Decoding semantics across fMRI sessions with different stimulus modalities: a practical MVPA study
Decoding semantics across fMRI sessions with different stimulus modalities: a practical MVPA study
复制标题
DOI：
10.3389/fninf.2012.00024
复制
发表时间：
2012-01-01
影响因子：
3.5
通讯作者：
Poesio, Massimo
中科院分区：
文献类型：
--
作者：
Akama, Hiroyuki;Murphy, Brian;Poesio, Massimo
概念组织的具身和符号解释都可以预测通过不同刺激方式激活的概念的神经激活之间的部分共享和部分差异。但是BOLD活动模式中的跨参与者和跨会话可变性使得使用MVPA方法分析此类模式具有挑战性。在这里，我们研究了跨模态和个体差异对机器学习分析的功能磁共振成像数据记录在一个词的属性生成任务。我们提出了相同的一套生活和非生活的概念（陆地哺乳动物，或工作工具）的一组日本参与者在两个会议：第一次使用听觉呈现的口语单词;第二次使用视觉呈现的单词写在日本字符。分类准确性证实，这些语义类别可以在单次试验中检测到，会话内预测准确率为80- 90%。然而，跨会话预测（从记忆任务数据中学习来分类来自书写单词任务的数据，反之亦然）遭受性能损失，达到65-75%（在p
Both embodied and symbolic accounts of conceptual organzation would predict partial sharing and partial differentiation between the neural activations seen for concepts activated via different stimulus modalities. But cross-participant and cross-session variability in BOLD activity patterns makes analyses of such patterns with MVPA methods challenging. Here, we examine the effect of cross-modal and individual variation on the machine learning analysis of fMRI data recorded during a word property generation task. We present the same set of living and non-living concepts (land-mammals, or work tools) to a cohort of Japanese participants in two sessions: the first using auditory presentation of spoken words; the second using visual presentation of words written in Japanese characters. Classification accuracies confirmed that these semantic categories could be detected in single trials, with within-session predictive accuracies of 80-90%. However cross-session prediction (learning from auditory-task data to classify data from the written-word-task, or vice versa) suffered from a performance penalty, achieving 65-75% (still individually significant at p