CNN Confidence Estimation for Rejection-Based Hand Gesture Classification in Myoelectric Control
CNN Confidence Estimation for Rejection-Based Hand Gesture Classification in Myoelectric Control
复制标题
DOI：
10.1109/thms.2021.3123186
复制
发表时间：
2021-11-15
影响因子：
3.6
通讯作者：
Zhang, Zhi-Qiang
中科院分区：
文献类型：
--
作者：
Bao, Tianzhe;Zaidi, Syed Ali Raza;Zhang, Zhi-Qiang
卷积神经网络（CNN）已被广泛用于从表面肌电信号（sEMG）中识别手势。然而，由于表面肌电信号的非平稳特性，在涉及复杂手部运动的日常生活环境中，分类精度通常会显着下降。为了进一步提高分类器的可靠性，期望识别和拒绝不可信的分类。在这项研究中，我们提出了一种新的方法来估计每个分类的正确性概率。具体而言，建立置信度估计模型以基于CNN的后验概率生成置信度得分（ConfScore），并设计目标函数来训练该模型的参数。此外，提出了一种结合真实接受率（TAR）和真实拒绝率（TRR）的综合指标来评价ConfScore的拒绝性能，从而充分考虑了系统安全性和控制滞后之间的权衡。ConfScore的有效性是使用公共数据库和我们的在线平台的数据进行验证的。实验结果表明，与传统的置信度特征相比，ConfScore能够更好地反映CNN分类的正确性，最大后验概率和概率向量的熵。此外，抑制性能被观察到对抑制阈值的变化不太敏感。
Convolutional neural networks (CNNs) have been widely utilized to identify hand gestures from surface electromyography (sEMG) signals. However, due to the nonstationary characteristics of sEMG, the classification accuracy usually degrades significantly in the daily living environment involving complex hand movements. To further improve the reliability of a classifier, unconfident classifications are expected to be identified and rejected. In this study, we propose a novel approach to estimate the probability of correctness for each classification. Specifically, a confidence estimation model is established to generate confidence scores (ConfScore) based on posterior probabilities of CNN, and an objective function is designed to train the parameters of this model. In addition, a comprehensive metric that combines the true acceptance rate (TAR) and the true rejection rate (TRR) is proposed to evaluate the rejection performance of ConfScore, so that the tradeoff between system security and control lag could be fully considered. The effectiveness of ConfScore is verified using data from public databases and our online platform. The experimental results illustrate that ConfScore can better reflect the correctness of CNN classifications than traditional confidence features, i.e., maximum posterior probability and entropy of the probability vector. Moreover, the rejection performance is observed to be less sensitive to variations in rejection thresholds.