CIF: Small: Source Separation with an Adaptive Structure for Multi-Modal Data Fusion

今天，在许多领域，关于某一特定现象的信息是通过不同类型的获取技术和实验条件获得的，这种多模式数据的可用性一直在增加。对这些数据进行联合分析，即数据融合，可以让我们对手头的任务有一个更全面、更有信息量的看法，如果仔细研究，可能会开辟新的领域，并回答我们在使用单一模式时甚至不会想到的问题。现在，在医学成像、遥感、语音处理、行为科学和代谢组学等学科中，数据融合领域的活动非常活跃。跨多个学科的共同挑战是确定不同数据集之间的关联方式和程度，即根据多个数据集为给定任务提供的信息确定公共和独特的子空间。目前的工作为这一关键挑战提供了一个强大的解决方案，能够以完全数据驱动的方式识别多个数据集之间的关系，从而可以鲁棒地识别每个数据集中的公共和独特子空间。通过将该自适应方案与独立向量分析框架（IVA）相结合，提出了一种新的强大的独立向量分析框架——自适应子空间结构（IVA- as），以实现多集和多模态数据的有效融合。这一框架的成功应用是通过一个独特的医学数据集来证明的，该数据集允许研究在分心驾驶或酒精影响下大脑功能的共性和差异。

In many fields today, information about a given phenomenon is obtained through different types of acquisition techniques and experimental conditions, and the availability of such multimodal data has been growing. Joint analysis of this data---its fusion---promises a more comprehensive and informative view of the task at hand, and, if probed carefully, may open new venues and answer questions we might not have even thought of asking when working with a single modality. There is now significant activity in data fusion in disciplines spanning medical imaging, remote sensing, speech processing, behavioral sciences, and metabolomics, to name a few. A common challenge across multiple disciplines is determining how and to what degree different datasets are related, i.e., identifying the common and distinct subspaces across multiple datasets in terms of the information they provide for the given task.The current work provides a powerful solution to this key challenge enabling identification of the relationship among multiple datasets in a completely data-driven manner such that both the common and distinct subspaces within each dataset can be robustly identified. By combining this adaptive scheme with the well defined but flexible framework of independent vector analysis (IVA), a new powerful framework, IVA with an adaptive subspace structure (IVA-AS) is developed for effective fusion of both the multiset and multimodal data. The successful application of this framework is demonstrated using a unique medical dataset that allows the study of commonalities and differences in brain function while driving with distractions or under the influence of alcohol.