Match!

Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network

Published on Jul 11, 2017in Frontiers in Neuroscience3.65
· DOI :10.3389/fnins.2017.00379
Xiaolong Zhai2
Estimated H-index: 2
(CityU: City University of Hong Kong),
Beth Jelfs9
Estimated H-index: 9
(CityU: City University of Hong Kong)
+ 1 AuthorsChung Tin11
Estimated H-index: 11
(CityU: City University of Hong Kong)
Cite
Abstract
Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications.
Figures & Tables
  • References (41)
  • Citations (29)
Cite
References41
Newest
Published on May 24, 2017in Communications of The ACM5.41
Alex Krizhevsky13
Estimated H-index: 13
(Google),
Ilya Sutskever40
Estimated H-index: 40
(Google),
Geoffrey E. Hinton123
Estimated H-index: 123
(OpenAI)
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and thre...
Evan Shelhamer14
Estimated H-index: 14
(University of California, Berkeley),
Jonathan Long6
Estimated H-index: 6
(University of California, Berkeley),
Trevor Darrell100
Estimated H-index: 100
(University of California, Berkeley)
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application ...
Published on Dec 1, 2016in Scientific Reports4.01
Weidong Geng7
Estimated H-index: 7
,
Yu Du4
Estimated H-index: 4
+ 3 AuthorsJiajun Li1
Estimated H-index: 1
Published on Sep 7, 2016in Frontiers in Neurorobotics3.00
Manfredo Atzori10
Estimated H-index: 10
(University of Applied Sciences Western Switzerland),
Matteo Cognolato2
Estimated H-index: 2
(University of Applied Sciences Western Switzerland),
Henning Müller42
Estimated H-index: 42
(University of Applied Sciences Western Switzerland)
Motivation: Natural control methods based on surface electromyography and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications and commercial prostheses are in the best case capable to offer natural control for only a few movements. Objective: In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our...
Marina M. C. Vidovic3
Estimated H-index: 3
(Technical University of Berlin),
Han-Jeong Hwang14
Estimated H-index: 14
(Technical University of Berlin)
+ 3 AuthorsKlaus-Robert Müller82
Estimated H-index: 82
(Technical University of Berlin)
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...
Published on Sep 1, 2016in Scientific Reports4.01
Geert J. S. Litjens20
Estimated H-index: 20
,
Clara I. Sánchez23
Estimated H-index: 23
+ 7 AuthorsJeroen van der Laak24
Estimated H-index: 24
Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis
Published on Aug 1, 2016 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
Xiaolong Zhai2
Estimated H-index: 2
(CityU: City University of Hong Kong),
Beth Jelfs9
Estimated H-index: 9
(CityU: City University of Hong Kong)
+ 1 AuthorsChung Tin11
Estimated H-index: 11
(CityU: City University of Hong Kong)
Hand gesture recognition from forearm surface electromyography (sEMG) is an active research field in the development of motor prosthesis. Studies have shown that classification accuracy and efficiency is highly dependent on the features extracted from the EMG. In this paper, we show that EMG spectrograms are a particularly effective feature for discriminating multiple classes of hand gesture when subjected to principal component analysis for dimensionality reduction. We tested our method on the ...
Meena Abdelmaseeh4
Estimated H-index: 4
(UW: University of Waterloo),
Tsu-Wei Chen2
Estimated H-index: 2
(UW: University of Waterloo),
Daniel W. Stashuk24
Estimated H-index: 24
(UW: University of Waterloo)
This paper proposes a system for hand movement recognition using multichannel electromyographic (EMG) signals obtained from the forearm surface. This system can be used to control prostheses or to provide inputs for a wide range of human computer interface systems. In this work, the hand movement recognition problem is formulated as a multi-class distance based classification of multi-dimensional sequences. More specifically, the extraction of multi-channel EMG activation trajectories underlying...
Published on 2016in Scientific Reports4.01
Sheng Wang18
Estimated H-index: 18
(U of C: University of Chicago),
Jian Peng28
Estimated H-index: 28
(Illinois College)
+ 1 AuthorsJinbo Xu35
Estimated H-index: 35
(Toyota Technological Institute at Chicago)
Protein secondary structure (SS) prediction is important for studying protein structure and function. When only the sequence (profile) information is used as input feature, currently the best predictors can obtain ~80% Q3 accuracy, which has not been improved in the past decade. Here we present DeepCNF (Deep Convolutional Neural Fields) for protein SS prediction. DeepCNF is a Deep Learning extension of Conditional Neural Fields (CNF), which is an integration of Conditional Random Fields (CRF) an...
Jianwei Liu5
Estimated H-index: 5
(SJTU: Shanghai Jiao Tong University),
Xinjun Sheng15
Estimated H-index: 15
(SJTU: Shanghai Jiao Tong University)
+ 2 AuthorsXiangyang Zhu21
Estimated H-index: 21
(SJTU: Shanghai Jiao Tong University)
In spite of several decades of intense research and development, the existing algorithms of myoelectric pattern recognition (MPR) are yet to satisfy the criteria that a practical upper extremity prostheses should fulfill. This study focuses on the criterion of the short, or even zero subject training. Due to the inherent nonstationarity in surface electromyography (sEMG) signals, current myoelectric control algorithms usually need to be retrained daily during a multiple days' usage. This study w...
