Match!

Improving the Robustness of Myoelectric Pattern Recognition for Upper Limb Prostheses by Covariate Shift Adaptation

Published on Sep 1, 2016in IEEE Transactions on Neural Systems and Rehabilitation Engineering3.478
· DOI :10.1109/TNSRE.2015.2492619
Marina M.-C. Vidovic5
Estimated H-index: 5
(Technical University of Berlin),
Han-Jeong Hwang19
Estimated H-index: 19
(Technical University of Berlin)
+ 3 AuthorsKlaus-Robert Müller93
Estimated H-index: 93
(Technical University of Berlin)
Abstract
Fundamental changes over time of surface EMG signal characteristics are a challenge for myocontrol algorithms controlling prosthetic devices. These changes are generally caused by electrode shifts after donning and doffing, sweating, additional weight or varying arm positions, which results in a change of the signal distribution - a scenario often referred to as covariate shift. A substantial decrease in classification accuracy due to these factors hinders the possibility to directly translate EMG signals into accurate myoelectric control patterns outside laboratory conditions. To overcome this limitation, we propose the use of supervised adaptation methods. The approach is based on adapting a trained classifier using a small calibration set only, which incorporates the relevant aspects of the nonstationarities, but requires only less than 1 min of data recording. The method was tested first through an offline analysis on signals acquired across 5 days from seven able-bodied individuals and four amputees. Moreover, we also conducted a three day online experiment on eight able-bodied individuals and one amputee, assessing user performance and user-ratings of the controllability. Across different testing days, both offline and online performance improved significantly when shrinking the training model parameters by a given estimator towards the calibration set parameters. In the offline data analysis, the classification accuracy remained above 92% over five days with the proposed approach, whereas it decreased to 75% without adaptation. Similarly, in the online study, with the proposed approach the performance increased by 25% compared to a test without adaptation. These results indicate that the proposed methodology can contribute to improve robustness of myoelectric pattern recognition methods in daily life applications.
  • References (23)
  • Citations (47)
📖 Papers frequently viewed together
486 Citations
968 Citations
343 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References23
Newest
#1Ali H. Al-Timemy (UOB: University of Baghdad)H-Index: 9
#2Rami N. Khushaba (UTS: University of Technology, Sydney)H-Index: 20
Last. Javier Escudero (Edin.: University of Edinburgh)H-Index: 25
view all 4 authors...
We investigate the problem of achieving robust control of hand prostheses by the electromyogram (EMG) of transradial amputees in the presence of variable force levels, as these variations can have a substantial impact on the robustness of the control of the prostheses. We also propose a novel set of features that aim at reducing the impact of force level variations on the prosthesis controlled by amputees. These features characterize the EMG activity by means of the orientation between a set of ...
94 CitationsSource
#1Janne M. HahneH-Index: 10
#2Sven DähneH-Index: 22
Last. Lucas C. Parra (CCNY: City College of New York)H-Index: 54
view all 5 authors...
Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation o...
30 CitationsSource
Nov 6, 2014 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
#1Marina M.-C. Vidovic (Technical University of Berlin)H-Index: 5
#2Liliana P. ParedesH-Index: 6
Last. Klaus-Robert Müller (Technical University of Berlin)H-Index: 4
view all 9 authors...
: Ensuring robustness of myocontrol algorithms for prosthetic devices is an important challenge. Robustness needs to be maintained under nonstationarities, e.g. due to electrode shifts after donning and doffing, sweating, additional weight or varying arm positions. Such nonstationary behavior changes the signal distributions - a scenario often referred to as covariate shift. This circumstance causes a significant decrease in classification accuracy in daily life applications. Re-training is poss...
5 CitationsSource
#1Han-Jeong Hwang (Technical University of Berlin)H-Index: 19
#2Janne M. Hahne (Technical University of Berlin)H-Index: 10
Last. Klaus-Robert MüllerH-Index: 93
view all 3 authors...
Objective. Recent studies have shown the possibility of simultaneous and proportional control of electrically powered upper-limb prostheses, but there has been little investigation on optimal channel selection. The objective of this study is to find a robust channel selection method and the channel subsets most suitable for simultaneous and proportional myoelectric prosthesis control of multiple degrees-of-freedom (DoFs). Approach. Ten able-bodied subjects and one person with congenital upper-li...
19 CitationsSource
#1Ning Jiang (GAU: University of Göttingen)H-Index: 31
#2Ivan VujaklijaH-Index: 13
Last. Dario Farina (GAU: University of Göttingen)H-Index: 80
view all 5 authors...
