An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering

Medical experts employ electroencephalography (EEG) for analyzing the electrical activity in the brain to infer disorders. However, the time costs of human experts are very high, and the examination of EEGs by such experts, therefore, accounts for a plethora of medical resources. In this study, an i...

Full description

Saved in:
Bibliographic Details
Main Authors: Unmesh Shukla, Geetika Jain Saxena, Manish Kumar, Anil Singh Bafila, Amit Pundir, Sanjeev Singh
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9638672/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223093824782336
author Unmesh Shukla
Geetika Jain Saxena
Manish Kumar
Anil Singh Bafila
Amit Pundir
Sanjeev Singh
author_facet Unmesh Shukla
Geetika Jain Saxena
Manish Kumar
Anil Singh Bafila
Amit Pundir
Sanjeev Singh
author_sort Unmesh Shukla
collection DOAJ
description Medical experts employ electroencephalography (EEG) for analyzing the electrical activity in the brain to infer disorders. However, the time costs of human experts are very high, and the examination of EEGs by such experts, therefore, accounts for a plethora of medical resources. In this study, an improved one-dimensional CNN-only system of 25 layers has been proposed to identify abnormal and normal adult EEG signals using a single EEG montage without using any explicit feature extraction technique. Most of the previous systems based on deep learning, that have been proposed to solve this problem, use extremely deep architectures containing very large numbers of layers. This study also presents an independent preprocessing module that has been exhaustively evaluated for optimal parameters with the target of adult EEG signal classification. The achieved accuracy of the proposed classifier as a part of the decision support system is 82.24%, which is a substantial improvement of ~3% over the previous best reported classifier of comparable depth. The system also exhibits significantly higher F1-score and sensitivity as well as lower loss. The proposed system is intended to be a part of an expert system for overall brain health evaluation.
format Article
id doaj-art-69f6aad583e14f97b432e87a30a7c99e
institution Kabale University
issn 2169-3536
language English
publishDate 2021-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-69f6aad583e14f97b432e87a30a7c99e2025-08-25T23:11:19ZengIEEEIEEE Access2169-35362021-01-01916349216350310.1109/ACCESS.2021.31333269638672An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay FilteringUnmesh Shukla0https://orcid.org/0000-0001-6738-8933Geetika Jain Saxena1https://orcid.org/0000-0002-5828-8049Manish Kumar2Anil Singh Bafila3https://orcid.org/0000-0002-3392-2410Amit Pundir4Sanjeev Singh5https://orcid.org/0000-0002-2416-7011Institute of Informatics and Communication, University of Delhi South Campus, New Delhi, IndiaDepartment of Electronics, Maharaja Agrasen College, University of Delhi, New Delhi, IndiaSchool of Computer and Information Sciences, Indira Gandhi National Open University, New Delhi, IndiaInstitute of Informatics and Communication, University of Delhi South Campus, New Delhi, IndiaDepartment of Electronics, Maharaja Agrasen College, University of Delhi, New Delhi, IndiaInstitute of Informatics and Communication, University of Delhi South Campus, New Delhi, IndiaMedical experts employ electroencephalography (EEG) for analyzing the electrical activity in the brain to infer disorders. However, the time costs of human experts are very high, and the examination of EEGs by such experts, therefore, accounts for a plethora of medical resources. In this study, an improved one-dimensional CNN-only system of 25 layers has been proposed to identify abnormal and normal adult EEG signals using a single EEG montage without using any explicit feature extraction technique. Most of the previous systems based on deep learning, that have been proposed to solve this problem, use extremely deep architectures containing very large numbers of layers. This study also presents an independent preprocessing module that has been exhaustively evaluated for optimal parameters with the target of adult EEG signal classification. The achieved accuracy of the proposed classifier as a part of the decision support system is 82.24%, which is a substantial improvement of ~3% over the previous best reported classifier of comparable depth. The system also exhibits significantly higher F1-score and sensitivity as well as lower loss. The proposed system is intended to be a part of an expert system for overall brain health evaluation.https://ieeexplore.ieee.org/document/9638672/Electroencephalographymachine learningdecision support systemsconvolutional neural networksdata preprocessingSavitzky-Golay filtering
spellingShingle Unmesh Shukla
Geetika Jain Saxena
Manish Kumar
Anil Singh Bafila
Amit Pundir
Sanjeev Singh
An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering
IEEE Access
Electroencephalography
machine learning
decision support systems
convolutional neural networks
data preprocessing
Savitzky-Golay filtering
title An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering
title_full An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering
title_fullStr An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering
title_full_unstemmed An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering
title_short An Improved Decision Support System for Identification of Abnormal EEG Signals Using a 1D Convolutional Neural Network and Savitzky-Golay Filtering
title_sort improved decision support system for identification of abnormal eeg signals using a 1d convolutional neural network and savitzky golay filtering
topic Electroencephalography
machine learning
decision support systems
convolutional neural networks
data preprocessing
Savitzky-Golay filtering
url https://ieeexplore.ieee.org/document/9638672/
work_keys_str_mv AT unmeshshukla animproveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT geetikajainsaxena animproveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT manishkumar animproveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT anilsinghbafila animproveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT amitpundir animproveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT sanjeevsingh animproveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT unmeshshukla improveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT geetikajainsaxena improveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT manishkumar improveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT anilsinghbafila improveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT amitpundir improveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering
AT sanjeevsingh improveddecisionsupportsystemforidentificationofabnormaleegsignalsusinga1dconvolutionalneuralnetworkandsavitzkygolayfiltering