Decoding Behavior Tasks From Brain Activity Using Deep Transfer Learning
Decoding Behavior Tasks From Brain Activity Using Deep Transfer Learning
复制标题
DOI：
10.1109/access.2019.2907040
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Zhang, Jiacai
中科院分区：
文献类型：
--
作者：
Gao, Yufei;Zhang, Yameng;Zhang, Jiacai
最近，非侵入性检测技术的进步表明，从可测量的大脑活动中解码视觉信息是可能的。然而，这些研究通常集中在个体水平上神经活动与视觉信息(如图像或视频刺激)之间的映射。在这里，研究了从大脑信号中对行为任务进行分类的跨个体通用解码模型。我们提出了一种基于深度迁移学习(DTL)的跨被试解码方法，用于从功能磁共振成像(FMRI)记录中破译被试在执行不同任务时的行为任务。我们将在ImageNet数据集上预先训练的最先进网络的部分连接到我们定义的适配层，以从fMRI数据中对行为任务进行分类。我们在人类连接组计划(Human Connectome Project，HCP)数据集上的实验表明，与以往的研究相比，该方法获得了更高的跨主题解码精度。我们还在五个HCP数据子集上进行了实验，进一步证明了我们的DTL方法在小数据集上比传统方法更有效。
Recently, advances in noninvasive detection techniques have shown that it is possible to decode visual information from measurable brain activities. However, these studies typically focused on the mapping between neural activities and visual information, such as the image or video stimulus, on the individual level. Here, the common decoding models across individuals that classifying behavior tasks from brain signals were investigated. We proposed a cross-subject decoding approach using deep transfer learning (DTL) to decipher the behavior tasks from functional magnetic resonance imaging (fMRI) recording during subjects performing different tasks. We connected parts of the state-of-the-art networks pre-trained on the ImageNet dataset to our defined adaption layers to classify the behavior tasks from fMRI data. Our experiments on the Human Connectome Project (HCP) dataset showed that the proposed method achieved a higher decoding accuracy across subjects than the previous studies. We also conducted an experiment on five subsets of HCP data, which further demonstrated that our DTL approach is more effective on small dataset than the traditional methods.