihnJadeja, Predicting Patient-specific Epileptic Seizures from Scalp EEG signals using KNN model with Transfer learning, vol. 12, Dec. 2024.
Tengzi Liu, Muhammad Zohaib Hassan Shah, Xucun Yan, and Dongping Yang, Unsupervised Feature Representation based on Deep Boltzmann Machine for Seizure Detection, vol. 31, 2023.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
