Deep learning for surface electromyography artifact contamination type detection

Real-time identification of noise type contaminated in surface electromyogram signals using efficient statistical features

Different types of noise contaminating the surface electromyogram (EMG) signal may degrade the recognition performance. For noise removal, the type of noise has to first be identified. In this paper, we propose a real-time efficient system for identifying a clean EMG signal and noisy EMG signals contaminated with any one of the following three types of noise: electrocardiogram interference, spike noise, and power line interference. Two statistical descriptors, kurtosis and skewness, are used as input features for the cascading quadratic discriminant analysis classifier. An efficient simplification of kurtosis and skewness calculations that can reduce computation time and memory storage is proposed. The experimental results from the real-time system based on an ATmega 2560 microcontroller demonstrate that the kurtosis and skewness values show root mean square errors between the traditional and proposed efficient techniques of 0.08 and 0.09, respectively. The identification accuracy with five-fold cross-validation resulting from the quadratic discriminant analysis classifier is 96.00%.

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

Actor-Critic Reinforcement Learning Based Algorithm for Contaminant Minimization in sEMG Movement Recognition

This paper aims to present an approach based on Reinforcement Learning (RL) concept to detect contaminants' type and minimize their effect on surface electromyography signal (sEMG) based movement recognition. The referred method was applied in the pre-processing stage of a sEMG based motion classification system using the Ninapro database 2 artificially contaminated with electrocardiography (ECG) interference, motion artifact (MOA), powerline interference (PLI) and additive white Gaussian noise (WGN). Support Vector Machine was the method for movement classification. The results showed an improvement of 8.9%, 16.7%, 15.9%, 16.5%, and 11.9% in the movement recognition accuracy with the application of the pre-processing algorithm to restore, respectively, one, three, six, nine, and 12 contaminated channels.

Design and Evaluation of a Custom-Made Electromyographic Biofeedback System for Facial Rehabilitation

Background

In the rehabilitation of postoperative facial palsy, physical therapy is of paramount importance. However, in the early rehabilitation phase, voluntary movements are often limited, and thus, the motivation of patients is impacted. In these situations, biofeedback of facial electromyographic (EMG) signals enables the visual representation of the rehabilitation progress, even without apparent facial movements. In the present study, we designed and evaluated a custom-made EMG biofeedback system enabling cost-effective facial rehabilitation.

Methods

This prospective study describes a custom-made EMG system, consisting of a microcontroller board and muscle sensors, which was used to record the EMG of frontal and zygomatic facial muscles during frowning and smiling. First, the mean EMG amplitudes and movement onset detection rates (ACC) achieved with the custom-made EMG system were compared with a commercial EMG device in 12 healthy subjects. Subsequently, the custom-made device was applied to 12 patients with and without postoperative facial paresis after neurosurgical intervention. Here, the ratio [laterality index (LI)] between the mean EMG amplitude of the healthy and affected side was calculated and related to the facial function as measured by the House and Brackmann scale (H&B) ranging from 1 (normal) to 6 (total paralysis).

Results

In healthy subjects, a good correlation was measured between the mean EMG amplitudes of the custom-made and commercial EMG device for both frontal (r = 0.84, p = 0.001) and zygomatic muscles (r = 0.8, p = 0.002). In patients, the LI of the frontal and zygomatic muscles correlated significantly with the H&B (r = −0.83, p = 0.001 and r = −0.65, p = 0.023). The ACC of the custom-made EMG system varied between 65 and 79% depending on the recorded muscle and cohort.

Conclusion

The present study demonstrates a good application potential of our custom-made EMG biofeedback device to detect facial EMG activity in healthy subjects as well as patients with facial palsies. There is a correlation between the electrophysiological measurements and the clinical outcome. Such a device might enable cost-efficient home-based facial EMG biofeedback. However, movement detection accuracy should be improved in future studies to reach ranges of commercial devices.