Spatial Filtering for Robust Myoelectric Control

Published on May 1, 2012in IEEE Transactions on Biomedical Engineering4.491
· DOI :10.1109/TBME.2012.2188799
Janne M. Hahne9
Estimated H-index: 9
Bernhard Graimann27
Estimated H-index: 27
Klaus-Robert Müller92
Estimated H-index: 92
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 filter coefficients provides insight into the physiology of the muscles related to the performed contractions. The CSP methods are compared with a commonly used pattern recognition approach in a six-class classification task. Cross-validation results show a significant improvement in performance and a higher robustness against noise than commonly used pattern recognition methods.
  • References (17)
  • Citations (58)
📖 Papers frequently viewed together
968 Citations
1,193 Citations
424 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
#1Anders Lyngvi Fougner (NTNU: Norwegian University of Science and Technology)H-Index: 7
#2Erik Scheme (UNB: University of New Brunswick)H-Index: 20
Last. Øyvind Stavdahl (NTNU: Norwegian University of Science and Technology)H-Index: 23
view all 5 authors...
Reported studies on pattern recognition of electromyograms (EMG) for the control of prosthetic devices traditionally focus on classification accuracy of signals recorded in a laboratory. The difference between the constrained nature in which such data are often collected and the unpredictable nature of prosthetic use is an example of the semantic gap between research findings and a viable clinical implementation. In this paper, we demonstrate that the variations in limb position associated with ...
182 CitationsSource
#1Erik Scheme (UNB: University of New Brunswick)H-Index: 20
#2Kevin Englehart (UNB: University of New Brunswick)H-Index: 39
Last. B. Hudgins (UNB: University of New Brunswick)H-Index: 19
view all 3 authors...
Recent literature in pattern recognition-based myoelectric control has highlighted a disparity between classification accuracy and the usability of upper limb prostheses. This paper suggests that the conventionally defined classification accuracy may be idealistic and may not reflect true clinical performance. Herein, a novel myoelectric control system based on a selective multiclass one-versus-one classification scheme, capable of rejecting unknown data patterns, is introduced. This scheme is s...
90 CitationsSource
Using electromyogram (EMG) signals to control upper-limb prostheses is an important clinical option, offering a person with amputation autonomy of control by contracting residual muscles. The dexterity with which one may control a prosthesis has progressed very little, especially when control- ling multiple degrees of freedom. Using pattern recognition to discriminate multiple degrees of freedom has shown great promise in the research literature, but it has yet to transition to a clinically viab...
424 CitationsSource
#1Steven LemmH-Index: 10
#2Benjamin Blankertz (AG: Analysis Group)H-Index: 56
Last. Klaus-Robert MüllerH-Index: 92
view all 4 authors...
Abstract Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly ...
366 CitationsSource
#1Benjamin Blankertz (AG: Analysis Group)H-Index: 56
#2Steven Lemm (AG: Analysis Group)H-Index: 10
Last. Klaus-Robert MüllerH-Index: 92
view all 5 authors...
Abstract Analyzing brain states that correspond to event related potentials (ERPs) on a single trial basis is a hard problem due to the high trial-to-trial variability and the unfavorable ratio between signal (ERP) and noise (artifacts and neural background activity). In this tutorial, we provide a comprehensive framework for decoding ERPs, elaborating on linear concepts, namely spatio-temporal patterns and filters as well as linear ERP classification. However, the bottleneck of these techniques...
609 CitationsSource
#1Lauren H. Smith (NU: Northwestern University)H-Index: 11
#2Levi J. Hargrove (Rehabilitation Institute of Chicago)H-Index: 33
Last. Todd A. Kuiken (Rehabilitation Institute of Chicago)H-Index: 43
view all 4 authors...