In this paper, we present a systematic analysis of the relationship between the accuracy of the mapping between EMG and hand kinematics and the control performance in goal-oriented tasks of three simultaneous and proportional myoelectric control algorithms: nonnegative matrix factorization (NMF), linear regression (LR), and artificial neural networks (ANN). The purpose was to investigate the impact of the precision of the kinematics estimation by a myoelectric controller for accurately complete ...
122 CitationsSource
#1Sebastian Amsüss (GAU: University of Göttingen)H-Index: 5
#2Peter M. GoebelH-Index: 5
Last. Dario Farina (GAU: University of Göttingen)H-Index: 80
view all 6 authors...
Pattern recognition methods for classifying user motion intent based on surface electromyography developed by research groups in well-controlled laboratory conditions are not yet clinically viable for upper limb prosthesis control, due to their limited robustness in users' real-life situations. To address this problem, a novel postprocessing algorithm, aiming to detect and remove misclassifications of a pattern recognition system of forearm and hand motions, is proposed. Using the maximum likeli...
104 CitationsSource
#1Janne M. HahneH-Index: 10
#2F. BiebmannH-Index: 1
Last. Lucas C. Parra (CCNY: City College of New York)H-Index: 54
view all 8 authors...
In recent years the number of active controllable joints in electrically powered hand-prostheses has increased significantly. However, the control strategies for these devices in current clinical use are inadequate as they require separate and sequential control of each degree-of-freedom (DoF). In this study we systematically compare linear and nonlinear regression techniques for an independent, simultaneous and proportional myoelectric control of wrist movements with two DoF. These techniques i...
169 CitationsSource
#1Xinpu Chen (SJTU: Shanghai Jiao Tong University)H-Index: 4
#2Dingguo Zhang (SJTU: Shanghai Jiao Tong University)H-Index: 21
Last. Xiangyang Zhu (SJTU: Shanghai Jiao Tong University)H-Index: 26
view all 3 authors...
Background The nonstationary property of electromyography (EMG) signals usually makes the pattern recognition (PR) based methods ineffective after some time in practical application for multinational prosthesis. The conventional EMG PR, which is accomplished in two separate steps: training and testing, ignores the mismatch between training and testing conditions and often discards the useful information in testing dataset.
73 CitationsSource
Oct 3, 2012 in ICIRA (International Conference on Intelligent Robotics and Applications)
#1Jiayuan He (SJTU: Shanghai Jiao Tong University)H-Index: 8
#2Dingguo Zhang (SJTU: Shanghai Jiao Tong University)H-Index: 21
Last. Xiangyang Zhu (SJTU: Shanghai Jiao Tong University)H-Index: 26
view all 3 authors...
Towards the real-world application of multifunctional prostheses based on electromyography (EMG) signal, an unsupervised adaptive myoelectric control approach was presented in order to improve the long-time classification performance of EMG pattern recognition. The widely-used linear discriminant analysis (LDA) was improved to three new different classifiers separately termed as linear discriminant analysis with single pattern updating (SPLDA), linear discriminant analysis with multiple patterns...
12 CitationsSource
Pattern recognition techniques have been applied to extract information from electromyographic (EMG) signals that can be used to control electrical powered hand prostheses. In this paper, optimized spatial filters that enhance separation properties of EMG signals are investigated. In particular, different multiclass extensions of the common spatial patterns algorithm are applied to high-density surface EMG signals acquired from the forearms of ten healthy subjects. Visualization of the obtained ...
63 CitationsSource
Cited By47
Newest
#1Ashirbad Pradhan (UNB: University of New Brunswick)
#2Ning Jiang (UW: University of Waterloo)
Last. Usha Kuruganti (UNB: University of New Brunswick)H-Index: 10
view all 4 authors...
Abstract Myoelectric controlled prostheses systems have evolved significantly over the last few decades, however, there remains a need for more robust systems. Clinically, prosthesis control schemes must be robust to various Electromyography (EMG) signal non-stationarities such as unintended activations and contraction level variations to ensure appropriate operation of the prosthesis. This study compared performance measures between two control schemes, linear regression with frequency division...
Source
#1Xu ZhangH-Index: 15
#2Le WuH-Index: 1
Last. Xun Chen (USTC: University of Science and Technology of China)H-Index: 20
view all 5 authors...
The shift of surface electrodes during their replacement is a key issue that compromises myoelectric control performance and hinders its practical applications. High-density surface electromyogram signals recorded from a two-dimensional electrode array carry rich spatial information and can serve as a muscular activation image. Inspired by the idea of image object detection, a novel method is proposed in this paper for myoelectric pattern recognition that enables adaptive calibration of an elect...
