Deep Learning in EMG-based Gesture Recognition

Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios

doi:10.5220/0006960201070114

Cited by 56 publications

(62 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tsinganos et al [15] achieve 89.8% classification accuracy on the 53 classes of NinaPro DB1 with an RMSfed TCN. This result is 4.8% better than SoA [39] and surpasses by 19.3% the previous results from the same authors obtained with conventional 2d-CNNs [28]. This TCN was evaluated using receptive field (i.e., input sequence lengths) of 300 ms up to 2.5 s. Although the NinaPro DB1 dataset is not multi-session [9] and so does not involve the temporal variability which is the focus of this work, [15] is a valuable demonstration that TCNs can yield good accuracy on this task.…”

Section: B Related Workcontrasting

confidence: 47%

“…All of them share a typical structure, based on i) an analog front end for bio-potential acquisition, ii) a data preprocessing and feature extraction/selection step, and iii) a final classification back end. Moreover, they usually all rely on Machine Learning (ML) algorithms such as Support Vector Machine (SVM), Random Forest (RF), LDA or artificial neural networks (ANN) [8], [9], [27], [10], [13], [28].…”

Section: B Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Robust Real-Time Embedded EMG Recognition Framework Using Temporal Convolutional Networks on a Multicore IoT Processor

Zanghieri

Benatti

Burrello

et al. 2020

IEEE Trans. Biomed. Circuits Syst.

109

111

View full text Add to dashboard Cite

Hand movement classification via surface electromyographic (sEMG) signal is a well-established approach for advanced Human-Computer Interaction. However, sEMG movement recognition has to deal with the long-term reliability of sEMG-based control, limited by the variability affecting the sEMG signal. Embedded solutions are affected by a recognition accuracy drop over time that makes them unsuitable for reliable gesture controller design. In this paper, we present a complete wearable-class embedded system for robust sEMGbased gesture recognition, based on Temporal Convolutional Networks (TCNs). Firstly, we developed a novel TCN topology (TEMPONet), and we tested our solution on a benchmark dataset (Ninapro), achieving 49.6% average accuracy, 7.8%, better than current State-Of-the-Art (SoA). Moreover, we designed an energy-efficient embedded platform based on GAP8, a novel 8-core IoT processor. Using our embedded platform, we collected a second 20-sessions dataset to validate the system on a setup which is representative of the final deployment. We obtain 93.7% average accuracy with the TCN, comparable with a SoA SVM approach (91.1%). Finally, we profiled the performance of the network implemented on GAP8 by using an 8-bit quantization strategy to fit the memory constraint of the processor. We reach a 4× lower memory footprint (460 kB) with a performance degradation of only 3% accuracy. We detailed the execution on the GAP8 platform, showing that the quantized network executes a single classification in 12.84 ms with a power envelope of 0.9 mJ, making it suitable for a longlifetime wearable deployment.

show abstract

Section: B Related Workcontrasting

confidence: 47%

Section: B Related Workmentioning

confidence: 99%

Robust Real-Time Embedded EMG Recognition Framework Using Temporal Convolutional Networks on a Multicore IoT Processor

Zanghieri

Benatti

Burrello

et al. 2020

IEEE Trans. Biomed. Circuits Syst.

109

111

View full text Add to dashboard Cite

show abstract

“…Huang [17] utilized spectrogram in conjunction with a CNN-LSTM (Long Short-Term Memory network) combination and showed improved classification (from 77.167% to 79.329%) on the NinaPro dataset. Tsinganos [18] proposed a modified CNN and achieved an improvement of 3% on NinaPro dataset. Pinzón-Arenas [19] used CNN to recognize six hand gestures using a wearable EMG recording device (Myo Armband, Thalamic Labs) and achieved a validation accuracy of 98.4% and 99% testing accuracy.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG

Asif

Waris

Gilani

et al. 2020

Sensors

103

View full text Add to dashboard Cite

Electromyography (EMG) is a measure of electrical activity generated by the contraction of muscles. Non-invasive surface EMG (sEMG)-based pattern recognition methods have shown the potential for upper limb prosthesis control. However, it is still insufficient for natural control. Recent advancements in deep learning have shown tremendous progress in biosignal processing. Multiple architectures have been proposed yielding high accuracies (>95%) for offline analysis, yet the delay caused due to optimization of the system remains a challenge for its real-time application. From this arises a need for optimized deep learning architecture based on fine-tuned hyper-parameters. Although the chance of achieving convergence is random, however, it is important to observe that the performance gain made is significant enough to justify extra computation. In this study, the convolutional neural network (CNN) was implemented to decode hand gestures from the sEMG data recorded from 18 subjects to investigate the effect of hyper-parameters on each hand gesture. Results showed that the learning rate set to either 0.0001 or 0.001 with 80-100 epochs significantly outperformed (p < 0.05) other considerations. In addition, it was observed that regardless of network configuration some motions (close hand, flex hand, extend the hand and fine grip) performed better (83.7% ± 13.5%, 71.2% ± 20.2%, 82.6% ± 13.9% and 74.6% ± 15%, respectively) throughout the course of study. So, a robust and stable myoelectric control can be designed on the basis of the best performing hand motions. With improved recognition and uniform gain in performance, the deep learning-based approach has the potential to be a more robust alternative to traditional machine learning algorithms.

show abstract

“…The above-mentioned methods are evaluated by measuring the improvement of classification accuracy for two CNN architectures. These are a modified version of the simple model of [ 13 ] denoted as AtzoriNet* described in [ 22 ], and an implementation of the bigger network of [ 19 ] called WeiNet to evaluate how well augmentation works in overparameterized networks. Details of the models can be seen in Table A1 .…”

Section: Methodsmentioning

confidence: 99%

Data Augmentation of Surface Electromyography for Hand Gesture Recognition

Tsinganos

Cornelis

et al. 2020

Sensors

View full text Add to dashboard Cite

The range of applications of electromyography-based gesture recognition has increased over the last years. A common problem regularly encountered in literature is the inadequate data availability. Data augmentation, which aims at generating new synthetic data from the existing ones, is the most common approach to deal with this data shortage in other research domains. In the case of surface electromyography (sEMG) signals, there is limited research in augmentation methods and quite regularly the results differ between available studies. In this work, we provide a detailed evaluation of existing (i.e., additive noise, overlapping windows) and novel (i.e., magnitude warping, wavelet decomposition, synthetic sEMG models) strategies of data augmentation for electromyography signals. A set of metrics (i.e., classification accuracy, silhouette score, and Davies–Bouldin index) and visualizations help with the assessment and provides insights about their performance. Methods like signal magnitude warping and wavelet decomposition yield considerable increase (up to 16%) in classification accuracy across two benchmark datasets. Particularly, a significant improvement of 1% in the classification accuracy of the state-of-the-art model in hand gesture recognition is achieved.

show abstract

Deep Learning in EMG-based Gesture Recognition

Cited by 56 publications

References 16 publications

Robust Real-Time Embedded EMG Recognition Framework Using Temporal Convolutional Networks on a Multicore IoT Processor

Robust Real-Time Embedded EMG Recognition Framework Using Temporal Convolutional Networks on a Multicore IoT Processor

Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG

Data Augmentation of Surface Electromyography for Hand Gesture Recognition

Contact Info

Product

Resources

About