Abstract
Abstract
Background
Advanced prostheses can restore function and improve quality of life for individuals with amputations. Unfortunately, most commercial control strategies do not fully utilize the rich control information from residual nerves and musculature. Continuous decoders can provide more intuitive prosthesis control using multi-channel neural or electromyographic recordings. Three components influence continuous decoder performance: the data used to train the algorithm, the algorithm, and smoothing filters on the algorithm’s output. Individual groups often focus on a single decoder, so very few studies compare different decoders using otherwise similar experimental conditions.
Methods
We completed a two-phase, head-to-head comparison of 12 continuous decoders using activities of daily living. In phase one, we compared two training types and a smoothing filter with three algorithms (modified Kalman filter, multi-layer perceptron, and convolutional neural network) in a clothespin relocation task. We compared training types that included only individual digit and wrist movements vs. combination movements (e.g., simultaneous grasp and wrist flexion). We also compared raw vs. nonlinearly smoothed algorithm outputs. In phase two, we compared the three algorithms in fragile egg, zipping, pouring, and folding tasks using the combination training and smoothing found beneficial in phase one. In both phases, we collected objective, performance-based (e.g., success rate), and subjective, user-focused (e.g., preference) measures.
Results
Phase one showed that combination training improved prosthesis control accuracy and speed, and that the nonlinear smoothing improved accuracy but generally reduced speed. Phase one importantly showed simultaneous movements were used in the task, and that the modified Kalman filter and multi-layer perceptron predicted more simultaneous movements than the convolutional neural network. In phase two, user-focused metrics favored the convolutional neural network and modified Kalman filter, whereas performance-based metrics were generally similar among all algorithms.
Conclusions
These results confirm that state-of-the-art algorithms, whether linear or nonlinear in nature, functionally benefit from training on more complex data and from output smoothing. These studies will be used to select a decoder for a long-term take-home trial with implanted neuromyoelectric devices. Overall, clinical considerations may favor the mKF as it is similar in performance, faster to train, and computationally less expensive than neural networks.
Funder
Defense Advanced Research Projects Agency
National Center for Advancing Translational Sciences
Publisher
Springer Science and Business Media LLC
Subject
Health Informatics,Rehabilitation
Reference91 articles.
1. Mobius Bionics LLC. LUKE Arm System.. 2019. https://www.mobiusbionics.com/wp-content/uploads/2019/09/Mobius-Bionics-LUKE-Product-Spec-Sheet.pdf.
2. Taska Prosthetics. TASKA Hand. 2020. https://www.taskaprosthetics.com/the-taska. Accessed 8 Jul 2020.
3. Otto Bock HealthCare LP. Bebionic hand User Guide. 2018. https://www.ottobock.ca/media/local-media/prosthetics/upper-limb/files/15667-bebionic-user-guide.pdf.
4. Otto Bock HealthCare LP. Michelangelo Hand Brochure. 2017. http://www.ottobockus.com/media/local-media/prosthetics/upper-limb/michelangelo/files/michelangelo-brochure.pdf.
5. Motion Control Division of Fillauer. Utah Arm U3 and U3+ User Guide. 2020. https://fillauer.com/wp-content/uploads/2020/09/1910025-USER-GUIDE-Utah-Arm-U3-and-U3-Plus-Rev-C-08-24-2020.pdf.
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Adaptations of Neuroprostheses for Training: A Technological and Systematic Review;2023 IEEE XXX International Conference on Electronics, Electrical Engineering and Computing (INTERCON);2023-11-02
2. Correcting Temporal Inaccuracies in Labeled Training Data for Electromyographic Control Algorithms;2023 International Conference on Rehabilitation Robotics (ICORR);2023-09-24
3. Automated Quantifiable Assessments of Sensorimotor Function Using an Instrumented Fragile Object;2023 International Conference on Rehabilitation Robotics (ICORR);2023-09-24
4. Impact of Measurement Conditions on Classification of ADL using Surface EMG Signals;2023 International Symposium on Image and Signal Processing and Analysis (ISPA);2023-09-18
5. Advances in artificial muscles: A brief literature and patent review;Frontiers in Bioengineering and Biotechnology;2023-01-19