论文标题
用变异自动编码器学习脑电图数据的生成因子
Learning Generative Factors of EEG Data with Variational auto-encoders
论文作者
论文摘要
脑电图产生高维的随机数据，从中提取有关感兴趣现象的高级知识可能具有挑战性。我们通过将变异自动编码器的框架应用于1）对多种病理进行分类和2）以数据驱动方式恢复这些病理学的神经系统机制来应对这一挑战。我们的框架学习了与病理有关的数据的生成因素。我们提供了一种算法来进一步解码这些因素，并发现不同的病理如何影响观察到的数据。我们说明了拟议方法在识别精神分裂症的适用性，然后是听觉口头幻觉。我们进一步展示了框架学习与当前领域知识一致的疾病相关机制的能力。我们还将所提出的框架与几种基准方法进行比较，并表明其分类性能和解释性优势。
Electroencephalography produces high-dimensional, stochastic data from which it might be challenging to extract high-level knowledge about the phenomena of interest. We address this challenge by applying the framework of variational auto-encoders to 1) classify multiple pathologies and 2) recover the neurological mechanisms of those pathologies in a data-driven manner. Our framework learns generative factors of data related to pathologies. We provide an algorithm to decode those factors further and discover how different pathologies affect observed data. We illustrate the applicability of the proposed approach to identifying schizophrenia, either followed or not by auditory verbal hallucinations. We further demonstrate the ability of the framework to learn disease-related mechanisms consistent with current domain knowledge. We also compare the proposed framework with several benchmark approaches and indicate its classification performance and interpretability advantages.
