Recurrent Neural Network for Contaminant Type Detector in Surface Electromyography Signals

Machado, Juliano Costa; Tosin, Maurício Cagliari; Bagesteiro, Leia B.; Balbinot, Alexandre

doi:10.1109/embc44109.2020.9175348

Cited by 11 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it is important to guarantee a proper signal conditioning to achieve maximum information related to the task in subsequent processing phases. Therefore, studies have been published in recent years with new proposals for pre-processing stage that appears as alternatives to improve the classifiers performance (Chen et al 2020a;He et al 2019;Machado et al 2020;Sezgin 2019;Tam et al 2020;Wahid et al 2020;Xu et al 2020;Zhou et al 2020). Among the gains brought by these works, we can mention the improvement in the quality of the acquired signal, minimization of the effects of electrode displacement, temporal variation, and inter-subject variation in the characteristics of the EMG signal, to cite a few, which induce an increase in the performance of the movement classification system.…”

Section: Pre-processingmentioning

confidence: 99%

“…The presence of these factors in the EMG signal is unwanted and may make it impossible to extract the information depending on the level of contamination. Thereby, many researchers have been working on methods for detection, EMG signal recovery, identification of the type of interference, as well as classification strategies robust to the presence of contaminants (Favieiro & Balbinot 2019;Fraser et al 2014;Fraser et al 2012a;Ijaz & Choi 2018;De Luca et al 2010;Machado et al 2020;Machado et al 2019;McCool et al 2014;De Moura & Balbinot 2018;Stachaczyk et al 2020). Table 8 It is noteworthy that, despite the majority of works listed on Table 8 was not performed aiming the motion recognition task, all apply to it.…”

Section: Analysis Of the Presence Of Contaminants In The Semg Signalmentioning

confidence: 99%

“…However, despite the importance of contamination detection for data quality assessment, knowing the type of interference is also desirable for eliminating its source by correcting the acquisition procedure. Within this context are the works (Ijaz & Choi 2018;Machado et al 2020;McCool et al 2014). McCool et al (2014 implemented an SVM-based classifier to recognize five different sources of contamination (ECG, motion artifact, amplifier saturation, power line interference, and baseline noise, represented by additive white Gaussian noise).…”

Section: Analysis Of the Presence Of Contaminants In The Semg Signalmentioning

confidence: 99%

“…Dispensing with a pre-processing and feature extraction step was the innovation introduced by Machado et al (2020). In their work, the identification of four contaminant types (power line, motion artifact, white noise characterizing baseline noise, and ECG) plus clean signal was assigned to a classifier based on Recurrent Neural Networks (RNR) and LSTM.…”

Section: Analysis Of the Presence Of Contaminants In The Semg Signalmentioning

confidence: 99%

See 3 more Smart Citations

sEMG-Based Upper Limb Movement Classifier: Current Scenario and Upcoming Challenges

Tosin

Machado²,

Balbinot³

2022

jair

Self Cite

View full text Add to dashboard Cite

Despite achieving accuracies higher than 90% on recognizing upper-limb movements through sEMG (surface Electromyography) signal with the state of art classifiers in the laboratory environment, there are still issues to be addressed for a myo-controlled prosthesis achieve similar performance in real environment conditions. Thereby, the main goal of this review is to expose the latest researches in terms of strategies in each block of the system, giving a global view of the current state of academic research. A systematic review was conducted, and the retrieved papers were organized according to the system step related to the proposed method. Then, for each stage of the upper limb motion recognition system, the works were described and compared in terms of strategy, methodology and issue addressed. An additional section was destined for the description of works related to signal contamination that is often neglected in reviews focused on sEMG based motion classifiers. Therefore, this section is the main contribution of this paper. Deep learning methods are a current trend for classification stage, providing strategies based on time-series and transfer learning to address the issues related to limb position, temporal/inter-subject variation, and electrode displacement. Despite the promising strategies presented for contaminant detection, identification, and removal, there are still some factors to be considered, such as the occurrence of simultaneous contaminants. This review exposes the current scenario of the movement classification system, providing valuable information for new researchers and guiding future works towards myo-controlled devices.

show abstract

Section: Pre-processingmentioning

confidence: 99%

Section: Analysis Of the Presence Of Contaminants In The Semg Signalmentioning

confidence: 99%

Section: Analysis Of the Presence Of Contaminants In The Semg Signalmentioning

confidence: 99%

Section: Analysis Of the Presence Of Contaminants In The Semg Signalmentioning

confidence: 99%

See 2 more Smart Citations

sEMG-Based Upper Limb Movement Classifier: Current Scenario and Upcoming Challenges

Tosin

Machado²,

Balbinot³

2022

jair

Self Cite

View full text Add to dashboard Cite

show abstract

“…This model can be used to distinguish static gestures, but it is not enough to infer temporal tactical sign language gestures. The hybrid neural network obtained by combining the recurrent neural network (RNN) and multinetwork model [23] is applied to distinguish the EMG signals acquired from different sign language actions with high accuracy. Zhang et al [24] presented Myo-Sign which combines the signals of industrial sensor and EMG sensor.…”

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

MyoTac: Real-Time Recognition of Tactical Sign Language Based on Lightweight Deep Neural Network

Zhang

Cao

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Real-time tactical sign language recognition enables communication in a silent environment and outside the visual range, and human-computer interaction (HCI) can also be realized. Although the existing methods have high accuracy, they cannot be conveniently implemented in a portable system due to the complexity of their models. In this paper, we present MyoTac, a user-independent real-time tactical sign language classification system that makes the network lightweight through knowledge distillation, so as to balance between high accuracy and execution efficiency. We design tactical convolutional neural networks (TCNN) and bidirectional long short-term memory (B-LSTM) to capture the spatial and temporal features of the signals, respectively, and extract the soft target with knowledge distillation to compress the scale of the neural network by nearly four times without affecting the accuracy. We evaluate MyoTac on 30 tactical sign language (TSL) words based on data from 38 volunteers, including 25 volunteers collecting offline data and 13 volunteers conducting online tests. When dealing with new users, MyoTac achieves an average accuracy of 92.67% and the average recognition time is 2.81 ms. The obtained results show that our approach outperforms other algorithms proposed in the literature, reducing the real-time recognition time by 84.4% with higher accuracy.

show abstract

Dynamic Classifier Chains for Multi-label Learning

Trajdos

Kurzyński

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we deal with the task of building a dynamic ensemble of chain classifiers for multi-label classification. To do so, we proposed two concepts of classifier chains algorithms that are able to change label order of the chain without rebuilding the entire model. Such modes allows anticipating the instance-specific chain order without a significant increase in computational burden. The proposed chain models are built using the Naive Bayes classifier and nearest neighbour approach as a base single-label classifiers. To take the benefits of the proposed algorithms, we developed a simple heuristic that allows the system to find relatively good label order. The heuristic sort labels according to the label-specific classification quality gained during the validation phase. The heuristic tries to minimise the phenomenon of error propagation in the chain. The experimental results showed that the proposed model based on Naive Bayes classifier the above-mentioned heuristic is an efficient tool for building dynamic chain classifiers.

show abstract

Recurrent Neural Network for Contaminant Type Detector in Surface Electromyography Signals

Cited by 11 publications

References 11 publications

sEMG-Based Upper Limb Movement Classifier: Current Scenario and Upcoming Challenges

sEMG-Based Upper Limb Movement Classifier: Current Scenario and Upcoming Challenges

MyoTac: Real-Time Recognition of Tactical Sign Language Based on Lightweight Deep Neural Network

Dynamic Classifier Chains for Multi-label Learning

Contact Info

Product

Resources

About