Machine Learning Recognizes Frequency-Following Responses in American Adults: Effects of Reference Spectrogram and Stimulus Token.

IF 1.4 4区 心理学 Q4 PSYCHOLOGY, EXPERIMENTAL Perceptual and Motor Skills Pub Date : 2024-10-01 Epub Date: 2024-08-16 DOI:10.1177/00315125241273993
Sydney W Bauer, Fuh-Cherng Jeng, Amanda Carriero
{"title":"Machine Learning Recognizes Frequency-Following Responses in American Adults: Effects of Reference Spectrogram and Stimulus Token.","authors":"Sydney W Bauer, Fuh-Cherng Jeng, Amanda Carriero","doi":"10.1177/00315125241273993","DOIUrl":null,"url":null,"abstract":"<p><p>Electrophysiological research has been widely utilized to study brain responses to acoustic stimuli. The frequency-following response (FFR), a non-invasive reflection of how the brain encodes acoustic stimuli, is a particularly propitious electrophysiologic measure. While the FFR has been studied extensively, there are limitations in obtaining and analyzing FFR recordings that recent machine learning algorithms may address. In this study, we aimed to investigate whether FFRs can be enhanced using an \"improved\" source-separation machine learning algorithm. For this study, we recruited 28 native speakers of American English with normal hearing. We obtained two separate FFRs from each participant while they listened to two stimulus tokens /i/ and /da/. Electroencephalographic signals were pre-processed and analyzed using a source-separation non-negative matrix factorization (SSNMF) machine learning algorithm. The algorithm was trained using individual, grand-averaged, or stimulus token spectrograms as a reference. A repeated measures analysis of variance revealed that FFRs were significantly enhanced (<i>p</i> < .001) when the \"improved\" SSNMF algorithm was trained using both individual and grand-averaged spectrograms, but not when utilizing the stimulus token spectrogram. Similar results were observed when extracting FFRs elicited by using either stimulus token, /i/ or /da/. This demonstration shows how the SSNMF machine learning algorithm, using individual and grand-averaged spectrograms as references in training the algorithm, significantly enhanced FFRs. This improvement has important implications for the obtainment and analytical processes of FFR, which may lead to advancements in clinical applications of FFR testing.</p>","PeriodicalId":19869,"journal":{"name":"Perceptual and Motor Skills","volume":" ","pages":"1584-1602"},"PeriodicalIF":1.4000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Perceptual and Motor Skills","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1177/00315125241273993","RegionNum":4,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/16 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"PSYCHOLOGY, EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Electrophysiological research has been widely utilized to study brain responses to acoustic stimuli. The frequency-following response (FFR), a non-invasive reflection of how the brain encodes acoustic stimuli, is a particularly propitious electrophysiologic measure. While the FFR has been studied extensively, there are limitations in obtaining and analyzing FFR recordings that recent machine learning algorithms may address. In this study, we aimed to investigate whether FFRs can be enhanced using an "improved" source-separation machine learning algorithm. For this study, we recruited 28 native speakers of American English with normal hearing. We obtained two separate FFRs from each participant while they listened to two stimulus tokens /i/ and /da/. Electroencephalographic signals were pre-processed and analyzed using a source-separation non-negative matrix factorization (SSNMF) machine learning algorithm. The algorithm was trained using individual, grand-averaged, or stimulus token spectrograms as a reference. A repeated measures analysis of variance revealed that FFRs were significantly enhanced (p < .001) when the "improved" SSNMF algorithm was trained using both individual and grand-averaged spectrograms, but not when utilizing the stimulus token spectrogram. Similar results were observed when extracting FFRs elicited by using either stimulus token, /i/ or /da/. This demonstration shows how the SSNMF machine learning algorithm, using individual and grand-averaged spectrograms as references in training the algorithm, significantly enhanced FFRs. This improvement has important implications for the obtainment and analytical processes of FFR, which may lead to advancements in clinical applications of FFR testing.

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
机器学习识别美国成年人的频率跟随反应:参考谱图和刺激标记的影响
电生理研究已被广泛用于研究大脑对声音刺激的反应。频率跟随反应(FFR)是大脑如何对声音刺激进行编码的一种非侵入性反映,是一种特别理想的电生理测量方法。虽然对 FFR 进行了广泛的研究,但在获取和分析 FFR 记录方面存在一些局限性,而最新的机器学习算法可以解决这些问题。在本研究中,我们旨在研究是否可以使用 "改进的 "声源分离机器学习算法来增强 FFR。在这项研究中,我们招募了 28 名听力正常的以美式英语为母语的人。我们在每位受试者聆听两个刺激标记/i/和/da/时分别获得了他们的FFR。我们使用源分离非负矩阵因式分解(SSNMF)机器学习算法对脑电信号进行了预处理和分析。该算法使用单个、总平均或刺激标记谱图作为参考进行训练。重复测量方差分析显示,当 "改进的 "SSNMF 算法同时使用单个和总平均频谱图进行训练时,FFR 显著增强(p < .001),而使用刺激标记频谱图时,FFR 则没有显著增强。在提取由刺激标记/i/或/da/引起的 FFR 时,也观察到了类似的结果。该演示表明,SSNMF 机器学习算法在训练中使用单个和总平均频谱图作为参考,可显著提高 FFR。这种改进对 FFR 的获取和分析过程具有重要意义,可促进 FFR 测试的临床应用。
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
Perceptual and Motor Skills
Perceptual and Motor Skills PSYCHOLOGY, EXPERIMENTAL-
CiteScore
2.90
自引率
6.20%
发文量
110
期刊最新文献
Associations Between Fundamental Motor Skill Domains and Physical Fitness Components in 5-11-Year-Old Children. Immediate Effects of Custom Foot Orthoses on Postural Balance and Pain in Obese Middle-Aged Women With Plantar Fasciitis. Reliability and Validity of the Trunk Control Measurement Scale in Children With Duchenne Muscular Dystrophy. Magnitude and Direction of Interlimb Asymmetry and the Association of Interlimb Asymmetry with Physical Performance in Judo Athletes with Visual Impairment. The Effects of Telerehabilitation-Based Exercise Therapy on Motor and Non-Motor Clinical Outcomes in Adults With Facial Palsy: A Randomized Controlled Trial.
×
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