一种新的基于移动窗口的功率谱特征用于单通道脑电分类

IF 0.6 4区 综合性期刊 Q3 MULTIDISCIPLINARY SCIENCES
A. M. Alqudah, Shoroq Qazan, Yusra M. Obeidat
{"title":"一种新的基于移动窗口的功率谱特征用于单通道脑电分类","authors":"A. M. Alqudah, Shoroq Qazan, Yusra M. Obeidat","doi":"10.4025/actascitechnol.v45i1.61684","DOIUrl":null,"url":null,"abstract":"Electroencephalogram (EEG) signal classification is a crucial and very difficult task. Meanwhile, extracting features that are representative and able to discriminate different types of EEG signals is a complex task. Such features are usually fed to machine learning algorithms to classify the EEG signals based on the extracted features. This paper proposed a highly accurate and real-time features extraction method that can be used to help physicians in detecting different types of seizures and states in EEG signals characterized by a set of features extracted from the power spectrum of the EEG window. This is achieved by applying the following four steps. First, the EEG signals dataset contains different classes of EEG signals: Normal Eye Closed, Normal Eye Opened, Focal Seizure, Non-Focal Seizure, and Ictal Seizure activities. Second, each EEG signal has a length of 4097 samples sampled with a sampling frequency of 173.6 Hz which resulted in 23.6 seconds in length, this signal will be truncated into windows (Sub-signals) with a length of 349 samples (Approximately 2 seconds) with a total number of 12 windows for each signal. Afterward, the Fourier Transform (FT) based power spectrum will be computed for each window, then a set of different features are extracted from each window's FT power spectrum, and these features are classified using different Machine Learning (ML) algorithms. The results showed that the proposed methodology yields around 98% accuracy for the five different classification scenarios using different ML algorithms. The suggested method is hence robust, fast, real-time, accurate, and simple.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel moving window-based power spectrum features for single-channel EEG classification using machine learning\",\"authors\":\"A. M. Alqudah, Shoroq Qazan, Yusra M. Obeidat\",\"doi\":\"10.4025/actascitechnol.v45i1.61684\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Electroencephalogram (EEG) signal classification is a crucial and very difficult task. Meanwhile, extracting features that are representative and able to discriminate different types of EEG signals is a complex task. Such features are usually fed to machine learning algorithms to classify the EEG signals based on the extracted features. This paper proposed a highly accurate and real-time features extraction method that can be used to help physicians in detecting different types of seizures and states in EEG signals characterized by a set of features extracted from the power spectrum of the EEG window. This is achieved by applying the following four steps. First, the EEG signals dataset contains different classes of EEG signals: Normal Eye Closed, Normal Eye Opened, Focal Seizure, Non-Focal Seizure, and Ictal Seizure activities. Second, each EEG signal has a length of 4097 samples sampled with a sampling frequency of 173.6 Hz which resulted in 23.6 seconds in length, this signal will be truncated into windows (Sub-signals) with a length of 349 samples (Approximately 2 seconds) with a total number of 12 windows for each signal. Afterward, the Fourier Transform (FT) based power spectrum will be computed for each window, then a set of different features are extracted from each window's FT power spectrum, and these features are classified using different Machine Learning (ML) algorithms. The results showed that the proposed methodology yields around 98% accuracy for the five different classification scenarios using different ML algorithms. The suggested method is hence robust, fast, real-time, accurate, and simple.\",\"PeriodicalId\":7140,\"journal\":{\"name\":\"Acta Scientiarum-technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2022-12-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Acta Scientiarum-technology\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://doi.org/10.4025/actascitechnol.v45i1.61684\",\"RegionNum\":4,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MULTIDISCIPLINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Scientiarum-technology","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.4025/actascitechnol.v45i1.61684","RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

脑电图(EEG)信号分类是一项关键而又困难的工作。同时,提取具有代表性且能够区分不同类型脑电信号的特征是一项复杂的任务。这些特征通常被输入到机器学习算法中,根据提取的特征对脑电信号进行分类。本文提出了一种高精度、实时性高的特征提取方法,可以帮助医生检测EEG信号中不同类型的癫痫发作和状态,这些信号是通过EEG窗口功率谱提取的一组特征来表征的。这可以通过应用以下四个步骤来实现。首先,EEG信号数据集包含不同类别的EEG信号:正常闭眼、正常睁眼、局灶性癫痫发作、非局灶性癫痫发作和癫痫发作活动。其次,每个EEG信号的采样长度为4097个样本,采样频率为173.6 Hz,长度为23.6秒,该信号将被截断为长度为349个样本(约2秒)的窗口(子信号),每个信号共有12个窗口。然后,计算每个窗口的傅立叶变换(FT)功率谱,然后从每个窗口的FT功率谱中提取一组不同的特征,并使用不同的机器学习(ML)算法对这些特征进行分类。结果表明,对于使用不同ML算法的五种不同分类场景,所提出的方法的准确率约为98%。该方法具有鲁棒性好、快速、实时、准确、简便等特点。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A novel moving window-based power spectrum features for single-channel EEG classification using machine learning
Electroencephalogram (EEG) signal classification is a crucial and very difficult task. Meanwhile, extracting features that are representative and able to discriminate different types of EEG signals is a complex task. Such features are usually fed to machine learning algorithms to classify the EEG signals based on the extracted features. This paper proposed a highly accurate and real-time features extraction method that can be used to help physicians in detecting different types of seizures and states in EEG signals characterized by a set of features extracted from the power spectrum of the EEG window. This is achieved by applying the following four steps. First, the EEG signals dataset contains different classes of EEG signals: Normal Eye Closed, Normal Eye Opened, Focal Seizure, Non-Focal Seizure, and Ictal Seizure activities. Second, each EEG signal has a length of 4097 samples sampled with a sampling frequency of 173.6 Hz which resulted in 23.6 seconds in length, this signal will be truncated into windows (Sub-signals) with a length of 349 samples (Approximately 2 seconds) with a total number of 12 windows for each signal. Afterward, the Fourier Transform (FT) based power spectrum will be computed for each window, then a set of different features are extracted from each window's FT power spectrum, and these features are classified using different Machine Learning (ML) algorithms. The results showed that the proposed methodology yields around 98% accuracy for the five different classification scenarios using different ML algorithms. The suggested method is hence robust, fast, real-time, accurate, and simple.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Acta Scientiarum-technology
Acta Scientiarum-technology 综合性期刊-综合性期刊
CiteScore
1.40
自引率
12.50%
发文量
60
审稿时长
6-12 weeks
期刊介绍: The journal publishes original articles in all areas of Technology, including: Engineerings, Physics, Chemistry, Mathematics, Statistics, Geosciences and Computation Sciences. To establish the public inscription of knowledge and its preservation; To publish results of research comprising ideas and new scientific suggestions; To publicize worldwide information and knowledge produced by the scientific community; To speech the process of scientific communication in Technology.
×
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