Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques

Electroencephalogram (EEG) signal analysis plays a vital role in diagnosing and monitoring alcoholism, where accurate classification of individuals into alcoholic and control groups is essential. However, the inherent noise and complexity of EEG signals pose significant challenges. This study invest...

Full description

Saved in:
Bibliographic Details
Main Authors: Nidhi Patel, Jaiprakash Verma, Swati Jain
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Neuroinformatics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fninf.2025.1618050/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330104879022080
author Nidhi Patel
Jaiprakash Verma
Swati Jain
author_facet Nidhi Patel
Jaiprakash Verma
Swati Jain
author_sort Nidhi Patel
collection DOAJ
description Electroencephalogram (EEG) signal analysis plays a vital role in diagnosing and monitoring alcoholism, where accurate classification of individuals into alcoholic and control groups is essential. However, the inherent noise and complexity of EEG signals pose significant challenges. This study investigates the impact of three signal denoising techniques' Discrete Wavelet Transform(DWT), Discrete Fourier Transform(DFT), and Discrete Cosine Transform (DCT) Non EEG signal classification performance. The motivation behind this study is to identify the most effective preprocessing method for enhancing deep learning model performance in this domain. A novel DWT-CNN-BiGRU model is proposed, which leverages CNN layers for spatial feature extraction and BiGRU layers for capturing temporal dependencies. Experimental results show that the DWT-based approach, combined with standard scaling, achieves the highest accuracy of 94%, with a precision of 0.94, a recall of 0.95, and an F1-score of 0.94. Compared to the baseline DWT-CNN-BiLSTM model, the proposed method provides a modest yet meaningful improvement of approximately 17% in classification accuracy. These findings highlight the superiority of DWT as a preprocessing method and validate the proposed model's effectiveness for EEG-based classification, contributing to the development of more reliable medical diagnostic tools.
format Article
id doaj-art-1634261dd2fb495bb5a2f2a6687a8ae7
institution Kabale University
issn 1662-5196
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroinformatics
spelling doaj-art-1634261dd2fb495bb5a2f2a6687a8ae72025-08-20T03:47:04ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962025-08-011910.3389/fninf.2025.16180501618050Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniquesNidhi PatelJaiprakash VermaSwati JainElectroencephalogram (EEG) signal analysis plays a vital role in diagnosing and monitoring alcoholism, where accurate classification of individuals into alcoholic and control groups is essential. However, the inherent noise and complexity of EEG signals pose significant challenges. This study investigates the impact of three signal denoising techniques' Discrete Wavelet Transform(DWT), Discrete Fourier Transform(DFT), and Discrete Cosine Transform (DCT) Non EEG signal classification performance. The motivation behind this study is to identify the most effective preprocessing method for enhancing deep learning model performance in this domain. A novel DWT-CNN-BiGRU model is proposed, which leverages CNN layers for spatial feature extraction and BiGRU layers for capturing temporal dependencies. Experimental results show that the DWT-based approach, combined with standard scaling, achieves the highest accuracy of 94%, with a precision of 0.94, a recall of 0.95, and an F1-score of 0.94. Compared to the baseline DWT-CNN-BiLSTM model, the proposed method provides a modest yet meaningful improvement of approximately 17% in classification accuracy. These findings highlight the superiority of DWT as a preprocessing method and validate the proposed model's effectiveness for EEG-based classification, contributing to the development of more reliable medical diagnostic tools.https://www.frontiersin.org/articles/10.3389/fninf.2025.1618050/fullalcoholismdeep learningmachine learningnoise filtering for EEG databrain computer interface
spellingShingle Nidhi Patel
Jaiprakash Verma
Swati Jain
Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques
Frontiers in Neuroinformatics
alcoholism
deep learning
machine learning
noise filtering for EEG data
brain computer interface
title Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques
title_full Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques
title_fullStr Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques
title_full_unstemmed Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques
title_short Improving EEG classification of alcoholic and control subjects using DWT-CNN-BiGRU with various noise filtering techniques
title_sort improving eeg classification of alcoholic and control subjects using dwt cnn bigru with various noise filtering techniques
topic alcoholism
deep learning
machine learning
noise filtering for EEG data
brain computer interface
url https://www.frontiersin.org/articles/10.3389/fninf.2025.1618050/full
work_keys_str_mv AT nidhipatel improvingeegclassificationofalcoholicandcontrolsubjectsusingdwtcnnbigruwithvariousnoisefilteringtechniques
AT jaiprakashverma improvingeegclassificationofalcoholicandcontrolsubjectsusingdwtcnnbigruwithvariousnoisefilteringtechniques
AT swatijain improvingeegclassificationofalcoholicandcontrolsubjectsusingdwtcnnbigruwithvariousnoisefilteringtechniques