Institute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, China.
Department of Biomedical Engineering, University of Houston, Houston, TX 77204, USA.
Comput Intell Neurosci. 2020 Mar 10;2020:3287589. doi: 10.1155/2020/3287589. eCollection 2020.
Recent technological advances have enabled researchers to collect large amounts of electroencephalography (EEG) signals in labeled and unlabeled datasets. It is expensive and time consuming to collect labeled EEG data for use in brain-computer interface (BCI) systems, however. In this paper, a novel active learning method is proposed to minimize the amount of labeled, subject-specific EEG data required for effective classifier training, by combining measures of uncertainty and representativeness within an extreme learning machine (ELM). Following this approach, an ELM classifier was first used to select a relatively large batch of unlabeled examples, whose uncertainty was measured through the best-versus-second-best (BvSB) strategy. The diversity of each sample was then measured between the limited labeled training data and previously selected unlabeled samples, and similarity is measured among the previously selected samples. Finally, a tradeoff parameter is introduced to control the balance between informative and representative samples, and these samples are then used to construct a powerful ELM classifier. Extensive experiments were conducted using benchmark and multiclass motor imagery EEG datasets to evaluate the efficacy of the proposed method. Experimental results show that the performance of the new algorithm exceeds or matches those of several state-of-the-art active learning algorithms. It is thereby shown that the proposed method improves classifier performance and reduces the need for training samples in BCI applications.
最近的技术进步使研究人员能够在标记和未标记的数据集上收集大量脑电图 (EEG) 信号。然而，用于脑机接口 (BCI) 系统的标记 EEG 数据的收集既昂贵又耗时。在本文中，我们提出了一种新的主动学习方法，通过在极限学习机 (ELM) 中结合不确定性和代表性度量来最小化有效分类器训练所需的标记、特定于主体的 EEG 数据量。按照这种方法，首先使用 ELM 分类器选择相对较大的一批未标记的示例，通过最佳与第二佳 (BvSB) 策略来衡量其不确定性。然后，在有限的标记训练数据和之前选择的未标记样本之间测量每个样本的多样性，并在之前选择的样本之间测量相似性。最后，引入一个权衡参数来控制信息丰富和代表性样本之间的平衡，然后使用这些样本构建强大的 ELM 分类器。使用基准和多类运动想象 EEG 数据集进行了广泛的实验，以评估所提出方法的效果。实验结果表明，新算法的性能优于或匹配几种最先进的主动学习算法。因此，所提出的方法可以提高分类器的性能并减少 BCI 应用中对训练样本的需求。