Pattern recognition-based control of myoelectric prostheses has shown great promise in research environments, but has not been optimized for use in a clinical setting. To explore the relationship between classification error, controller delay, and real-time controllability, 13 able-bodied subjects were trained to operate a virtual upper-limb prosthesis using pattern recognition of electromyogram (EMG) signals. Classification error and controller delay were varied by training different classifier...
174 CitationsSource
#1He Huang (URI: University of Rhode Island)H-Index: 23
#2Ping Zhou (NU: Northwestern University)H-Index: 22
Last. Todd A. Kuiken (NU: Northwestern University)H-Index: 43
view all 4 authors...
The combination of targeted muscle reinnervation (TMR) and pattern classification of electromyography (EMG) has shown great promise for multifunctional myoelectric prosthesis control. In this study, we hypothesized that surface EMG recordings with high spatial resolution over reinnervated muscles could capture focal muscle activity and improve the classification accuracy of identifying intended movements. To test this hypothesis, TMR subjects with transhumeral or shoulder disarticulation amputat...
31 CitationsSource
Interest in developing an effective communication interface connecting the human brain and a computer has grown rapidly over the past decade. The brain-computer interface (BCI) would allow humans to operate computers, wheelchairs, prostheses, and other devices, using brain signals only. BCI research may someday provide a communication channel for patients with severe physical disabilities but intact cognitive functions, a working tool in computational neuroscience that contributes to a better un...
357 CitationsSource
#1Levi J. Hargrove (UNB: University of New Brunswick)H-Index: 33
#2Kevin Englehart (UNB: University of New Brunswick)H-Index: 39
Last. Bernard Hudgins (UNB: University of New Brunswick)H-Index: 9
view all 3 authors...
Abstract Pattern recognition based myoelectric control systems rely on detecting repeatable patterns at given electrode locations. This work describes an experiment to determine the effect of electrode displacements on pattern classification accuracy, and a classifier training strategy to accommodate this degradation. The results show that electrode displacements adversely affect classification accuracy, but training the system to recognize plausible displacement locations mitigates the effect. ...
158 CitationsSource
#1Benjamin BlankertzH-Index: 56
#2Ryota TomiokaH-Index: 28
Last. Klaus-Robert Müller (Technical University of Berlin)H-Index: 92
view all 5 authors...
Due to the volume conduction multichannel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis in order to improve the signal-to-noise ratio. There are powerful methods from machine learning and signal processing that permit the optimization of spatio-temporal filters for each subject in a data dependent fashion beyond the fixed filters based on the sensor geometry, e.g., Laplacians. Here we e...
1,105 CitationsSource
Cited By58
#1Mingchao Yu (WUST: Wuhan University of Science and Technology)
#2Gongfa Li (WUST: Wuhan University of Science and Technology)H-Index: 13
Last. Disi Chen (University of Portsmouth)H-Index: 5
view all 7 authors...
2 CitationsSource
#1Carles IgualH-Index: 1
Last. Jorge IgualH-Index: 10
view all 4 authors...
State-of-the-art high-end prostheses are electro-mechanically able to provide a great variety of movements. Nevertheless, in order to functionally replace a human limb, it is essential that each movement is properly controlled. This is the goal of prosthesis control, which has become a growing research field in the last decades, with the ultimate goal of reproducing biological limb control. Therefore, exploration and development of prosthesis control are crucial to improve many aspects of an amp...
#1François Nougarou (Université du Québec)H-Index: 8
#2Alexandre Campeau-Lecours (Laval University)H-Index: 7
Last. Benoit Gosselin (Laval University)H-Index: 18
view all 6 authors...
Abstract To enable an efficient alternative control of an assistive robotic arm using electromyographic (EMG) signals, the control method must simultaneously provide both the direction and the velocity. However, the contraction variations of the forearm muscles, used to proportionally control the device’s velocity using a regression method, can disturb the accuracy of the classification used to estimate its direction at the same time. In this paper, the original set of spatial features takes adv...