2 CitationsSource
#1Suguru Kanoga (AIST: National Institute of Advanced Industrial Science and Technology)H-Index: 3
#2Atsunori Kanemura (AIST: National Institute of Advanced Industrial Science and Technology)H-Index: 5
Last. Hideki Asoh (AIST: National Institute of Advanced Industrial Science and Technology)H-Index: 21
view all 3 authors...
Abstract Myoelectric control systems (MCSs), which recognize motions through surface electromyograms (sEMGs), present potential applicability for clinical, recreational, and motion-assisting purposes. To increase the adoption of armband device-based MCSs, the performance of motion recognition algorithms should be determined over long periods and sensor placement shifts. We prepared an sEMG dataset to assess motion recognition algorithms for practical use over long periods with varying sensor pla...
Source
#1Janne M. Hahne (GAU: University of Göttingen)H-Index: 10
#2Meike A. Schweisfurth (Hamburg University of Applied Sciences)H-Index: 8
Last. Arndt F. Schilling (GAU: University of Göttingen)H-Index: 33
view all 5 authors...
Hand prostheses are usually controlled by electromyographic (EMG) signals from the remnant muscles of the residual limb. Most prostheses used today are controlled with very simple techniques using only two EMG electrodes that allow to control a single prosthetic function at a time only. Recently, modern prosthesis controllers based on EMG classification, have become clinically available, which allow to directly access more functions, but still in a sequential manner only. We have recently shown ...
Source
#1Philip P. Vu (UM: University of Michigan)H-Index: 4
#2Cynthia A. ChestekH-Index: 24
Last. Paul S. Cederna (UM: University of Michigan)H-Index: 29
view all 6 authors...
: The loss of upper limb motor function can have a devastating effect on people's lives. To restore upper limb control and functionality, researchers and clinicians have developed interfaces to interact directly with the human body's motor system. In this invited review, we aim to provide details on the peripheral nerve interfaces and brain-machine interfaces that have been developed in the past 30 years for upper extremity control, and we highlight the challenges that still remain to transition...
1 CitationsSource
#1Hanadi Abbas JaberH-Index: 2
Last. Luigi FortunaH-Index: 27
view all 3 authors...
1 CitationsSource
#1Xingchen Yang (SJTU: Shanghai Jiao Tong University)H-Index: 4
#2Jipeng Yan (SJTU: Shanghai Jiao Tong University)H-Index: 2
Last. Hongxuan LiuH-Index: 96
view all 5 authors...
The ability to predict wrist and hand motions simultaneously is essential for natural controls of hand protheses. In this paper, we propose a novel method that includes subclass discriminant analysis (SDA) and principal component analysis for the simultaneous prediction of wrist rotation (pronation/ supination) and finger gestures using wearable ultrasound. We tested the method on eight finger gestures with concurrent wrist rotations. Results showed that SDA was able to achieve accurate classifi...
Source
Abstract One of the most common issue in surface electromyography (sEMG) based myocontrol is to set a recurrent feature which allows to ensure a reliable multi degree of freedom (MDoF) prosthetic drive, mainly due to non-stationary behavior of signal. According to studies, electrode placement and shifts, variation in muscle contraction effort and muscle fatigue are the most common disturbance sources in sEMG recording, which traduces into a cumbersome donning and doffing recalibration. Many rele...
Source
#1Junchu Huang (SCUT: South China University of Technology)H-Index: 1
#2Zhiheng Zhou (SCUT: South China University of Technology)H-Index: 3
Last. Chang Niu (SCUT: South China University of Technology)H-Index: 1
view all 4 authors...
Heterogeneous domain adaptation is a challenging problem due to the fact that it requires generalizing a learning model across training data and testing data with different distributions and features. To alleviate the difficulty of this task, most researchers usually perform some data preprocessing operations. However, such operations may lead to the loss of shareable information before domain adaptation. Moreover, most current work neglects the structural information between data, which is cruc...
Source
#1Pandia Rajan Jeyaraj (Mepco Schlenk Engineering College)H-Index: 2
#2Edward Rajan Samuel Nadar (Mepco Schlenk Engineering College)H-Index: 3
In this research paper we present designing and evaluating the electrocardiography (ECG) and Myoelectric signal (EMG) pattern recognition methods based on the adaptive machine learning. For this theoretical model to describe how the Boundary Misclassification Risk (BMR) changes along parameters including, the adaptive learning times, the adaptive learning frequencies, the generalization ability of the predictive model, and the ratio of samples without supervised information during the adaptive l...
Source