Programa de Pós-Graduação em Engenharia Elétrica da Universidade Federal do Rio Grande do Sul, Avenue Osvaldo Aranha 103, Porto Alegre 90035-190, Brazil.
Sensors (Basel). 2019 Apr 18;19(8):1864. doi: 10.3390/s19081864.
Surface Electromyography (sEMG) signal processing has a disruptive technology potential to enable a natural human interface with artificial limbs and assistive devices. However, this biosignal real-time control interface still presents several restrictions such as control limitations due to a lack of reliable signal prediction and standards for signal processing among research groups. Our paper aims to present and validate our sEMG database through the signal classification performed by the reliable forms of our Extreme Learning Machines (ELM) classifiers, used to maintain a more consistent signal classification. To perform the signal processing, we explore the use of a stochastic filter based on the Antonyan Vardan Transform (AVT) in combination with two variations of our Reliable classifiers (denoted R-ELM and R-Regularized ELM (RELM), respectively), to derive a reliability metric from the system, which autonomously selects the most reliable samples for the signal classification. To validate and compare our database and classifiers with related papers, we performed the classification of the whole of Databases 1, 2, and 6 (DB1, DB2, and DB6) of the NINAProdatabase. Our database presented consistent results, while the reliable forms of ELM classifiers matched or outperformed related papers, reaching average accuracies higher than 99 % for the IEEdatabase, while average accuracies of 75 . 1 % , 79 . 77 % , and 69 . 83 % were achieved for NINAPro DB1, DB2, and DB6, respectively.
表面肌电图 (sEMG) 信号处理具有颠覆性技术潜力,可实现人工肢体和辅助设备的自然人机接口。然而,这种生物信号实时控制接口仍然存在一些限制,例如由于缺乏可靠的信号预测和研究小组之间的信号处理标准,导致控制受限。我们的论文旨在通过使用可靠形式的极端学习机 (ELM) 分类器对信号进行分类来展示和验证我们的 sEMG 数据库,以保持更一致的信号分类。为了进行信号处理,我们探索了基于 Antonyan Vardan 变换 (AVT) 的随机滤波器与我们的两种可靠分类器 (分别表示为 R-ELM 和 R-正则化 ELM (RELM)) 的结合使用,从系统中得出可靠性指标,该指标自动为信号分类选择最可靠的样本。为了验证和比较我们的数据库和分类器与相关论文,我们对 NINAPro 数据库的数据库 1、2 和 6 (DB1、DB2 和 DB6) 进行了分类。我们的数据库呈现出一致的结果,而 ELM 分类器的可靠形式与相关论文相匹配或超过了相关论文,在 IEEdatabase 上的平均准确率达到了 99%以上,而在 NINAPro DB1、DB2 和 DB6 上的平均准确率分别达到了 75.1%、79.77%和 69.83%。