An Improved AlexNet Model and Cepstral Coefficient-Based Classification of Autism Using EEG.

IF 1.6 4区 医学 Q3 CLINICAL NEUROLOGY Clinical EEG and Neuroscience Pub Date : 2024-01-01 Epub Date: 2023-05-29 DOI:10.1177/15500594231178274
R Menaka, R Karthik, S Saranya, M Niranjan, S Kabilan
{"title":"An Improved AlexNet Model and Cepstral Coefficient-Based Classification of Autism Using EEG.","authors":"R Menaka, R Karthik, S Saranya, M Niranjan, S Kabilan","doi":"10.1177/15500594231178274","DOIUrl":null,"url":null,"abstract":"<p><p>Autism is a neurodevelopmental disorder that cannot be completely cured, but early intervention during childhood can improve outcomes. Identifying autism spectrum disorder (ASD) has relied on subjective detection methods that involve questionnaires, medical professionals, and therapists and are subject to observer variability. The need for early diagnosis and the limitations of subjective detection methods has led researchers to explore machine learning-based approaches, such as Random Forests, K-Nearest Neighbors, Naive Bayes, and Support Vector Machines, to predict ASD meltdowns. In recent years, deep learning techniques have gained traction for early ASD detection. This study evaluates the performance of various deep learning networks, including AlexNet, VGG16, and ResNet50, using 5 cepstral coefficient features for ASD detection. The main contributions of this study are the utilization of Cepstral Coefficients in the processing stage to construct spectrograms and the modification of the AlexNet architecture for precise classification. Experimental observations indicate that the AlexNet with Linear Frequency Cepstral Coefficients (LFCC) yields the highest accuracy of 85.1%, while a customized AlexNet with LFCC achieves 90% accuracy.</p>","PeriodicalId":10682,"journal":{"name":"Clinical EEG and Neuroscience","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical EEG and Neuroscience","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/15500594231178274","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/5/29 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 2

Abstract

Autism is a neurodevelopmental disorder that cannot be completely cured, but early intervention during childhood can improve outcomes. Identifying autism spectrum disorder (ASD) has relied on subjective detection methods that involve questionnaires, medical professionals, and therapists and are subject to observer variability. The need for early diagnosis and the limitations of subjective detection methods has led researchers to explore machine learning-based approaches, such as Random Forests, K-Nearest Neighbors, Naive Bayes, and Support Vector Machines, to predict ASD meltdowns. In recent years, deep learning techniques have gained traction for early ASD detection. This study evaluates the performance of various deep learning networks, including AlexNet, VGG16, and ResNet50, using 5 cepstral coefficient features for ASD detection. The main contributions of this study are the utilization of Cepstral Coefficients in the processing stage to construct spectrograms and the modification of the AlexNet architecture for precise classification. Experimental observations indicate that the AlexNet with Linear Frequency Cepstral Coefficients (LFCC) yields the highest accuracy of 85.1%, while a customized AlexNet with LFCC achieves 90% accuracy.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
改进的AlexNet模型及基于倒谱系数的自闭症脑电分类。
自闭症是一种不能完全治愈的神经发育障碍,但在儿童时期进行早期干预可以改善结果。自闭症谱系障碍(ASD)的识别依赖于主观检测方法,包括问卷调查、医疗专业人员和治疗师,并且受观察者变化的影响。早期诊断的需要和主观检测方法的局限性促使研究人员探索基于机器学习的方法,如随机森林、k近邻、朴素贝叶斯和支持向量机,来预测自闭症谱系障碍的崩溃。近年来,深度学习技术在早期ASD检测中获得了关注。本研究评估了各种深度学习网络的性能,包括AlexNet, VGG16和ResNet50,使用5个倒谱系数特征进行ASD检测。本研究的主要贡献是在处理阶段利用倒谱系数来构建谱图,以及修改AlexNet架构以进行精确分类。实验结果表明,线性频率倒谱系数(LFCC)的AlexNet准确率最高,达到85.1%,而定制的LFCC AlexNet准确率达到90%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Clinical EEG and Neuroscience
Clinical EEG and Neuroscience 医学-临床神经学
CiteScore
5.20
自引率
5.00%
发文量
66
审稿时长
>12 weeks
期刊介绍: Clinical EEG and Neuroscience conveys clinically relevant research and development in electroencephalography and neuroscience. Original articles on any aspect of clinical neurophysiology or related work in allied fields are invited for publication.
期刊最新文献
Ikelos-RWA. Validation of an Automatic Tool to Quantify REM Sleep Without Atonia. Age-dependent Electroencephalogram Characteristics During Different Levels of Anesthetic Depth. The Clinical Utility of Finding Unexpected Subclinical Spikes Detected by High-Density EEG During Neurodiagnostic Investigations Comparative Analysis of LORETA Z Score Neurofeedback and Cognitive Rehabilitation on Quality of Life and Response Inhibition in Individuals with Opioid Addiction Deep Learning-Based Artificial Intelligence Can Differentiate Treatment-Resistant and Responsive Depression Cases with High Accuracy
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1