Recurrent Convolutional Neural Networks as an Approach to Position-Aware Myoelectric Prosthesis Control

Williams, Heather E.; Shehata, Ahmed W.; Dawson, Michael R.; Scheme, Erik; Hebert, Jacqueline S.; Pilarksi, Patrick

doi:10.1109/tbme.2022.3140269

Cited by 21 publications

(28 citation statements)

References 53 publications

(97 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in the introduction, most deep learning methods are based on the sEMG signals. The mainstream methods can be classified into three categories: CNN models [ 11 , 12 , 13 , 14 , 15 , 16 , 17 ], RNN models [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ], and ANN models [ 25 , 26 , 27 , 28 ]. The single-layer CNN proposed by Zia ur Rehman M accomplished the classification task of 7 gestures [ 12 ], which pioneered the application of CNN models to gesture recognition.…”

Section: Related Workmentioning

confidence: 99%

“…Some scholars have begun to pay attention to combining sEMG and IMU signals for gesture recognition by machine learning algorithms [ 2 , 4 , 34 , 35 ] or deep learning algorithms [ 23 , 24 ]. Xiaoliang [ 24 ] imposed the LSTM model to solve the gesture recognition problem based on the combination of sEMG and IMU signals. Although Xiaoliang achieved to complete the classification task of 10 gestures, the accuracy remains to be uplifted.…”

Section: Related Workmentioning

confidence: 99%

“…Although Xiaoliang achieved to complete the classification task of 10 gestures, the accuracy remains to be uplifted. Williams [ 24 ] also proposed the RCNN model to settle the 5-class task with these two signals, reaching an accuracy of 99%. Both Xiaoliang and Williams took several wearable devices to obtain more adequate data, such as Smart Glove or several Myo armbands.…”

Section: Related Workmentioning

confidence: 99%

“…Many studies have proposed machine learning or deep learning algorithms to implement Myo-based gesture recognition tasks. Among them, support vector machine (SVM) [ 1 , 2 , 3 , 4 ], k-nearest neighbor (KNN) [ 5 , 6 , 7 , 8 , 9 ], decision tree (DT) [ 10 ], convolutional neural network (CNN) [ 11 , 12 , 13 , 14 , 15 , 16 , 17 ], recurrent neural network (RNN) [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ], and artificial neural networks (ANN) [ 25 , 26 , 27 , 28 , 29 , 30 ] are the most popular algorithms with good recognition accuracy; however, there are still some challenges in this field of research. First, most studies build their datasets for specific application scenarios; these datasets involve mostly less than 10 gesture actions, and there is a lack of publicly available datasets for more classification tasks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Category Gesture Recognition Modeling Based on sEMG and IMU Signals

Jiang

Song

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Gesture recognition based on wearable devices is one of the vital components of human–computer interaction systems. Compared with skeleton-based recognition in computer vision, gesture recognition using wearable sensors has attracted wide attention for its robustness and convenience. Recently, many studies have proposed deep learning methods based on surface electromyography (sEMG) signals for gesture classification; however, most of the existing datasets are built for surface EMG signals, and there is a lack of datasets for multi-category gestures. Due to model limitations and inadequate classification data, the recognition accuracy of these methods cannot satisfy multi-gesture interaction scenarios. In this paper, a multi-category dataset containing 20 gestures is recorded with the help of a wearable device that can acquire surface electromyographic and inertial (IMU) signals. Various two-stream deep learning models are established and improved further. The basic convolutional neural network (CNN), recurrent neural network (RNN), and Transformer models are experimented on with our dataset as the classifier. The CNN and the RNN models’ test accuracy is over 95%; however, the Transformer model has a lower test accuracy of 71.68%. After further improvements, the CNN model is introduced into the residual network and augmented to the CNN-Res model, achieving 98.24% accuracy; moreover, it has the shortest training and testing time. Then, after combining the RNN model and the CNN-Res model, the long short term memory (LSTM)-Res model and gate recurrent unit (GRU)-Res model achieve the highest classification accuracy of 99.67% and 99.49%, respectively. Finally, the fusion of the Transformer model and the CNN model enables the Transformer-CNN model to be constructed. Such improvement dramatically boosts the performance of the Transformer module, increasing the recognition accuracy from 71.86% to 98.96%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Category Gesture Recognition Modeling Based on sEMG and IMU Signals

Jiang

Song

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In semi-autonomous prosthetic hand control, cameras are integrated to the system to output grasp patterns facilitating the prosthetic hand to grasp objects, thus reducing the user's burden. Traditional surface electrical myography (sEMG) based grasp pattern recognition [1], [2] has problems such as easily being affected by sweat, power line interference, and the variance of sEMG signals between different people. On the contrary, the image-based methods do not have such problems [3]- [5].…”

Section: Introductionmentioning

confidence: 99%

DL-Net: Sparsity Prior Learning for Grasp Pattern Recognition

et al. 2023

View full text Add to dashboard Cite

The purpose of grasp pattern recognition is to determine the grasp type for an object to be grasped, which can be applied to prosthetic hand control and ease the burden of amputees. To enhance the performance of grasp pattern recognition, we propose a network DL-Net inspired by dictionary learning. Our method includes two parts: (1) forward propagation for sparsity representation learning and (2) backward propagation for dictionary learning, which utilizes the sparsity prior effectively and learns a discriminative dictionary with stronger expressive ability from a mass of training data. The experiment was performed on two household object datasets, the RGB-D Object dataset, and the Hit-GPRec dataset. The experimental results illustrate that the DL-Net performs better than traditional deep learning methods in grasp pattern recognition.INDEX TERMS Grasp pattern recognition, computer vision, dictionary learning, deep learning.

show abstract