IEEE Trans Neural Syst Rehabil Eng. 2020 Aug;28(8):1702-1709. doi: 10.1109/TNSRE.2020.3004462. Epub 2020 Jun 23.
The convolutional neural network (CNN) model is an active research topic in the field of EEG signals analysis. However, the classification effect of CNN on EEG signals of amnestic mild cognitive impairment (aMCI) with type 2 diabetes mellitus (T2DM) is not ideal. Even if EEG signals are transformed into multispectral images that are more closely matched with the model, the best classification performance can not be achieved. Therefore, to improve the performance of CNN toward EEG multispectral image classification, a multi-view convolutional neural network (MVCNN) classification model based on inceptionV1 is designed in this study. This model mainly improves and optimizes the convolutional layers and stochastic gradient descent (SGD) in the convolutional architecture model. Firstly, based on the discreteness of EEG multispectral image features, the multi-view convolutional layer structure was proposed. Then the learning rate change function of the SGD was optimized to increase the classification performance. The multi-view convolutional nerve was used in an EEG multispectral classification task involving 19 aMCI with T2DM and 20 normal controls. The results showed that compared with the traditional classification models, MVCNN had a better stability and accuracy. Therefore, MVCNN could be used as an effective feature classification method for aMCI with T2DM.
卷积神经网络（CNN）模型是 EEG 信号分析领域的一个活跃研究课题。然而，CNN 对 2 型糖尿病伴遗忘型轻度认知障碍（aMCI）的 EEG 信号的分类效果并不理想。即使将 EEG 信号转换为与模型更匹配的多谱图像，也无法达到最佳的分类性能。因此，为了提高 CNN 对 EEG 多谱图像分类的性能，本研究设计了一种基于 inceptionV1 的多视角卷积神经网络（MVCNN）分类模型。该模型主要改进和优化了卷积架构模型中的卷积层和随机梯度下降（SGD）。首先，基于 EEG 多谱图像特征的离散性，提出了多视角卷积层结构。然后优化了 SGD 的学习率变化函数，以提高分类性能。多视角卷积神经被用于涉及 19 名 2 型糖尿病伴遗忘型轻度认知障碍患者和 20 名正常对照者的 EEG 多谱分类任务中。结果表明，与传统分类模型相比，MVCNN 具有更好的稳定性和准确性。因此，MVCNN 可以作为 2 型糖尿病伴遗忘型轻度认知障碍患者的一种有效的特征分类方法。
