Xue Jing, Gu Xiaoqing, Ni Tongguang
Department of Nephrology, The Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi, China.
School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, China.
Front Neurosci. 2020 Sep 29;14:586149. doi: 10.3389/fnins.2020.586149. eCollection 2020.
Metric learning is a class of efficient algorithms for EEG signal classification problem. Usually, metric learning method deals with EEG signals in the single view space. To exploit the diversity and complementariness of different feature representations, a new uto-weighted ulti-view iscriminative etric earning method with Fisher discriminative and global structure constraints for epilepsy EEG signal classification called AMDML is proposed to promote the performance of EEG signal classification. On the one hand, AMDML exploits the multiple features of different views in the scheme of the multi-view feature representation. On the other hand, considering both the Fisher discriminative constraint and global structure constraint, AMDML learns the discriminative metric space, in which the intraclass EEG signals are compact and the interclass EEG signals are separable as much as possible. For better adjusting the weights of constraints and views, instead of manually adjusting, a closed form solution is proposed, which obtain the best values when achieving the optimal model. Experimental results on Bonn EEG dataset show AMDML achieves the satisfactory results.
度量学习是一类用于脑电信号分类问题的高效算法。通常，度量学习方法在单视图空间中处理脑电信号。为了利用不同特征表示的多样性和互补性，提出了一种新的具有Fisher判别和全局结构约束的自动加权多视图判别度量学习方法（称为AMDML）用于癫痫脑电信号分类，以提升脑电信号分类性能。一方面，AMDML在多视图特征表示方案中利用不同视图的多种特征。另一方面，考虑到Fisher判别约束和全局结构约束，AMDML学习判别度量空间，在该空间中，类内脑电信号紧凑，类间脑电信号尽可能可分离。为了更好地调整约束和视图的权重，提出了一种闭式解，而非手动调整，该闭式解在实现最优模型时获得最佳值。在Bonn脑电数据集上的实验结果表明AMDML取得了令人满意的结果。
