Zhang Jianhua, Li Sunan, Wang Rubin
School of Information Science and Engineering, East China University of Science and TechnologyShanghai, China.
School of Sciences, East China University of Science and TechnologyShanghai, China.
Front Neurosci. 2017 May 30;11:310. doi: 10.3389/fnins.2017.00310. eCollection 2017.
In this paper, we deal with the Mental Workload (MWL) classification problem based on the measured physiological data. First we discussed the optimal depth (i.e., the number of hidden layers) and parameter optimization algorithms for the Convolutional Neural Networks (CNN). The base CNNs designed were tested according to five classification performance indices, namely Accuracy, Precision, F-measure, G-mean, and required training time. Then we developed an Ensemble Convolutional Neural Network (ECNN) to enhance the accuracy and robustness of the individual CNN model. For the ECNN design, three model aggregation approaches (weighted averaging, majority voting and stacking) were examined and a resampling strategy was used to enhance the diversity of individual CNN models. The results of MWL classification performance comparison indicated that the proposed ECNN framework can effectively improve MWL classification performance and is featured by entirely automatic feature extraction and MWL classification, when compared with traditional machine learning methods.
在本文中，我们基于测量的生理数据处理心理负荷（MWL）分类问题。首先，我们讨论了卷积神经网络（CNN）的最优深度（即隐藏层数）和参数优化算法。根据五个分类性能指标，即准确率、精确率、F值、G均值和所需训练时间，对所设计的基础CNN进行了测试。然后，我们开发了一种集成卷积神经网络（ECNN）来提高单个CNN模型的准确性和鲁棒性。对于ECNN设计，研究了三种模型聚合方法（加权平均、多数投票和堆叠），并使用重采样策略来增强单个CNN模型的多样性。MWL分类性能比较结果表明，与传统机器学习方法相比，所提出的ECNN框架能够有效提高MWL分类性能，并且具有完全自动的特征提取和MWL分类功能。