Cited By29
Newest
Yusuke Yamanoi2
Estimated H-index: 2
(Yokohama National University),
Yosuke Ogiri (Yokohama National University), Ryu Kato12
Estimated H-index: 12
(Yokohama National University)
Abstract Our purpose is a development of a myoelectric hand that does not require relearning even after being reseated. Because an electromyogram is a fragile biological signal, learning is necessary every time the hand is reseated, which is a burden to the operator. A classification method is proposed that uses a convolutional neural network, and test results confirmed that the decrease in classification rate is suppressed when large-scale data are used for learning. The proposed method was mou...
Published on Dec 1, 2019in Scientific Reports4.01
Chelsea D. Pernici (La. Tech: Louisiana Tech University), Benjamin S. Kemp1
Estimated H-index: 1
(La. Tech: Louisiana Tech University),
Teresa A. Murray6
Estimated H-index: 6
(La. Tech: Louisiana Tech University)
Time course, in vivo imaging of brain cells is crucial to fully understand the progression of secondary cellular damage and recovery in murine models of injury. We have combined high-resolution gradient index lens technology with a model of diffuse axonal injury in rodents to enable repeated visualization of fine features of individual cells in three-dimensional space over several weeks. For example, we recorded changes in morphology in the same axons in the external capsule numerous times over ...
Published on Nov 1, 2019in International Journal of Mechanical Sciences4.13
Xiaoguo Li (NTU: Nanyang Technological University), Anthony Meng Huat Tiong1
Estimated H-index: 1
(NTU: Nanyang Technological University)
+ 3 AuthorsSoo Jay Phee22
Estimated H-index: 22
(NTU: Nanyang Technological University)
Abstract Distal-end force information is usually missing in flexible endoscopic robots due to the difficulties of mounting miniature force sensors on their end-effectors. This hurdle creates big challenges in providing a sense of touch for the operating surgeons. Many existing studies have developed models to calculate the distal-end forces based on the measured proximal-end forces of Tendon-Sheath Mechanisms (TSMs), but these models assume known sheath bending configuration which is unknown dur...
Published on Sep 21, 2019in arXiv: Signal Processing
Mohsen Jafarzadeh2
Estimated H-index: 2
,
Daniel Curtiss Hussey , Yonas Tadesse13
Estimated H-index: 13
Natural muscles provide mobility in response to nerve impulses. Electromyography (EMG) measures the electrical activity of muscles in response to a nerve's stimulation. In the past few decades, EMG signals have been used extensively in the identification of user intention to potentially control assistive devices such as smart wheelchairs, exoskeletons, and prosthetic devices. In the design of conventional assistive devices, developers optimize multiple subsystems independently. Feature extractio...
Published on Sep 9, 2019
Kirill A. Shatilov (HKUST: Hong Kong University of Science and Technology), Dimitris Chatzopoulos3
Estimated H-index: 3
(HKUST: Hong Kong University of Science and Technology)
+ 1 AuthorsPan Hui1
Estimated H-index: 1
(HKUST: Hong Kong University of Science and Technology)
Published on Jul 17, 2019in arXiv: Human-Computer Interaction
Piotr Kaczmarek4
Estimated H-index: 4
,
Tomasz Mańkowski2
Estimated H-index: 2
,
Jakub Tomczyński2
Estimated H-index: 2
In this paper, we present a putEMG dataset intended for evaluation of hand gesture recognition methods based on sEMG signal. The dataset was acquired for 44 able-bodied subjects and include 8 gestures (3 full hand gestures, 4 pinches, and idle). It consists of uninterrupted recordings of 24 sEMG channels from the subject's forearm, RGB video stream and depth camera images used for hand motion tracking. Moreover, exemplary processing scripts are also published. putEMG dataset is available under C...
Published on Aug 1, 2019in Biomedical Signal Processing and Control2.94
Dheeraj Kumar36
Estimated H-index: 36
(RMIT: RMIT University),
Beth Jelfs9
Estimated H-index: 9
(RMIT: RMIT University)
+ 1 AuthorsSridhar Poosapadi Arjunan10
Estimated H-index: 10
(RMIT: RMIT University)
Abstract Prosthetic hand control has fired the imagination of many researchers and thousands of papers have been published in this field, but the user acceptance has not been strong and there appears to be a significant gap between the published research and its translation. One observation of the literature is that while this requires multidisciplinary research, most articles appear to be topic focused, with lack of literature that connect across the different disciplines. This paper reports a ...
Published on Apr 15, 2019in Health technology
Vincius Horn Cene (UFRGS: Universidade Federal do Rio Grande do Sul), Alexandre Balbinot7
Estimated H-index: 7
(UFRGS: Universidade Federal do Rio Grande do Sul)
In movement classification through surface electromyography signal processing, the classification method must identify the user’s intention with satisfactory accuracy to promote an adequate biosignal interface. Traditionally, classical methods such as Support Vector Machines, Artificial Neural Networks, and Logistic Regression have been used to this end. Recently, Non-Iterative Methods based on Artificial Neural Networks have been revisited in the form of Random Vector Functional-Link Networks (...