Match!

Transfer Learning for Rapid Re-calibration of a Myoelectric Prosthesis After Electrode Shift

Published on Jan 1, 2017
· DOI :10.1007/978-3-319-46669-9_28
Cosima Prahm5
Estimated H-index: 5
(Medical University of Vienna),
Benjamin Paaßen7
Estimated H-index: 7
(Citec)
+ 2 AuthorsOskar C. Aszmann25
Estimated H-index: 25
(Medical University of Vienna)
Abstract
For decades, researchers have attempted to provide patients with an intuitive method to control upper limb prostheses, enabling them to manipulate multiple degrees of freedom continuously and simultaneously using only simple myoelectric signals. However, such controlling schemes are still highly vulnerable to disturbances in the myoelectric signal, due to electrode shifts, posture changes, sweat, fatigue etc. Recent research has demonstrated that such robustness problems can be alleviated by rapid re-calibration of the prosthesis once a day, using only very small amounts of training data (less than one minute of training time). In this contribution, we propose such a re-calibration scheme for a pattern recognition controller based on transfer learning. In a pilot study with able-bodied subjects we demonstrate that high controller accuracy can be re-obtained after strong electrode shift, even for simultaneous movements in multiple degrees of freedom.
  • References (12)
  • Citations (12)
📖 Papers frequently viewed together
2018EMBC: International Conference of the IEEE Engineering in Medicine and Biology Society
27 Citations
1991
3 Authors (B. Hudgins, ..., R. N. Scott)
10 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References12
Newest
#1Marina M.-C. Vidovic (Technical University of Berlin)H-Index: 4
#2Han-Jeong Hwang (Technical University of Berlin)H-Index: 16
Last. Klaus-Robert Müller (Technical University of Berlin)H-Index: 4
view all 6 authors...
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 E...
29 CitationsSource
#1Janne M. Hahne (GAU: University of Göttingen)H-Index: 9
#2Dario Farina (GAU: University of Göttingen)H-Index: 76
Last. David Liebetanz (GAU: University of Göttingen)H-Index: 35
view all 4 authors...
Despite several decades of research, electrically powered hand and arm prostheses are still controlled with very simple algorithms that process the surface electromyogram (EMG) of remnant muscles to achieve control of one prosthetic function at a time. More advanced machine learning methods have shown promising results under laboratory conditions. However, limited robustness has largely prevented the transfer of these laboratory advances to clinical applications. In this paper, we introduce a no...
9 CitationsSource
#1Antonietta Stango (GAU: University of Göttingen)H-Index: 4
#2Francesco Negro (GAU: University of Göttingen)H-Index: 46
Last. Dario Farina (GAU: University of Göttingen)H-Index: 76
view all 3 authors...
Research on pattern recognition for myoelectric control has usually focused on a small number of electromyography (EMG) channels because of better clinical acceptability and low computational load with respect to multi-channel EMG. However, recently, high density (HD) EMG technology has substantially improved, also in practical usability, and can thus be applied in myocontrol. HD EMG provides several closely spaced recordings in multiple locations over the skin surface. This study considered the...
61 CitationsSource
#1Rami N. Khushaba (UTS: University of Technology, Sydney)H-Index: 19
#2Maen Takruri (American University of Ras Al Khaimah)H-Index: 9
Last. Sarath Kodagoda (UTS: University of Technology, Sydney)H-Index: 18
view all 4 authors...
Abstract Recent studies in Electromyogram (EMG) pattern recognition reveal a gap between research findings and a viable clinical implementation of myoelectric control strategies. One of the important factors contributing to the limited performance of such controllers in practice is the variation in the limb position associated with normal use as it results in different EMG patterns for the same movements when carried out at different positions. However, the end goal of the myoelectric control sc...
62 CitationsSource
#1Dario Farina (GAU: University of Göttingen)H-Index: 76
#2Ning Jiang (GAU: University of Göttingen)H-Index: 29
Last. Oskar C. Aszmann (Medical University of Vienna)H-Index: 25
view all 7 authors...
Despite not recording directly from neural cells, the surface electromyogram (EMG) signal contains information on the neural drive to muscles, i.e, the spike trains of motor neurons. Using this property, myoelectric control consists of the recording of EMG signals for extracting control signals to command external devices, such as hand prostheses. In commercial control systems, the intensity of muscle activity is extracted from the EMG and used for single degrees of freedom activation (direct co...
290 CitationsSource
#1Silvia Muceli (GAU: University of Göttingen)H-Index: 17
#2Ning Jiang (GAU: University of Göttingen)H-Index: 29
Last. Dario Farina (GAU: University of Göttingen)H-Index: 76
view all 3 authors...
Previous research proposed the extraction of myoelectric control signals by linear factorization of multi-channel electromyogram (EMG) recordings from forearm muscles. This paper further analyses the theoretical basis for dimensionality reduction in high-density EMG signals from forearm muscles. Moreover, it shows that the factorization of muscular activation patterns in weights and activation signals by non-negative matrix factorization (NMF) is robust with respect to the channel configuration ...
79 CitationsSource
#1Sebastian Amsüss (GAU: University of Göttingen)H-Index: 5
#2Peter M. GoebelH-Index: 5
Last. Dario Farina (GAU: University of Göttingen)H-Index: 76
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...
88 CitationsSource
#1Janne M. HahneH-Index: 9
#2F. BiebmannH-Index: 1
Last. Lucas C. Parra (CCNY: City College of New York)H-Index: 51
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...
136 CitationsSource
#1Max Ortiz-Catalan (Chalmers University of Technology)H-Index: 11
#2Rickard Brånemark (Sahlgrenska University Hospital)H-Index: 33
Last. Bo Håkansson (Chalmers University of Technology)H-Index: 28
view all 3 authors...