#1Tao Duan (HUST: Huazhong University of Science and Technology)
#2Jian Huang (HUST: Huazhong University of Science and Technology)H-Index: 20
Last. Caihua Xiong (HUST: Huazhong University of Science and Technology)
view all 5 authors...
The efficient control of neural wrist-hand prostheses with two degrees of freedom (DOF) has been expected by amputees for decades. Unlike the intrusive methods which can control the independent movements of the wrist and hand by detecting independent muscle groups in the deep layer, the non-invasive technology is hampered by the crosstalk problem between the surface electromyography (sEMG) signal sources. In this paper, a new myoelectric control method combined with Teager-Kaiser energy (TKE) an...
#1Minjae Kim (KIST: Korea Institute of Science and Technology)H-Index: 3
#2Wan Kyun Chung (POSTECH: Pohang University of Science and Technology)H-Index: 34
Last. Keehoon Kim (KIST: Korea Institute of Science and Technology)H-Index: 12
view all 3 authors...
Surface electromyography (sEMG) is widely used in various fields to analyze user intentions. Conventional sEMG-based classifications are electrode-dependent; thus, trained classifiers cannot be applied to other electrodes that have different parameters. This defect degrades the practicability of sEMG-based applications. In this study, we propose a virtual sEMG signal-assisted classification to achieve electrode-independent classification. The virtual signal for any electrode configuration can be...
#1Jiayuan HeH-Index: 8
Last. Ning Jiang (UW: University of Waterloo)H-Index: 29
view all 5 authors...
With the ability to detect volumetric changes of contracting muscles, ultrasound (US) was a potential technique in the field of human–machine interface. Compared to the US imaging (B-mode US), the signal from a static single-element US transducer, A-mode US, was a more cost-effective and convenient way toward the real-world application, particularly the wearables. This study compared the performance of the single-channel A-mode US with single-channel surface electromyogram (sEMG) signals, one of...
#1Turky N. Alotaiby (KACST: King Abdulaziz City for Science and Technology)H-Index: 5
#2Saleh A. Alshebeili (KSU: King Saud University)H-Index: 16
Last. Waleed M. Alsabhan (KACST: King Abdulaziz City for Science and Technology)
view all 4 authors...
In this paper, a nonfiducial electrocardiogram (ECG, the process of recording the electrical activity of the heart over a period of time using electrodes placed on the skin) identification system based on the common spatial pattern (CSP) feature extraction technique is presented. The single- and multilead ECG signals of each subject are divided into nonoverlapping segments, and different segment lengths (1, 3, 5, 7, 10, or 15 seconds) are investigated. Features are extracted from each signal seg...
#1Alexander Boschmann (University of Paderborn)H-Index: 6
#2Andreas Agne (University of Paderborn)H-Index: 8
Last. Marco Platzner (University of Paderborn)H-Index: 25
view all 6 authors...
Abstract Advances in electromyographic (EMG) sensor technology and machine learning algorithms have led to an increased research effort into high density EMG-based pattern recognition methods for prosthesis control. With the goal set on an autonomous multi-movement prosthesis capable of performing training and classification of an amputee’s EMG signals, the focus of this paper lies in the acceleration of the embedded signal processing chain. We present two Xilinx Zynq-based architectures for acc...
1 CitationsSource
#1Jiayuan He (UW: University of Waterloo)H-Index: 8
#2Xinjun Sheng (SJTU: Shanghai Jiao Tong University)H-Index: 17
Last. Ning Jiang (UW: University of Waterloo)H-Index: 29
view all 4 authors...
With the availability of high-density (HD) electrodes technology, the electrodes used in myoelectric control can have much higher density than the current practice. In this study, we investigated the effects of electrode density on pattern recognition (PR) based myoelectric control. Four density levels were analyzed in two directions: parallel and perpendicular to muscle fibers. Their influence on PR-based myoelectric control algorithms was investigated under three conditions between training an...
3 CitationsSource