Machine learning and interpretation in neuroimaging : 4th international workshop, MLINI 2014, held at NIPS 2014, Montreal QC, Canada, December 13, 2014 : revised selected papers. MLINI (Workshop) (4th : 2014 : Montreal, Quebec)最新文献

Estimating Learning Effects: A Short-Time Fourier Transform Regression Model for MEG Source Localization. 估计学习效果:一种用于脑磁图源定位的短时傅立叶变换回归模型。

Machine learning and interpretation in neuroimaging : 4th international workshop, MLINI 2014, held at NIPS 2014, Montreal QC, Canada, December 13, 2014 : revised selected papers. MLINI (Workshop) (4th : 2014 : Montreal, Quebec)

Pub Date : 2016-01-01 Epub Date: 2016-09-13 DOI: 10.1007/978-3-319-45174-9_8

Ying Yang, Michael J Tarr, Robert E Kass

Magnetoencephalography (MEG) has a high temporal resolution well-suited for studying perceptual learning. However, to identify where learning happens in the brain, one needs to apply source localization techniques to project MEG sensor data into brain space. Previous source localization methods, such as the short-time Fourier transform (STFT) method by Gramfort et al.([6]) produced intriguing results, but they were not designed to incorporate trial-by-trial learning effects. Here we modify the approach in [6] to produce an STFT-based source localization method (STFT-R) that includes an additional regression of the STFT components on covariates such as the behavioral learning curve. We also exploit a hierarchical L₂₁ penalty to induce structured sparsity of STFT components and to emphasize signals from regions of interest (ROIs) that are selected according to prior knowledge. In reconstructing the ROI source signals from simulated data, STFT-R achieved smaller errors than a two-step method using the popular minimum-norm estimate (MNE), and in a real-world human learning experiment, STFT-R yielded more interpretable results about what time-frequency components of the ROI signals were correlated with learning.

脑磁图(MEG)具有很高的时间分辨率，非常适合研究感知学习。然而，为了确定学习在大脑中发生的位置，需要应用源定位技术将MEG传感器数据投射到大脑空间中。以前的源定位方法，如Gramfort等人([6])的短时傅里叶变换(STFT)方法，产生了有趣的结果，但它们的设计并没有考虑到逐试学习的效果。在这里，我们修改了[6]中的方法，产生了一种基于STFT的源定位方法(STFT- r)，该方法包括对协变量(如行为学习曲线)上的STFT分量的额外回归。我们还利用分层L21惩罚来诱导STFT分量的结构化稀疏性，并强调根据先验知识选择的感兴趣区域(roi)的信号。在从模拟数据重建ROI源信号时，STFT-R比使用流行的最小范数估计(MNE)的两步方法获得更小的误差，并且在现实世界的人类学习实验中，STFT-R在ROI信号的时频分量与学习相关方面产生了更可解释的结果。

{"title":"Estimating Learning Effects: A Short-Time Fourier Transform Regression Model for MEG Source Localization.","authors":"Ying Yang, Michael J Tarr, Robert E Kass","doi":"10.1007/978-3-319-45174-9_8","DOIUrl":"https://doi.org/10.1007/978-3-319-45174-9_8","url":null,"abstract":"Magnetoencephalography (MEG) has a high temporal resolution well-suited for studying perceptual learning. However, to identify where learning happens in the brain, one needs to apply source localization techniques to project MEG sensor data into brain space. Previous source localization methods, such as the short-time Fourier transform (STFT) method by Gramfort et al.([6]) produced intriguing results, but they were not designed to incorporate trial-by-trial learning effects. Here we modify the approach in [6] to produce an STFT-based source localization method (STFT-R) that includes an additional regression of the STFT components on covariates such as the behavioral learning curve. We also exploit a hierarchical L21 penalty to induce structured sparsity of STFT components and to emphasize signals from regions of interest (ROIs) that are selected according to prior knowledge. In reconstructing the ROI source signals from simulated data, STFT-R achieved smaller errors than a two-step method using the popular minimum-norm estimate (MNE), and in a real-world human learning experiment, STFT-R yielded more interpretable results about what time-frequency components of the ROI signals were correlated with learning.","PeriodicalId":92424,"journal":{"name":"Machine learning and interpretation in neuroimaging : 4th international workshop, MLINI 2014, held at NIPS 2014, Montreal QC, Canada, December 13, 2014 : revised selected papers. MLINI (Workshop) (4th : 2014 : Montreal, Quebec)","volume":"9444 ","pages":"69-82"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/978-3-319-45174-9_8","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36516205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}