Deep Learning Movement Intent Decoders Trained With Dataset Aggregation for Prosthetic Limb Control

• Published in: IEEE transactions on biomedical engineering 2019-11, Vol.66 (11), p.3192-3203
• Main Authors: Dantas, Henrique, Warren, David J., Wendelken, Suzanne M., Davis, Tyler S., Clark, Gregory A., Mathews, V John
• Format: Article
• Language: English
• Subjects: Agglomeration; Algorithms; Amputation; Amputees; Artificial Limbs; Artificial neural networks; Biology; Biomedical Engineering; Biomedical signal processing; Datasets; Decoders; Decoding; Deep Learning; Electromyography; Electromyography - methods; Error analysis; Humans; Intention; Kalman filter; Kalman filters; Kinematics; learning systems; Long short-term memory; machine learning; motor intent decoder; Movement - physiology; Multilayer perceptrons; neural engineering; neural network; Neural networks; Performance evaluation; Polynomials; Prostheses; Quality of life; reinforcement learning; Signal Processing, Computer-Assisted; Task analysis; Testing; Training
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2019.2901882

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.