Williams N J, Nasuto S J, Saddy J D
Centre for Integrative Neuroscience & Neurodynamics, University of Reading, Whiteknights Campus, Reading RG6 6AH, United Kingdom.
Centre for Integrative Neuroscience & Neurodynamics, University of Reading, Whiteknights Campus, Reading RG6 6AH, United Kingdom.
J Neurosci Methods. 2015 Jul 30;250:22-33. doi: 10.1016/j.jneumeth.2015.02.007. Epub 2015 Feb 16.
The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data.
We propose a complete pipeline for the cluster analysis of ERP data. To increase the signal-to-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA) to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA).
After validating the pipeline on simulated data, we tested it on data from two experiments - a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership.
COMPARISON WITH EXISTING METHOD(S): Our analysis operates on denoised single-trials, the number of clusters are determined in a principled manner and the results are presented through an intuitive visualisation.
Given the cluster structure in some experimental conditions, we suggest application of cluster analysis as a preliminary step before ensemble averaging.
由于事件相关电位（ERP）数据的总体平均法假定各次试验中的ERP相同，其有效性受到质疑。因此，需要对数据中的聚类结构进行初步测试。
我们提出了一个用于ERP数据聚类分析的完整流程。为了提高原始单次试验的信噪比（SNR），我们使用了基于经验模态分解（EMD）的去噪方法。接下来，我们使用基于自助法的方法，通过一种称为稳定性指数（SI）的度量来确定聚类的数量。然后，我们使用基于遗传算法（GA）的聚类算法来定义初始聚类中心，以便进行后续的k均值聚类。最后，我们通过基于主成分分析（PCA）的方案对聚类结果进行可视化。
在对模拟数据验证了该流程之后，我们将其应用于两个实验的数据——一个针对单个受试者的P300拼写器范式和一个针对25名受试者的语言处理研究。结果显示，在语言处理研究的一个实验条件下存在6个聚类的证据。此外，双向卡方检验显示受试者对聚类成员有影响。
我们的分析基于去噪后的单次试验进行，聚类数量以有原则的方式确定，结果通过直观的可视化呈现。
鉴于在某些实验条件下存在聚类结构，我们建议在总体平均之前将聚类分析作为初步步骤应用。
