Hand Gesture Recognition via Transient sEMG Using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics

Tyacke, Eion; Reddy, Shreyas P. J.; Feng, Natalie; Edlabadkar, Rama; Zhou, Shucong; Patel, Jay; Hu, Qin; Atashzar, S. Farokh

doi:10.1109/lra.2022.3191238

Cited by 14 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D CapsNet architecture (see Fig. 2), inspired by [19], enhances the original Dilated Eff-Caps model for the utilization of 3D data through the conversion of 2D convolutional layers to 3D convolutional layers. In general, in capsular networks, the model classifies objects through collections of neurons called capsules.…”

Section: B 3d Dilated Efficient Capsnetmentioning

confidence: 99%

“…This makes the architecture ideal for addressing the altered spacial relationships but maintaining global context caused by channel dropout. We have recently shown that the 2D CapsNet significantly outperforms the standard CNN, MLP, and RNN-CNN hybrid model in gesture classification on transient sEMG [19]. The proposed augmentation forces the neural network to learn the variations in the input space caused by hundreds of variations of channel dropout.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hand Gesture Prediction via Transient-phase sEMG using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics

Tyacke

Reddy²,

Feng

et al. 2022

Preprint

View full text Add to dashboard Cite

There has been an accelerated surge to utilize the deep neural network for decoding central and peripheral activations of the human's nervous system to boost up the spatiotemporal resolution of neural interfaces used in neurorobotics. Such algorithmic solutions are motivated for use in human-centered robotic systems, such as neurorehabilitation, prosthetics, and exoskeletons. These methods are proved to achieve higher accuracy on individual data when compared with the conventional machine learning methods but are also challenged by their assumption of having access to massive training samples. Objective: In this letter, we propose Dilated Efficient CapsNet to improve the predictive performance when the available individual data is very minimum and not enough to train an individualized network for controlling a personalized robotic system. Method: We proposed the concept of transfer learning using a new design of the dilated efficient capsular neural network to relax the need of having access to massive individual data and utilize the field knowledge which can be learned from a group of participants. In addition, instead of using complete sEMG signals, we only use the transient phase, reducing the volume of training samples to 20\% of the original and maximizing the agility. Results: In experiments, we validate our model performance with various amounts of injected personalized training data (25%-100% of transient phase) that is segmented once by time and once by repetition. The results of this paper support the use of transfer learning using a dilated capsular neural network and show that with the use of such a model, the knowledge domain learned on a small number of subjects can be utilized to minimize the need for new data of new subjects while focusing only on the transient phase of contraction (which is a challenging neural interfacing problem).

show abstract

Section: B 3d Dilated Efficient Capsnetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hand Gesture Prediction via Transient-phase sEMG using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics

Tyacke

Reddy²,

Feng

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to achieve adequate classification accuracy for new users, the EMG-based motion recognition methods based on the traditional machine learning algorithms [9][10][11][12] such as linear discriminant analysis (LDA), artificial neural network (ANN), and support vector machine, or the deep learning models of convolutional neural network (CNN) and long short-term memory, often require collecting sEMG signals of new users for each motion class and retraining a specific classifier. However, collecting training data from new users usually requires them to perform motions according to the designed experimental paradigm, which is time-consuming and boring [13,14]. Therefore, developing a more efficient crossindividual motion intention recognition method is crucial for the practical application of myoelectric systems and has attracted the attention of many researchers worldwide.…”

Section: Introductionmentioning

confidence: 99%

A novel unsupervised dynamic feature domain adaptation strategy for cross-individual myoelectric gesture recognition

Liu,

Peng,

Tan

et al. 2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective.Surface electromyography pattern recognition (sEMG-PR) is considered as a promising control method for human-machine interaction systems. However, the performance of a trained classifier would greatly degrade for novel users since sEMG signals are user-dependent and largely affected by a number of individual factors such as the quantity of subcutaneous fat and the skin impedance. Approach. To solve this issue, we proposed a novel unsupervised cross-individual motion recognition method that aligned sEMG features from different individuals by self-adaptive dimensional dynamic distribution adaptation (SD-DDA) in this study. In the method, both the distances of marginal and conditional distributions between source and target features were minimized through automatically selecting the optimal feature domain dimension by using a small amount of unlabelled target data.Main results.The effectiveness of the proposed method was tested on four different feature sets, and results showed that the average classification accuracy was improved by above 10% on our collected dataset with the best accuracy reached 90.4%. Compared to six kinds of classic transfer learning methods, the proposed method showed an outstanding performance with improvements of 3.2%-13.8%. Additionally, the proposed method achieved an approximate 9% improvement on a publicly available dataset. Significance. These results suggested that the proposed SD-DDA method is feasible for cross-individual motion intention recognition, which would provide help for the application of sEMG-PR based system.

show abstract

“…Recent years, the cross-user transferring effect of transient EMG signals has been explored by many researchers. And it has been demonstrated that the use of transient EMG signals can make the myoelectric interface more seamless [21,22]. Tyacke et al [21] demonstrated that the use of transient myoelectric signals can reduce the myoelectric delay while also achieving a well cross-user transferring effect.…”

Section: Introductionmentioning

confidence: 99%

“…And it has been demonstrated that the use of transient EMG signals can make the myoelectric interface more seamless [21,22]. Tyacke et al [21] demonstrated that the use of transient myoelectric signals can reduce the myoelectric delay while also achieving a well cross-user transferring effect. Tigrini et al [22] claimed that hand movement prediction algorithms can also be migrated to the mid filed when transient EMG signals are utilized.…”

Section: Introductionmentioning

confidence: 99%

Multi-source domain generalization and adaptation toward cross-subject myoelectric pattern recognition

Zhang

et al. 2023

J. Neural Eng.

View full text Add to dashboard Cite

Myoelectric pattern recognition (MPR) has shown satisfactory performance under ideal laboratory conditions. Nevertheless, the individual variances lead to dramatic performance degradation in cross-user MPR applications. It is crucial to enable the myoelectric interface to adapt to multiple users’ surface electromyography (sEMG) distributions in practical. Domain adaptation (DA) is a promising approach to tackle cross-user challenges due to its ability to diminish the divergence between individual users' EMG distributions and escalate model generalization performance. However, existing DA methods in sEMG control are based on single-source domain adaptation (SDA). SDA solely mixes multiple training users’ data as a combined source domain and attempts to align with a novel user. This simple data mixing manner ignores the sEMG distribution variations between disparate training users, leading to an insufficient variance elimination and lower performance. To this end, this paper proposes a multi-source synchronize domain adaptation (MS-DA) framework with both domain adaptation and domain generalization (DG) capability. This multi-source framework aligns each source user and the new user in individual feature spaces, which better transfers the knowledge of existing users to the new user. Moreover, we retain the source-combined data to preserve the effectiveness of SDA. The property was further confirmed by evaluating the performance of the proposed method on data from nine subjects performing six tasks. Experiment results prove that the proposed multi-source framework achieved both positive DG and DA performance in a cross-user classification manner. This work demonstrates the usability and feasibility of the proposed multi-source framework in cross-user myoelectric control.

show abstract

Hand Gesture Recognition via Transient sEMG Using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics

Cited by 14 publications

References 35 publications

Hand Gesture Prediction via Transient-phase sEMG using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics

Hand Gesture Prediction via Transient-phase sEMG using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics

A novel unsupervised dynamic feature domain adaptation strategy for cross-individual myoelectric gesture recognition

Multi-source domain generalization and adaptation toward cross-subject myoelectric pattern recognition

Contact Info

Product

Resources

About