Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
. 2018 Sep 13;13(9):e0203835.
doi: 10.1371/journal.pone.0203835. eCollection 2018.

Real-time, simultaneous myoelectric control using a convolutional neural network

Ali Ameri  1 , Mohammad Ali Akhaee  2 , Erik Scheme  3 , Kevin Englehart  3
Affiliations
Comparative Study

Real-time, simultaneous myoelectric control using a convolutional neural network

Ali Ameri et al. PLoS One. .

Abstract

The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a possible alternative to traditional approaches that rely on specifically designed features. This CNN-based system is validated using a real-time Fitts' law style target acquisition test requiring single and combined wrist motions. The performance of the proposed system is then compared to that of a standard support vector machine (SVM) based myoelectric system using a set of time-domain features. Despite the prevalence and demonstrated performance of these well-known features, no significant difference (p>0.05) was found between the two methods for any of the computed control metrics. This demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals. This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1
A simple block diagram of (a) classical and (b) CNN based approaches to myoelectric pattern recognition.
Fig 2
Fig 2. The extracted feature maps are shown during the proposed CNN process.
The input is 8x192 EMG data. In each phase, the features are obtained by applying convolution, batch normalization, rectified linear unit (relu), and pooling. A fully connected (FC) layer combines the features to produce 9 final features. The softmax (SM) layer computes the classification probabilities, and the classification layer outputs the estimated class. (Note that for example 32 3x3x16 convolutions are performed in the second convolution layer, and the second pooling layer transforms the 4x96 feature map to 2x48 feature map).
Fig 3
Fig 3
A 2D representation of the overlay of path traces for all users in the Fitts’ law test for the (a) CNN and (b) SVM based control scheme (x+: extension, x-: flexion, y+: supination, y-: pronation).
Fig 4
Fig 4. A strong linear relationship (R2>0.98) was found between the movement time and index of difficulty.
See this image and copyright information in PMC

References

    1. Farina D, Jiang N, Rehbaum H, Holobar A, Graimann B, Dietl H, et al. The extraction of neural information from the surface EMG for the control of upper-limb prostheses: emerging avenues and challenges. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2014. July;22(4):797–809. 10.1109/TNSRE.2014.2305111 - DOI - PubMed
    1. Farina D, Aszmann O. Bionic limbs: clinical reality and academic promises. Science translational medicine. 2014. October 8;6(257):257ps12 10.1126/scitranslmed.3010453 - DOI - PubMed
    1. Hargrove LJ, Lock BA, Simon AM. Pattern recognition control outperforms conventional myoelectric control in upper limb patients with targeted muscle reinnervation. InEngineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE 2013 Jul 3 (pp. 1599–1602). IEEE. - PubMed
    1. Simon AM, Hargrove LJ, Lock BA, Kuiken TA. The Target Achievement Control Test: Evaluating real-time myoelectric pattern recognition control of a multifunctional upper-limb prosthesis. Journal of rehabilitation research and development. 2011;48(6):619 - PMC - PubMed
    1. Scheme E, Lock B, Hargrove L, Hill W, Kuruganti U, Englehart K. Motion normalized proportional control for improved pattern recognition-based myoelectric control. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2014. January;22(1):149–57. 10.1109/TNSRE.2013.2247421 - DOI - PubMed

Publication types