An online self-paced brain-computer interface onset detection based on sound-production imagery applied to real-life scenarios

2017 5th International Winter Conference on Brain-Computer Interface (BCI) Pub Date : 1900-01-01 DOI:10.1109/IWW-BCI.2017.7858155

Youngjae Song, F. Sepulveda

{"title":"An online self-paced brain-computer interface onset detection based on sound-production imagery applied to real-life scenarios","authors":"Youngjae Song, F. Sepulveda","doi":"10.1109/IWW-BCI.2017.7858155","DOIUrl":null,"url":null,"abstract":"This research investigated an online onset detection (i.e., ON state detection in asynchronous BCIs) method for BCIs by opening a message when it arrives in two different daily-life task scenarios (watching video and reading text). A new sound-production related cognitive task (Sound-production imagery, SI) was tested. Blind-source separation with canonical correlation analysis was used for artefact handling. Autoregressive coefficients, band power, common spatial patterns and discrete wavelet transform were used for feature extraction to cover all time, frequency, and spatial time-frequency domain. Linear discriminant analysis was used for classification. The averaged true-positive rate with six subjects was 88.9% in the watching video scenario and 78.9% in the reading text case. The average false-positive rates were 4.2% and 3.9%, respectively. In terms of task response speed, SI task recognition took 4.45s on average for an onset. From these results, the new SI task showed promising results for an online self-paced onset detection system compared to other similar studies.","PeriodicalId":443427,"journal":{"name":"2017 5th International Winter Conference on Brain-Computer Interface (BCI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 5th International Winter Conference on Brain-Computer Interface (BCI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWW-BCI.2017.7858155","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 5

Abstract

This research investigated an online onset detection (i.e., ON state detection in asynchronous BCIs) method for BCIs by opening a message when it arrives in two different daily-life task scenarios (watching video and reading text). A new sound-production related cognitive task (Sound-production imagery, SI) was tested. Blind-source separation with canonical correlation analysis was used for artefact handling. Autoregressive coefficients, band power, common spatial patterns and discrete wavelet transform were used for feature extraction to cover all time, frequency, and spatial time-frequency domain. Linear discriminant analysis was used for classification. The averaged true-positive rate with six subjects was 88.9% in the watching video scenario and 78.9% in the reading text case. The average false-positive rates were 4.2% and 3.9%, respectively. In terms of task response speed, SI task recognition took 4.45s on average for an onset. From these results, the new SI task showed promising results for an online self-paced onset detection system compared to other similar studies.

查看原文本刊更多论文

基于声音制作图像应用于现实生活场景的在线自定节奏脑机接口发作检测

本研究通过在两种不同的日常任务场景(观看视频和阅读文本)中打开消息，研究了一种针对脑机接口的在线启动检测(即异步脑机接口的ON状态检测)方法。一项新的与声音产生相关的认知任务(声音产生意象，SI)被测试。伪影处理采用典型相关分析的盲源分离。利用自回归系数、频带功率、共同空间模式和离散小波变换进行特征提取，覆盖了时间、频率和空间时频域。采用线性判别分析进行分类。6名被试的平均真阳性率在观看视频组为88.9%，在阅读文本组为78.9%。平均假阳性率分别为4.2%和3.9%。在任务响应速度方面，SI任务识别平均耗时4.45秒。从这些结果来看，与其他类似的研究相比，新的SI任务显示了在线自定节奏发病检测系统的有希望的结果。

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

2017 5th International Winter Conference on Brain-Computer Interface (BCI)

自引率

0.00%

发文量