Spinnato J, Roubaud M-C, Burle B, Torrésani B
Aix-Marseille Université, CNRS, Centrale Marseille, I2M, UMR 7373, 13453 Marseille, France. Aix-Marseille Université, CNRS, LNC, UMR 7291, 13331 Marseille, France.
J Neural Eng. 2015 Jun;12(3):036013. doi: 10.1088/1741-2560/12/3/036013. Epub 2015 May 14.
The main goal of this work is to develop a model for multisensor signals, such as magnetoencephalography or electroencephalography (EEG) signals that account for inter-trial variability, suitable for corresponding binary classification problems. An important constraint is that the model be simple enough to handle small size and unbalanced datasets, as often encountered in BCI-type experiments.
The method involves the linear mixed effects statistical model, wavelet transform, and spatial filtering, and aims at the characterization of localized discriminant features in multisensor signals. After discrete wavelet transform and spatial filtering, a projection onto the relevant wavelet and spatial channels subspaces is used for dimension reduction. The projected signals are then decomposed as the sum of a signal of interest (i.e., discriminant) and background noise, using a very simple Gaussian linear mixed model.
Thanks to the simplicity of the model, the corresponding parameter estimation problem is simplified. Robust estimates of class-covariance matrices are obtained from small sample sizes and an effective Bayes plug-in classifier is derived. The approach is applied to the detection of error potentials in multichannel EEG data in a very unbalanced situation (detection of rare events). Classification results prove the relevance of the proposed approach in such a context.
The combination of the linear mixed model, wavelet transform and spatial filtering for EEG classification is, to the best of our knowledge, an original approach, which is proven to be effective. This paper improves upon earlier results on similar problems, and the three main ingredients all play an important role.
本研究的主要目标是开发一种针对多传感器信号（如脑磁图或脑电图（EEG）信号）的模型，该模型考虑试验间变异性，适用于相应的二元分类问题。一个重要的限制是该模型要足够简单，以处理BCI类实验中经常遇到的小尺寸和不平衡数据集。
该方法涉及线性混合效应统计模型、小波变换和空间滤波，旨在表征多传感器信号中的局部判别特征。在进行离散小波变换和空间滤波后，将投影到相关小波和空间通道子空间上以进行降维。然后，使用非常简单的高斯线性混合模型将投影信号分解为感兴趣信号（即判别信号）和背景噪声之和。
由于模型的简单性，相应的参数估计问题得到简化。从小样本量中获得了类协方差矩阵的稳健估计，并推导了有效的贝叶斯插件分类器。该方法应用于非常不平衡情况下（罕见事件检测）多通道EEG数据中的错误电位检测。分类结果证明了该方法在这种情况下的相关性。
据我们所知，将线性混合模型、小波变换和空间滤波相结合用于EEG分类是一种原创方法，已被证明是有效的。本文改进了早期关于类似问题的结果，并且这三个主要因素都发挥了重要作用。
