IEEE J Biomed Health Inform. 2019 Jul;23(4):1526-1534. doi: 10.1109/JBHI.2018.2864335. Epub 2018 Aug 8.
Currently, most of the adopted myoelectric schemes for upper limb prostheses do not provide users with intuitive control. Higher accuracies have been reported using different classification algorithms but investigation on the reliability over time for these methods is very limited. In this study, we compared for the first time the longitudinal performance of selected state-of-the-art techniques for electromyography (EMG) based classification of hand motions. Experiments were conducted on ten able-bodied and six transradial amputees for seven continuous days. Linear discriminant analysis (LDA), artificial neural network (ANN), support vector machine (SVM), K-nearest neighbor (KNN), and decision trees (TREE) were compared. Comparative analysis showed that the ANN attained highest classification accuracy followed by LDA. Three-way repeated ANOVA test showed a significant difference (P < 0.001) between EMG types (surface, intramuscular, and combined), days (1-7), classifiers, and their interactions. Performance on the last day was significantly better (P < 0.05) than the first day for all classifiers and EMG types. Within-day, classification error (WCE) across all subject and days in ANN was: surface (9.12 ± 7.38%), intramuscular (11.86 ± 7.84%), and combined (6.11 ± 7.46%). The between-day analysis in a leave-one-day-out fashion showed that the ANN was the optimal classifier (surface (21.88 ± 4.14%), intramuscular (29.33 ± 2.58%), and combined (14.37 ± 3.10%). Results indicate that within day performances of classifiers may be similar but over time, it may lead to a substantially different outcome. Furthermore, training ANN on multiple days might allow capturing time-dependent variability in the EMG signals and thus minimizing the necessity for daily system recalibration.
目前，大多数用于上肢假肢的肌电方案都不能为用户提供直观的控制。使用不同的分类算法可以报告更高的准确性，但对这些方法随时间的可靠性的研究非常有限。在这项研究中，我们首次比较了用于手部运动肌电（EMG）分类的选定最先进技术的纵向性能。在十名健全人和六名桡骨截肢者中进行了为期七天的连续实验。比较了线性判别分析（LDA）、人工神经网络（ANN）、支持向量机（SVM）、K 最近邻（KNN）和决策树（TREE）。对比分析表明，ANN 获得了最高的分类准确性，其次是 LDA。三向重复方差分析测试显示 EMG 类型（表面、肌内和组合）、天数（1-7）、分类器及其相互作用之间存在显著差异（P < 0.001）。所有分类器和 EMG 类型的最后一天的性能明显优于第一天（P < 0.05）。在日内，ANN 在所有受试者和所有日内的分类误差（WCE）为：表面（9.12 ± 7.38%）、肌内（11.86 ± 7.84%）和组合（6.11 ± 7.46%）。在一日一留的方式进行的日内分析表明，ANN 是最优的分类器（表面（21.88 ± 4.14%）、肌内（29.33 ± 2.58%）和组合（14.37 ± 3.10%）。结果表明，分类器的日内性能可能相似，但随着时间的推移，可能会导致截然不同的结果。此外，在多日内对 ANN 进行训练可能允许捕获 EMG 信号中的时间相关变化，从而最大限度地减少对每日系统重新校准的需求。
