Despite not recording directly from neural cells, the surface electromyogram (EMG) signal contains information on the neural drive to muscles, i.e., the spike trains of motor neurons. Using this property, myoelectric control consists of the recording of EMG signals for extracting control signals to command external devices, such as hand prostheses. In commercial control systems, the intensity of muscle activity is extracted from the EMG and used for single degrees of freedom activation (direct control). Over the past 60 years, academic research has progressed to more sophisticated approaches but, surprisingly, none of these academic achievements has been implemented in commercial systems so far. We provide an overview of both commercial and academic myoelectric control systems and we analyze their performance with respect to the characteristics of the ideal myocontroller. Classic and relatively novel academic methods are described, including techniques for simultaneous and proportional control of multiple degrees of freedom and the use of individual motor neuron spike trains for direct control. The conclusion is that the gap between industry and academia is due to the relatively small functional improvement in daily situations that academic systems offer, despite the promising laboratory results, at the expense of a substantial reduction in robustness. None of the systems so far proposed in the literature fulfills all the important criteria needed for widespread acceptance by the patients, i.e. intuitive, closed-loop, adaptive, and robust real-time ( 200 ms delay) control, minimal number of recording electrodes with low sensitivity to repositioning, minimal training, limited complexity and low consumption. Nonetheless, in recent years, important efforts have been invested in matching these criteria, with relevant steps forwards.

The Extraction of Neural Information from the Surface EMG for the Control of Upper-Limb Prostheses: Emerging Avenues and Challenges

An efficient and flexible dictionary structure is proposed for sparse and redundant signal representation. The proposed sparse dictionary is based on a sparsity model of the dictionary atoms over a base dictionary, and takes the form D = ? A, where ? is a fixed base dictionary and A is sparse. The sparse dictionary provides efficient forward and adjoint operators, has a compact representation, and can be effectively trained from given example data. In this, the sparse structure bridges the gap between implicit dictionaries, which have efficient implementations yet lack adaptability, and explicit dictionaries, which are fully adaptable but non-efficient and costly to deploy. In this paper, we discuss the advantages of sparse dictionaries, and present an efficient algorithm for training them. We demonstrate the advantages of the proposed structure for 3-D image denoising.

/pdf/double-sparsity-learning-sparse-dictionaries-for-sparse-1sikebnnor.pdf

Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation

In pattern recognition-based myoelectric control, high accuracy for multiple discriminated motions is presented in most of related literature. However, there is a gap between the classification accuracy and the usability of practical applications of myoelectric control, especially the effect of long-term usage. This paper proposes and investigates the behavior of fifty time-domain and frequency-domain features to classify ten upper limb motions using electromyographic data recorded during 21days. The most stable single feature and multiple feature sets are presented with the optimum configuration of myoelectric control, i.e. data segmentation and classifier. The result shows that sample entropy (SampEn) outperforms other features when compared using linear discriminant analysis (LDA), a robust classifier. The averaged test classification accuracy is 93.37%, when trained in only initial first day. It brings only 2.45% decrease compared with retraining schemes. Increasing number of features to four, which consists of SampEn, the fourth order cepstrum coefficients, root mean square and waveform length, increase the classification accuracy to 98.87%. The proposed techniques achieve to maintain the high accuracy without the retraining scheme. Additionally, this continuous classification allows the real-time operation.

http://iihm.imag.fr/publs/2014/ESWA-Draft.pdf

EMG feature evaluation for improving myoelectric pattern recognition robustness

In recent years, deep learning algorithms have become increasingly more prominent for their unparalleled ability to automatically learn discriminant features from large amounts of data. However, within the field of electromyography-based gesture recognition, deep learning algorithms are seldom employed as they require an unreasonable amount of effort from a single person, to generate tens of thousands of examples. This paper’s hypothesis is that general, informative features can be learned from the large amounts of data generated by aggregating the signals of multiple users, thus reducing the recording burden while enhancing gesture recognition. Consequently, this paper proposes applying transfer learning on aggregated data from multiple users while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets. Two datasets comprised 19 and 17 able-bodied participants, respectively (the first one is employed for pre-training), were recorded for this work, using the Myo armband. A third Myo armband dataset was taken from the NinaPro database and is comprised ten able-bodied participants. Three different deep learning networks employing three different modalities as input (raw EMG, spectrograms, and continuous wavelet transform (CWT)) are tested on the second and third dataset. The proposed transfer learning scheme is shown to systematically and significantly enhance the performance for all three networks on the two datasets, achieving an offline accuracy of 98.31% for 7 gestures over 17 participants for the CWT-based ConvNet and 68.98% for 18 gestures over 10 participants for the raw EMG-based ConvNet. Finally, a use-case study employing eight able-bodied participants suggests that real-time feedback allows users to adapt their muscle activation strategy which reduces the degradation in accuracy normally experienced over time.

/pdf/deep-learning-for-electromyographic-hand-gesture-signal-35yh5gi4gl.pdf

Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning

Several efforts have been carried out to enhance dexterous hand prosthesis control by impaired individuals. Choosing which voluntary signal to use for control purposes is a critical element to achieve this goal. This review presents and discusses the recent results achieved by using electromyographic signals, recorded either with surface (sEMG) or intramuscular (iEMG) electrodes, and electroneurographic (ENG) signals. The potential benefits and shortcomings of the different approaches are described with a particular attention to the definition of all the steps required to achieve an effective hand prosthesis control in the different cases. Finally, a possible roadmap in the field is also presented.

