sEMG pattern recognition based on recurrent neural network

Bittibssi, Tarek M.; Zekry, Abd Haliem; Genedy, Mohamed A.; Maged, Shady A.

doi:10.1016/j.bspc.2021.103048

Cited by 34 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3,4 The second method is to apply machine learning (ML) to assembly process quality control based on its good classification and prediction ability. ML methods [5][6][7][8] do not need manual participation in the application, reducing the influence of manual error on control chart recognition. Considering the advantages of ML, this section studies two key factors affecting the accuracy of abnormal pattern recognition based on ML: classification features and classifiers.…”

Section: Related Previous Workmentioning

confidence: 99%

Diesel engine quality abnormal patterns recognition based on feature fusion and adaptive decision fusion

Wang,

Zhang

et al. 2024

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

The current assembly process of marine diesel engines is low in intelligence and the control chart pattern classifier with unstable performance, which makes it difficult to control and identify the quality control chart pattern. This paper proposes a new assembly quality control diagram recognition method based on an adaptive decision model to address these problems. Through characteristics and changes of the diesel engine assembly process analyses, the triangular norm is used to fuse the extracted shape features and statistical features to reduce the influence of data fluctuation and imbalance on pattern recognition. An adaptive decision fusion model of the assembly process is established by defining multiple weights with considering the complexity and uncontrollability of the diesel engine assembly process. Based on these, the fusion coefficients within the adaptive decision model are optimized by the Ant Lion Optimization algorithm (ALO) to improve the decision efficiency and classification precision. To validate the proposed model, diesel engine exhaust pressure is selected as a case for abnormal pattern recognition, and the ability of the model is discussed in terms of recognition accuracy and stability.

show abstract

Section: Related Previous Workmentioning

confidence: 99%

Diesel engine quality abnormal patterns recognition based on feature fusion and adaptive decision fusion

Wang,

Zhang

et al. 2024

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

show abstract

“…Three models were developed utilizing RNNs with LSTM and their most popular variations, gated recurrent unit (GRU) network and peephole convolution LSTM, due to the success of sequential prediction. 25 The RNN concept uses random input data over extended sequences, where each element repeats the same function and has a dependent output input on the previous calculation. It features a memory that stores data till the training data sequence is finished.…”

Section: Lstm Architecturesmentioning

confidence: 99%

Implementation of surface electromyography controlled prosthetics limb based on recurrent neural network

Bittibssi

Zekry

Genedy

et al. 2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Low‐cost traditional prosthetic legs, available worldwide, can make walking and stair climbing possible but still difficult. This article presents the hardware implementation of the surface electromyography (sEMG) powered prosthesis actuation (PPA) system using a learned neural network algorithm based on recurrent neural network (RNN), which is used to train sEMG benchmark databases, and predict joint angle. This implementation was created based on sEMG signal measurements. The data were collected from three benchmark datasets describing different subjects during performance, and analyzing various gait patterns were used to construct the neural network and reduce significant model errors in a real‐time setting. Processing circuits, interfacing the output with the controller board, signal amplification, motor driving circuits, and single‐board computer programming are included in the implementation.

show abstract

“…However, these models only capture the spatial information of sEMG signals without considering the temporal information. To address this issue, recurrent neural networks (RNNs) [ 10 ] and the hybrid CNN–RNN [ 11 , 12 ] are adopted to extract both spatial and temporal features from sEMG signals and achieve better performances compared to CNN. However, RNN and CNN–RNN are rarely used in real-time HCIs due to their slow computation.…”

Section: Introductionmentioning

confidence: 99%

Improved Network and Training Scheme for Cross-Trial Surface Electromyography (sEMG)-Based Gesture Recognition

Dai,

Wong,

Kankanhali

et al. 2023

Bioengineering

View full text Add to dashboard Cite

To enhance the performance of surface electromyography (sEMG)-based gesture recognition, we propose a novel network-agnostic two-stage training scheme, called sEMGPoseMIM, that produces trial-invariant representations to be aligned with corresponding hand movements via cross-modal knowledge distillation. In the first stage, an sEMG encoder is trained via cross-trial mutual information maximization using the sEMG sequences sampled from the same time step but different trials in a contrastive learning manner. In the second stage, the learned sEMG encoder is fine-tuned with the supervision of gesture and hand movements in a knowledge-distillation manner. In addition, we propose a novel network called sEMGXCM as the sEMG encoder. Comprehensive experiments on seven sparse multichannel sEMG databases are conducted to demonstrate the effectiveness of the training scheme sEMGPoseMIM and the network sEMGXCM, which achieves an average improvement of +1.3% on the sparse multichannel sEMG databases compared to the existing methods. Furthermore, the comparison between training sEMGXCM and other existing networks from scratch shows that sEMGXCM outperforms the others by an average of +1.5%.

show abstract

sEMG pattern recognition based on recurrent neural network

Cited by 34 publications

References 19 publications

Diesel engine quality abnormal patterns recognition based on feature fusion and adaptive decision fusion

Diesel engine quality abnormal patterns recognition based on feature fusion and adaptive decision fusion

Implementation of surface electromyography controlled prosthetics limb based on recurrent neural network

Improved Network and Training Scheme for Cross-Trial Surface Electromyography (sEMG)-Based Gesture Recognition

Contact Info

Product

Resources

About