Department of Electrical, Information and Bioengineering, Politecnico di Milano, Milan, MI, Italy.
J Neural Eng. 2022 May 31;19(3). doi: 10.1088/1741-2552/ac6d7f.
Deep learning algorithms employed in brain computer interfaces (BCIs) need large electroencephalographic (EEG) datasets to be trained. These datasets are usually unbalanced, particularly when error potential (ErrP) experiment are considered, being ErrP's epochs much rarer than non-ErrP ones. To face the issue of unbalance of rare epochs, this paper presents a novel, data balancing methods based on ARX-modelling.AutoRegressive with eXogenous input (ARX)-models are identified on the EEG data of the 'Monitoring error-related potentials' dataset of the BNCI Horizon 2020 and then employed to generate new synthetic data of the minority class of ErrP epochs. The balanced dataset is used to train a classifier of non-ErrP vs. ErrP epochs based on EEGNet.Compared to classical techniques (e.g. class weights, CW) for data balancing, the new method outperforms the others in terms of resulting accuracy (i.e. ARX91.5%vs CW88.3%), F1-score (i.e. ARX78.3%vs CW73.7%) and balanced accuracy (i.e. ARX87.0%vs CW81.1%) and also reduces the number of false positive detection (i.e. ARX 51 vs CW 104). Moreover, the ARX-based method shows a better generalization capability of the whole model to classify and predict new data.The results obtained suggest that the proposed method can be used in BCI application for tackling the issue of data unbalance and obtain more reliable and robust performances.
深度学习算法在脑机接口 (BCI) 中需要大量的脑电图 (EEG) 数据集进行训练。这些数据集通常是不平衡的，特别是在考虑错误潜力 (ErrP) 实验时，ErrP 时期比非 ErrP 时期要少得多。为了解决罕见时期的不平衡问题，本文提出了一种基于 ARX 建模的新的数据平衡方法。基于脑机接口地平线 2020 的“监测错误相关电位”数据集的 EEG 数据，识别自回归与外生输入 (ARX) 模型，然后将其用于生成少数类 ErrP 时期的新合成数据。使用平衡数据集基于 EEGNet 训练非 ErrP 与 ErrP 时期的分类器。与数据平衡的经典技术（例如类权重、CW）相比，新方法在准确率（即 ARX91.5%对 CW88.3%）、F1 分数（即 ARX78.3%对 CW73.7%）和平衡准确率（即 ARX87.0%对 CW81.1%）方面表现优于其他方法，并且还减少了假阳性检测的数量（即 ARX51 对 CW104）。此外，基于 ARX 的方法还展示了整个模型对新数据进行分类和预测的更好的泛化能力。研究结果表明，所提出的方法可用于 BCI 应用，以解决数据不平衡问题，并获得更可靠和稳健的性能。
