Deep Learning Movement Intent Decoders Trained With Dataset Aggregation for Prosthetic Limb Control
Deep Learning Movement Intent Decoders Trained With Dataset Aggregation for Prosthetic Limb Control
复制标题
DOI：
10.1109/tbme.2019.2901882
复制
发表时间：
2019-11-01
影响因子：
4.6
通讯作者：
Mathews, V. John
中科院分区：
文献类型：
--
作者：
Dantas, Henrique;Warren, David J.;Mathews, V. John
重要性：从肌电图（EMG）和其他生物信号解码运动意图的传统方法的性能通常随着时间而降低。此外，用于训练基于神经网络的解码器的常规算法在训练期间观察到的状态转变的域之外可能不能很好地执行。本文中提出的工作缓解了这两个问题，从而产生了一种有可能大幅改善肢体丧失患者生活质量的方法。目的：研究肌电信号中自主运动意图的四种解码方法，并对其性能进行评价。研究方法：解码器使用数据集聚合（Dagger）算法进行训练，其中训练数据集在每次训练迭代期间基于来自先前迭代的解码估计进行扩充。开发了四种竞争解码方法，即多项式卡尔曼滤波器（KF），多层感知器（MLP）网络，卷积神经网络（CNN）和长短期记忆（LSTM）网络。四种解码方法的性能进行了评估，使用肌电图数据集记录从两个人类志愿者经桡动脉截肢。进行了短期分析，其中训练和交叉验证数据来自相同的数据集，以及长期分析，其中训练和测试在不同的数据集中进行。结果如下：对解码器的短期分析表明，CNN和MLP解码器的性能明显优于KF和LSTM解码器，在交叉验证测试中，归一化均方解码误差提高了60%。长期分析表明，CNN、MLP和LSTM解码器在训练和测试数据集采集之间的时间间隔（0-150天）的大多数分析情况下的性能明显优于基于KF的解码器。结论：短期和长期的表现MLP和CNN为基础的解码器训练Dagger证明了他们的潜力，提供更准确和自然的控制假肢手比替代方法。
Significance: The performance of traditional approaches to decoding movement intent from electromyograms (EMGs) and other biological signals commonly degrade over time. Furthermore, conventional algorithms for training neural network based decoders may not perform well outside the domain of the state transitions observed during training. The work presented in this paper mitigates both these problems, resulting in an approach that has the potential to substantially improve the quality of life of the people with limb loss. Objective: This paper presents and evaluates the performance of four decoding methods for volitional movement intent from intramuscular EMG signals. Methods: The decoders are trained using the dataset aggregation (DAgger) algorithm, in which the training dataset is augmented during each training iteration based on the decoded estimates from previous iterations. Four competing decoding methods, namely polynomial Kalman filters (KFs), multilayer perceptron (MLP) networks, convolutional neural networks (CNN), and long short-term memory (LSTM) networks, were developed. The performances of the four decoding methods were evaluated using EMG datasets recorded from two human volunteers with transradial amputation. Short-term analyses, in which the training and cross-validation data came from the same dataset, and long-term analyses, in which the training and testing were done in different datasets, were performed. Results: Short-term analyses of the decoders demonstrated that CNN and MLP decoders performed significantly better than KF and LSTM decoders, showing an improvement of up to 60% in the normalized mean-square decoding error in cross-validation tests. Long-term analyses indicated that the CNN, MLP, and LSTM decoders performed significantly better than a KF-based decoder at most analyzed cases of temporal separations (0-150 days) between the acquisition of the training and testing datasets. Conclusion: The short-term and long-term performances of MLP- and CNN-based decoders trained with DAgger demonstrated their potential to provide more accurate and naturalistic control of prosthetic hands than alternate approaches.