A review on EMG-based motor intention prediction of continuous human upper limb motion for human-robot collaboration

Gesture recognition using sparse multichannel surface electromyography (sEMG) is a challenging problem, and the solutions are far from optimal from the point of view of muscle–computer interface. In this paper, we address this problem from the context of multi-view deep learning. A novel multi-view convolutional neural network (CNN) framework is proposed by combining classical sEMG feature sets with a CNN-based deep learning model. The framework consists of two parts. In the first part, multi-view representations of sEMG are modeled in parallel by a multistream CNN, and a performance-based view construction strategy is proposed to choose the most discriminative views from classical feature sets for sEMG-based gesture recognition. In the second part, the learned multi-view deep features are fused through a view aggregation network composed of early and late fusion subnetworks, taking advantage of both early and late fusion of learned multi-view deep features. Evaluations on 11 sparse multichannel sEMG databases as well as five databases with both sEMG and inertial measurement unit data demonstrate that our multi-view framework outperforms single-view methods on both unimodal and multimodal sEMG data streams.

Surface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning

This paper proposed a wearable smart sEMG recorder integrated gradient boosting decision tree (GBDT) based hand gesture recognition. A hydrogel-silica gel based flexible surface electrode band is used as the tissue interface. The sEMG signal is collected using a neural signal acquisition analog front end (AFE) chip. A quantitative analysis method is proposed to balance the algorithm complexity and recognition accuracy. A parallel GBDT implementation is proposed featuring a low latency. The proposed GBDT based neural signal processing unit (NSPU) is implemented on an FPGA near the AFE. A RF module is used for wireless communication. A hand gesture set including 12 gestures is designed for human-computer interaction. Experimental results show an overall hand gesture recognition accuracy of 91%.

/pdf/design-of-a-flexible-wearable-smart-semg-recorder-integrated-1ivixmltd3.pdf

Design of a Flexible Wearable Smart sEMG Recorder Integrated Gradient Boosting Decision Tree Based Hand Gesture Recognition

Stretchable, transparent triboelectric nanogenerator as a highly sensitive self-powered sensor for driver fatigue and distraction monitoring

Wearable technology can be employed to elevate the abilities of humans to perform demanding and complex tasks more efficiently. Armbands capable of surface electromyography (sEMG) are attractive and noninvasive devices from which human intent can be derived by leveraging machine learning. However, the sEMG acquisition systems currently available tend to be prohibitively costly for personal use or sacrifice wearability or signal quality to be more affordable. This work introduces the 3DC Armband designed by the Biomedical Microsystems Laboratory in Laval University; a wireless, 10-channel, 1000 sps, dry-electrode, low-cost (∼150 USD) myoelectric armband that also includes a 9-axis inertial measurement unit. The proposed system is compared with the Myo Armband by Thalmic Labs, one of the most popular sEMG acquisition systems. The comparison is made by employing a new offline dataset featuring 22 able-bodied participants performing eleven hand/wrist gestures while wearing the two armbands simultaneously. The 3DC Armband systematically and significantly ( p < 0.05 ) outperforms the Myo Armband, with three different classifiers employing three different input modalities when using ten seconds or more of training data per gesture. This new dataset, alongside the source code, Altium project and 3-D models are made readily available for download within a Github repository.

A Low-Cost, Wireless, 3-D-Printed Custom Armband for sEMG Hand Gesture Recognition.

Wearable technology has gained increasing popularity in the applications of healthcare, sports science, and biomedical engineering in recent years. Because of its convenient nature, the wearable technology is particularly useful in the acquisition of the physiological signals. Specifically, the (surface electromyography) sEMG systems, which measure the muscle activation potentials, greatly benefit from this technology in both clinical and industrial applications. However, the current wearable sEMG systems have several drawbacks including inefficient noise cancellation, insufficient measurement quality, and difficult integration to customized applications. Additionally, none of these sEMG data acquisition systems can detect sEMG signals (i.e., contractions), which provides a valuable environment for further studies such as human machine interaction, gesture recognition, and fatigue tracking. To this end, we introduce an embedded, eight channel, noise canceling, wireless, wearable sEMG data acquisition system with adaptive muscle contraction detection. Our design consists of two stages, which are the sEMG sensors and the multichannel data acquisition unit. For the first stage, we propose a low cost, dry, and active sEMG sensor that captures the muscle activation potentials, a data acquisition unit that evaluates these captured multichannel sEMG signals and transmits them to a user interface. In the data acquisition unit, the sEMG signals are processed through embedded, adaptive methods in order to reject the power line noise and detect the muscle contractions. Through extensive experiments, we demonstrate that our sEMG sensor outperforms a widely used commercially available product and our data acquisition system achieves 4.583 dB SNR gain with $98.9784\%$ accuracy in the detection of the contractions.

/pdf/an-embedded-eight-channel-noise-canceling-wireless-wearable-3dum9j99ww.pdf

An Embedded, Eight Channel, Noise Canceling, Wireless, Wearable sEMG Data Acquisition System With Adaptive Muscle Contraction Detection.

One of the biggest issues encountered in the analysis of sensitive electromyography (EMG) sensor data is the power line interference (PLI). Conventional methods in literature either lose valuable sensor data or inadequately decrease the power line noise. Instead of filtering out predetermined frequencies, adaptively estimating the spectrum of PLI can provide better performance. This paper introduces an online adaptive algorithm that removes the power line interference in real time without disturbing the true EMG data. Our method sequentially processes the biomedical signal to properly estimate and remove the PLI component. Through experiments with real EMG data, we compared our method to the five state-of-the-art techniques. Our algorithm outperformed all of them with the highest SNR gain (3.6 dB on average) and with the least disturbance of the true EMG signal (0.0152 dB loss on average). Our method reduces the PLI the most while keeping the valuable sensor data loss at its minimum in comparison to the state-of-the-art. Reducing the noise without disturbing the valuable sensor data provides higher quality signals with decreased interference, which can be better processed and used in biomedical research.

An Adaptive Algorithm for Online Interference Cancellation in EMG Sensors

Muscle fatigue detection and tracking has gained significant attention as the sports science and rehabilitation technologies developed. It is known that muscle fatigue can be evaluated through surface Electromyography (sEMG) sensors, which are portable, non-invasive and applicable for real-time systems. There are plenty of fatigue tracking algorithms, many of which uses frequency, time and time-frequency behaviors of sEMG signals. An example to most commonly used sEMG-based fatigue detection methods can be mean frequency (MNF), median frequency (MDF), zero-crossing rate (ZCR) and continuous wavelet transform (CWT). However, all of these muscle fatigue calculation methods are adversely affected by the dynamically changing sEMG contraction amplitude, since EMG spectrum also demonstrates a shift with the changing signal RMS; powerful contractions lead a shift to high frequency bounds and the opposite happens for the weak. To overcome that, we propose an adaptive algorithm, which learns the effect of contraction power on sEMG power spectral density (PSD) and subtracts that amount of frequency shift from the PSD.

/pdf/an-semg-based-method-to-adaptively-reject-the-effect-of-3lmuzczbjw.pdf

Erhan Ertan

Papers

An Embedded, Eight Channel, Noise Canceling, Wireless, Wearable sEMG Data Acquisition System With Adaptive Muscle Contraction Detection.

An Adaptive Algorithm for Online Interference Cancellation in EMG Sensors

An sEMG-based method to adaptively reject the effect of contraction on spectral analysis for fatigue tracking

An sEMG-based method to adaptively reject the effect of contraction on spectral analysis for fatigue tracking.