/pdf/control-of-hand-prostheses-using-peripheral-information-3amjn63ibu.pdf

Control of Hand Prostheses Using Peripheral Information

Respiratory rate (RR), which is an essential observation for prediagnosis, can be obtained indirectly from the electrocardiogram (ECG), the so-called ECG-derived respiration (EDR). In this paper, we compared embroidered electrodes with gel electrodes on their performance in capturing EDR signals and analysed which frequency feature best estimates RR. Data were collected from 9 healthy subjects. Results reveal that (1) embroidered electrodes performed similarly to gel electrodes (P = 0.077), (2) using the median frequency of the obtained EDR signals is significantly better (P = 0.01) than the counting methods in the time domain. The obtained results are relevant for the future development of textile-based sensors.

Comparison between Embroidered and Gel Electrodes on ECG-Derived Respiration Rate

In real-life scenarios, outside of the laboratory setting, the performance of brain-computer interface (BCI) systems is influenced by the user’s mental state such as attentional diversion. Here, we propose a novel online BCI system able to adapt with variations in the users’ attention during real-time movement execution. Electroencephalography (EEG) signals were recorded from twelve channels in twelve healthy participants and two stroke patients while performing 50 trials of ankle dorsiflexion simultaneously with an auditory oddball task. For each participant, the selected channels, classifiers and features from the offline mode were used in the online mode to predict the attention status. For both healthy controls and subacute stroke patients, feedback to the user on attentional status reduced the amount of attentional diversion created by the oddball task. The findings presented here demonstrate that the users’ attention can be monitored in a fully online BCI system, and further, that real-time neurofeedback on the attentional state of the user can be implemented to focus the attention of the user back onto the main task of the BCI for neuromodulation. Monitoring the users’ attention status will have a major impact in the BCI for neurorehabilitation area in the future.

Online adaptive synchronous BCI system with attention variations

To provide amputees with intuitive prosthetic control systems, surface electromyography (EMG) has shown promising results in several studies. Myo armband (MYB) is a wireless, ready-to-use technology developed by Thalmic Labs, able to record eight EMG channels with limited frequency bandwidth (<100 Hz). The aim of this study was to evaluate the performance of five classifiers in order to assess the suitability of the MYB to provide reliable accuracy in comparison to the conventional EMG systems (CONV). Eight able-bodied subjects performed nine hand gestures in a crossover acquisition design. Six time-domain features were extracted from the data to evaluate the offline classification error of five classifiers: Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes (NB) and Neural Networks (NN). Friedman’s test showed no significant difference between CONV and MYB with six channels (P=0.10) with mean classification error of LDA (5.82 ± 3.63% vs. 9.86 ± 8.05%), SVM (9.70 ± 6.02% vs. 11.01 ± 8.79%), KNN (8.30 ± 6.00% vs. 11.12 ± 8.94%), NB (12.48 ± 8.51% vs. 13.77 ± 9.76%) and NN (1.77 ±1.28% vs. 4.64 ± 4.25%) for CONV and MYB, respectively. Although lower classification error was obtained, no significant improvement was found between MYB using eight and six channels (P=0.16).

Evaluation of classifiers performance using the myo armband

A better understanding of neural pain processing and of the development of pain over time, is critical to identify objective measures of pain and to evaluate the effect of pain alleviation therapies. One issue is, that the brain areas known to be related to pain processing are not exclusively responding to painful stimuli, and the neuronal activity is also influenced by other brain areas. Functional connectivity reflects synchrony or covariation of activation between groups of neurons. Previous studies found changes in connectivity days or weeks after pain induction. However, less in known on the temporal development of pain. Our objective was therefore to investigate the interaction between the anterior cingulate cortex (ACC) and primary somatosensory cortex (SI) in the hyperacute (minute) and sustained (hours) response in an animal model of neuropathic pain. Intra-cortical local field potentials (LFP) were recorded in 18 rats. In 10 rats the spared nerve injury model was used as an intervention. The intra-cortical activity was recorded before, immediately after, and three hours after the intervention. The interaction was quantified as the calculated correlation and coherence. The results from the intervention group showed a decrease in correlation between ACC and SI activity, which was most pronounced in the hyperacute phase but a longer time frame may be required for plastic changes to occur. This indicated that both SI and ACC are involved in hyperacute pain processing.

Nerve Injury Decreases Hyperacute Resting-State Connectivity Between the Anterior Cingulate and Primary Somatosensory Cortex in Anesthetized Rats

The respiratory rate (RR) is a vital physiological parameter in prediagnosis and daily monitoring. It can be obtained indirectly from Electrocardiogram (ECG) signals using ECG-derived respiration (EDR) techniques. As part of the study in designing an early cardiac screening system, this work aimed to study whether the accuracy of ECG derived RR depends on the auscultation sites. Experiments were conducted on 12 healthy subjects to obtain simultaneous ECG (at auscultation sites and Lead I as reference) and respiration signals from a microphone close to the nostril. Four EDR algorithms were tested on the data to estimate RR in both the time and frequency domain. Results reveal that: (1) The location of the ECG electrodes between auscultation sites does not impact the estimation of RR, (2) baseline wander and amplitude modulation algorithms outperformed the frequency modulation and band-pass filter algorithms, (3) using frequency domain features to estimate RR can provide more accurate RR except when using the band-pass filter algorithm. These results pave the way for ECG-based RR estimation in miniaturised integrated cardiac screening device.

https://www.mdpi.com/1424-8220/21/1/78/pdf

Ernest Nlandu Kamavuako

Papers

Comparison between Embroidered and Gel Electrodes on ECG-Derived Respiration Rate

Online adaptive synchronous BCI system with attention variations

Evaluation of classifiers performance using the myo armband

Nerve Injury Decreases Hyperacute Resting-State Connectivity Between the Anterior Cingulate and Primary Somatosensory Cortex in Anesthetized Rats

Estimation of the Respiratory Rate from Localised ECG at Different Auscultation Sites.