Screening of Moderate Traumatic Brain Injury from Power Feature of Resting State Electroencephalography using Support Vector Machine

Chi Qin Lai, M. Abdullah, J. Abdullah, A. Azman, H. Ibrahim
{"title":"Screening of Moderate Traumatic Brain Injury from Power Feature of Resting State Electroencephalography using Support Vector Machine","authors":"Chi Qin Lai, M. Abdullah, J. Abdullah, A. Azman, H. Ibrahim","doi":"10.1145/3362752.3362758","DOIUrl":null,"url":null,"abstract":"Traumatic brain injury (TBI) needs to be identified faster, so that suitable treatment can be planned properly. Normally, the severity of TBI is evaluated through the study from computed tomography (CT) or magnetic resonance imaging (MRI). Unfortunately, the number of CT scanners and MRI scanners is limited. Therefore, it is impractical to directly do CT or MRI scan to all patients without screening. Thus, this research investigates a method for screening moderate TBI patient. Data from resting state 63-channels electroencephalography is used in this work. Power of the signal is extracted from alpha, beta, theta and gamma frequency bands. This work utilizes a support vector machine, which is one of machine learning approaches, to identify moderate TBI patients. From the experimental results, it is shown that the average power from alpha or theta band gives the best accuracy score, which is at 70.83%.","PeriodicalId":430178,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Electronics and Electrical Engineering Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2019 2nd International Conference on Electronics and Electrical Engineering Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3362752.3362758","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

Abstract

Traumatic brain injury (TBI) needs to be identified faster, so that suitable treatment can be planned properly. Normally, the severity of TBI is evaluated through the study from computed tomography (CT) or magnetic resonance imaging (MRI). Unfortunately, the number of CT scanners and MRI scanners is limited. Therefore, it is impractical to directly do CT or MRI scan to all patients without screening. Thus, this research investigates a method for screening moderate TBI patient. Data from resting state 63-channels electroencephalography is used in this work. Power of the signal is extracted from alpha, beta, theta and gamma frequency bands. This work utilizes a support vector machine, which is one of machine learning approaches, to identify moderate TBI patients. From the experimental results, it is shown that the average power from alpha or theta band gives the best accuracy score, which is at 70.83%.
基于静息状态脑电图功率特征的支持向量机筛选中度创伤性脑损伤
创伤性脑损伤(TBI)需要更快地识别,以便可以适当地计划适当的治疗。通常,TBI的严重程度是通过计算机断层扫描(CT)或磁共振成像(MRI)来评估的。不幸的是,CT扫描仪和MRI扫描仪的数量有限。因此,不进行筛查,直接对所有患者进行CT或MRI扫描是不切实际的。因此,本研究探讨一种筛查中度TBI患者的方法。本研究使用静息状态63通道脑电图数据。信号的功率是从α、β、θ和γ频段提取的。这项工作利用支持向量机,这是机器学习方法之一,以识别中度脑损伤患者。实验结果表明,α和θ波段的平均功率为70.83%,准确率最高。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信