sEMG Gesture Recognition with a Simple Model of Attention (2020-06-05T00:00:00.000000Z)

TL;DR

The proposed methodology's model simplicity represents a compelling alternative to the convolutional neural network (CNN) approaches utilized in recent research.

Abstract

Myoelectric control is one of the leading brain-machine-interfaces in the field of robotic prosthetics. We present our research in real-time surface electromyography (sEMG) signal classification, where our simple and novel attention-based approach now leads the industry, universally beating more complex, state-of-the-art models. Our model achieved an accuracy of 87\% (class-balanced accuracy: 69\%) using sEMG data and 91\% (balanced accuracy: 74\%) using both sEMG and accelerometer (IMU) data on NinaPro DB5, as well as 73\% overall on NinaPro DB4, an improvement on both highly sophisticated deep learning and signal processing approaches. Notably, the representation of the data learned by the attention mechanism alone is powerful enough to yield an accuracy of 79\% on DB5. NinaPro DB5 is a standard benchmark for sEMG gesture recognition and consists of 53 unique gestures, including finger gestures, wrist gestures, and functional grasping gestures. Our proposed methodology's model simplicity represents a compelling alternative to the convolutional neural network (CNN) approaches utilized in recent research.

Authors

David Josephs

1 papers

Carson Drake

1 papers

Andrew Heroy

1 papers

TL;DR

Abstract

Authors

References51 items

XceptionTime: Independent Time-Window Xceptiontime Architecture for Hand Gesture Classification

The Break-Even Point on Optimization Trajectories of Deep Neural Networks

Recurrent Neural Network Control of a Hybrid Dynamical Transfemoral Prosthesis with EdgeDRNN Accelerator

Hand Gesture Recognition Using Compact CNN via Surface Electromyography Signals

The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation

Movements Classification of Multi-Channel sEMG Based on CNN and Stacking Ensemble Learning

Mish: A Self Regularized Non-Monotonic Neural Activation Function

On the Variance of the Adaptive Learning Rate and Beyond

Calibrating the adaptive learning rate to improve convergence of ADAM

Lookahead Optimizer: k steps forward, 1 step back

On the Use of Deeper CNNs in Hand Gesture Recognition Based on sEMG Signals

Survey on deep learning with class imbalance

Surface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning

Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks

Learning Approaches in Signal Processing

Dynamic Gesture Recognition Based on LSTM-CNN

A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition

Deep learning for time series classification: a review

Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques

EMG Pattern Recognition in the Era of Big Data and Deep Learning

SVM-Based Tool to Detect Patients with Multiple Sclerosis Using a Commercial EMG Sensor

DyHard-DNN: Even More DNN Acceleration with Dynamic Hardware Reconfiguration

Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning

Technical Features and Functionalities of Myo Armband: An Overview on Related Literature and Advanced Applications of Myoelectric Armbands Mainly Focused on Arm Prostheses

A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface

Attend and Diagnose: Clinical Time Series Analysis using Attention Models

Comparison of six electromyography acquisition setups on hand movement classification tasks

Focal Loss for Dense Object Detection

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

Surface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

EOG-sEMG Human Interface for Communication

Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems

The Ninapro database: A resource for sEMG naturally controlled robotic hand prosthetics

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Electromyography data for non-invasive naturally-controlled robotic hand prostheses

Living in a medically underserved county is an independent risk factor for major limb amputation.

Determining the Optimal Window Length for Pattern Recognition-Based Myoelectric Control: Balancing the Competing Effects of Classification Error and Controller Delay

A Fast Learning Algorithm for Deep Belief Nets

Rectification and non-linear pre-processing of EMG signals for cortico-muscular analysis

Assessing the accuracy of prediction algorithms for classification: an overview

Mish: A Self Regularized Non-Monotonic Activation Function

A review on researches and applications of semg-based motion intent recognition methods

Layer normalization (2016

Apl’s modular prosthetic limb reaches new levels of operability

Myoelectric control of prosthetic hands : state - ofthe - art review

Characterization of a Benchmark Database for Myoelectric Movement Classification

keras. GitHub repository (2015), https://github.com/fchollet/ keras

Independent consultant

A new strategy for multifunction myoelectric control

This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning

Field of Study

Journal Information

Name

Volume