Background Processing and pattern recognition of myoelectric signals have been at the core of prosthetic control research in the last decade. Although most studies agree on reporting the accuracy of predicting predefined movements, there is a significant amount of study-dependent variables that make high-resolution inter-study comparison practically impossible. As an effort to provide a common research platform for the development and evaluation of algorithms in prosthetic control, we introduce ...
81 CitationsSource
#1Guy N. Brock (University of Louisville)H-Index: 28
#2Partha Mukhopadhyay (University of Louisville)H-Index: 15
Last. M. Michele Pisano (University of Louisville)H-Index: 22
view all 6 authors...
Background MicroRNAs (miRNAs) constitute the largest family of noncoding RNAs involved in gene silencing and represent critical regulators of cell and tissue differentiation. Microarray expression profiling of miRNAs is an effective means of acquiring genome-level information of miRNA activation and inhibition, as well as the potential regulatory role that these genes play within a biological system. As with mRNA expression profiling arrays, miRNA microarrays come in a variety of platforms from ...
24 CitationsSource
Cited By12
Newest
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
#1Philip P. Vu (UM: University of Michigan)H-Index: 3
#2Cynthia A. ChestekH-Index: 23
Last. Paul S. Cederna (UM: University of Michigan)H-Index: 27
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...
Source
An important barrier to commercialization of pattern recognition myoelectric control of prostheses is the lack of robustness to confounding factors such as electrode shift, skin impedance variations, and learning effects. To overcome this challenge, a novel supervised adaptation approach based on transfer learning (TL) with convolutional neural networks (CNNs) is proposed which requires only a short training session (a few seconds for each class) to recalibrate the system. TL is proposed as a so...
Source
Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system's performance over multiple days is challenging, due to the transient nature of this recording technique. In practice, if the system is to remain usable, a time-consuming and periodic re-calibration is necessary. In the case where the sEMG interface is employed every few days, the user might need to do this re-calibration before every...
#1Cosima Prahm (Medical University of Vienna)H-Index: 5
#2Alexander SchulzH-Index: 38
Last. Oskar C. Aszmann (Medical University of Vienna)H-Index: 25
view all 8 authors...
Research on machine learning approaches for upper-limb prosthesis control has shown impressive progress. However, translating these results from the lab to patient’s everyday lives remains a challenge because advanced control schemes tend to break down under everyday disturbances, such as electrode shifts. Recently, it has been suggested to apply adaptive transfer learning to counteract electrode shifts using as little newly recorded training data as possible. In this paper, we present a novel, ...
Source
#1Sebastian Bittrich (TUD: Dresden University of Technology)H-Index: 3
#2Marika KadenH-Index: 7
Last. Dirk LabuddeH-Index: 6
view all 6 authors...
Background Machine learning strategies are prominent tools for data analysis. Especially in life sciences, they have become increasingly important to handle the growing datasets collected by the scientific community. Meanwhile, algorithms improve in performance, but also gain complexity, and tend to neglect interpretability and comprehensiveness of the resulting models.
1 CitationsSource
#1Benjamin Paaßen (Bielefeld University)H-Index: 7
#2Alexander Schulz (Bielefeld University)H-Index: 38
Last. Barbara Hammer (Bielefeld University)H-Index: 33
view all 4 authors...
Abstract Machine learning models in practical settings are typically confronted with changes to the distribution of the incoming data. Such changes can severely affect the model performance, leading for example to misclassifications of data. This is particularly apparent in the domain of bionic hand prostheses, where machine learning models promise faster and more intuitive user interfaces, but are hindered by their lack of robustness to everyday disturbances, such as electrode shifts. One way t...
3 CitationsSource
Jul 1, 2018 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
#1Suguru Kanogal (AIST: National Institute of Advanced Industrial Science and Technology)
#2Masashi Matsuokal (AIST: National Institute of Advanced Industrial Science and Technology)
Last. Atsunori Kanemura (AIST: National Institute of Advanced Industrial Science and Technology)H-Index: 5
view all 3 authors...
Wearable sensors for upper limbs enable the use of myoelectric control systems in real environments. An important issue in the practical use of myoelectric control is how to deal with the variations of electromyograms (EMGs); the distribution of EMGs changes over days and device (electrode) positions. The amount of training data is usually limited, as the data are collected at the beginning of the system use. To compensate for the difference of EMGs over time and device placement with limited-am...
1 CitationsSource
Feb 1, 2018 in ICIT (International Conference on Industrial Technology)
#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
A motion recognition module integrated into the myoelectric control system learns the parameters of the classifier using training data recorded during multiple days. However, such module will experience troubles (decreases in recognition accuracy) in daily life because the electrode position of the operation day is slightly different from past days. This paper aims to adjust model parameters using transfer learning and assess its performance. Twenty-two kinds of motions in free space were observ...
2 CitationsSource
Jun 21, 2017 in AIME (Artificial Intelligence in Medicine in Europe)
#1Cosima Prahm (Medical University of Vienna)H-Index: 5
#2Alexander Schulz (Bielefeld University)H-Index: 38
Last. Georg Dorffner (Medical University of Vienna)H-Index: 27
view all 6 authors...
Myoelectric signals (EMG) provide an intuitive and rapid interface for controlling technical devices, in particular bionic arm prostheses. However, inferring the intended movement from a surface EMG recording is a non-trivial pattern recognition task, especially if the data stems from low-cost sensors. At the same time, overly complex models are prohibited by strict speed, data parsimony and robustness requirements. As a compromise between high accuracy and strict requirements we propose to appl...
2 CitationsSource