How do sEMG segmentation parameters influence pattern recognition process? An approach based on wearable sEMG sensor

Mendes, José Jair Alves; Pontim, Carlos Eduardo; Dias, Thiago Simões; Campos, Daniel Prado

doi:10.1016/j.bspc.2022.104546

Cited by 4 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, a consistent increase in accuracy can be observed as the window size increases. Current literature regarding window size segmentation have found that increasing the window size improves the accuracy up to a certain threshold [ 20 , 21 ]. Considering the current literature regarding the noisy nature of biological signals emitted from stroke survivors, this threshold might be larger for them.…”

Section: Discussionmentioning

confidence: 99%

“…Then the data was segmented using an overlapped segmentation method with a window size of 222 milliseconds and a step size of 55.6 milliseconds. Oskoei and Hu [ 21 ] found that an overlapping segmentation approach to EMG data with a window size of 200 milliseconds and a step size of 50 milliseconds provides a quick response time while Junior et al [ 20 ] recommends a step size of 500 milliseconds with a 25% overlap. Both of those studies were tested on healthy participants.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks

Sarwat,

Alkhashab,

Song

et al. 2024

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Background In-home rehabilitation systems are a promising, potential alternative to conventional therapy for stroke survivors. Unfortunately, physiological differences between participants and sensor displacement in wearable sensors pose a significant challenge to classifier performance, particularly for people with stroke who may encounter difficulties repeatedly performing trials. This makes it challenging to create reliable in-home rehabilitation systems that can accurately classify gestures. Methods Twenty individuals who suffered a stroke performed seven different gestures (mass flexion, mass extension, wrist volar flexion, wrist dorsiflexion, forearm pronation, forearm supination, and rest) related to activities of daily living. They performed these gestures while wearing EMG sensors on the forearm, as well as FMG sensors and an IMU on the wrist. We developed a model based on prototypical networks for one-shot transfer learning, K-Best feature selection, and increased window size to improve model accuracy. Our model was evaluated against conventional transfer learning with neural networks, as well as subject-dependent and subject-independent classifiers: neural networks, LGBM, LDA, and SVM. Results Our proposed model achieved 82.2% hand—gesture classification accuracy, which was better (P<0.05) than one-shot transfer learning with neural networks (63.17%), neural networks (59.72%), LGBM (65.09%), LDA (63.35%), and SVM (54.5%). In addition, our model performed similarly to subject-dependent classifiers, slightly lower than SVM (83.84%) but higher than neural networks (81.62%), LGBM (80.79%), and LDA (74.89%). Using K-Best features improved the accuracy in 3 of the 6 classifiers used for evaluation, while not affecting the accuracy in the other classifiers. Increasing the window size improved the accuracy of all the classifiers by an average of 4.28%. Conclusion Our proposed model showed significant improvements in hand—gesture recognition accuracy in individuals who have had a stroke as compared with conventional transfer learning, neural networks and traditional machine learning approaches. In addition, K-Best feature selection and increased window size can further improve the accuracy. This approach could help to alleviate the impact of physiological differences and create a subject-independent model for stroke survivors that improves the classification accuracy of wearable sensors. Trial registration number: The study was registered in Chinese Clinical Trial Registry with registration number CHiCTR1800017568 in 2018/08/04

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks

Sarwat,

Alkhashab,

Song

et al. 2024

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

show abstract

“…This was previously tested in [35] for a prosthetic task, was found to be suitable in this investigation. Additionally, it could be adapted for online applications, in which the offset time could be suppressed, and overlap segmentation could be applied to improve results [36,51].…”

Section: Discussionmentioning

confidence: 99%

“…It was chosen over other identification methods because it presents results higher than similar algorithms for sEMG signal in pattern recognition processes, such as the double threshold onset method [35]. The used method does not need adjustment of window size after the signal identification, which has an impact in accuracy for sEMG signal classification [36]. Our algorithm can identify the start and the end of an sEMG signal for each gesture, which was suitable for this offline application.…”

Section: Methodsmentioning

confidence: 99%

Surgical Instrument Signaling Gesture Recognition Using Surface Electromyography Signals

Freitas

Mendes

Dias

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Surgical Instrument Signaling (SIS) is compounded by specific hand gestures used by the communication between the surgeon and surgical instrumentator. With SIS, the surgeon executes signals representing determined instruments in order to avoid error and communication failures. This work presented the feasibility of an SIS gesture recognition system using surface electromyographic (sEMG) signals acquired from the Myo armband, aiming to build a processing routine that aids telesurgery or robotic surgery applications. Unlike other works that use up to 10 gestures to represent and classify SIS gestures, a database with 14 selected gestures for SIS was recorded from 10 volunteers, with 30 repetitions per user. Segmentation, feature extraction, feature selection, and classification were performed, and several parameters were evaluated. These steps were performed by taking into account a wearable application, for which the complexity of pattern recognition algorithms is crucial. The system was tested offline and verified as to its contribution for all databases and each volunteer individually. An automatic segmentation algorithm was applied to identify the muscle activation; thus, 13 feature sets and 6 classifiers were tested. Moreover, 2 ensemble techniques aided in separating the sEMG signals into the 14 SIS gestures. Accuracy of 76% was obtained for the Support Vector Machine classifier for all databases and 88% for analyzing the volunteers individually. The system was demonstrated to be suitable for SIS gesture recognition using sEMG signals for wearable applications.

show abstract

sEMG-Based Segmentation Parameter Influence for Hand Gesture Recognition Using Deep Learning

Joseph,

Pathinarupothi,

Sankaran

2023

2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)

View full text Add to dashboard Cite

How do sEMG segmentation parameters influence pattern recognition process? An approach based on wearable sEMG sensor

Cited by 4 publications

References 33 publications

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks

Surgical Instrument Signaling Gesture Recognition Using Surface Electromyography Signals

sEMG-Based Segmentation Parameter Influence for Hand Gesture Recognition Using Deep Learning

Contact Info

Product

Resources

About