Recognition of hand movements in a trans-radial amputated subject by sEMG

Recurrent Neural Network as Estimator for a Virtual sEMG Channel

This study aims at estimating a virtual surface Electromyography (sEMG) channel through a Recurrent Neural Network (RNN) by using Long Short-Term Memory (LSTM) nodes. The virtual channel is used to classify hand postures from the publicly NinaPro database with a multi-class, one-against-all Support Vector Machine (SVM) using the Root Mean Square RMS of the sEMG signal as feature. The classification of the signals through the virtual channel was compared with uncontaminated data and data contaminated with noise saturation. The hit rate from the clean data has averaged 73.96% ± 3.02%. The classification from the contaminated data of one of the channels has improved from 9.29% ± 4.42% to 66.48% ± 6.11% with the virtual channel.

Identification of forearm skin zones with similar muscle activation patterns during activities of daily living

Background

A deeper knowledge of the activity of the forearm muscles during activities of daily living (ADL) could help to better understand the role of those muscles and allow clinicians to treat motor dysfunctions more effectively and thus improve patients’ ability to perform activities of daily living.

Methods

In this work, we recorded sEMG activity from 30 spots distributed over the skin of the whole forearm of six subjects during the performance of 21 representative simulated ADL from the Sollerman Hand Function Test. Functional principal component analysis and hierarchical cluster analysis (HCA) were used to identify forearm spots with similar muscle activation patterns.

Results

The best classification of spots with similar activity in simulated ADL consisted in seven muscular-anatomically coherent groups: (1) wrist flexion and ulnar deviation; (2) wrist flexion and radial deviation; (3) digit flexion; (4) thumb extension and abduction/adduction; (5) finger extension; (6) wrist extension and ulnar deviation; and (7) wrist extension and radial deviation.

Conclusion

The number of sEMG sensors could be reduced from 30 to 7 without losing any relevant information, using them as representative spots of the muscular activity of the forearm in simulated ADL. This may help to assess muscle function in rehabilitation while also simplifying the complexity of prosthesis control.

Learning from demonstration: Teaching a myoelectric prosthesis with an intact limb via reinforcement learning

Prosthetic arms should restore and extend the capabilities of someone with an amputation. They should move naturally and be able to perform elegant, coordinated movements that approximate those of a biological arm. Despite these objectives, the control of modern-day prostheses is often nonintuitive and taxing. Existing devices and control approaches do not yet give users the ability to effect highly synergistic movements during their daily-life control of a prosthetic device. As a step towards improving the control of prosthetic arms and hands, we introduce an intuitive approach to training a prosthetic control system that helps a user achieve hard-to-engineer control behaviours. Specifically, we present an actor-critic reinforcement learning method that for the first time promises to allow someone with an amputation to use their non-amputated arm to teach their prosthetic arm how to move through a wide range of coordinated motions and grasp patterns. We evaluate our method during the myoelectric control of a multi-joint robot arm by non-amputee users, and demonstrate that by using our approach a user can train their arm to perform simultaneous gestures and movements in all three degrees of freedom in the robot's hand and wrist based only on information sampled from the robot and the user's above-elbow myoelectric signals. Our results indicate that this learning-from-demonstration paradigm may be well suited to use by both patients and clinicians with minimal technical knowledge, as it allows a user to personalize the control of his or her prosthesis without having to know the underlying mechanics of the prosthetic limb. These preliminary results also suggest that our approach may extend in a straightforward way to next-generation prostheses with precise finger and wrist control, such that these devices may someday allow users to perform fluid and intuitive movements like playing the piano, catching a ball, and comfortably shaking hands.

Fully embedded myoelectric control for a wearable robotic hand orthosis

To prevent learned non-use of the affected hand in chronic stroke survivors, rehabilitative training should be continued after discharge from the hospital. Robotic hand orthoses are a promising approach for home rehabilitation. When combined with intuitive control based on electromyography, the therapy outcome can be improved. However, such systems often require extensive cabling, experience in electrode placement and connection to external computers. This paper presents the framework for a stand-alone, fully wearable and real-time myoelectric intention detection system based on the Myo armband. The hard and software for real-time gesture classification were developed and combined with a routine to train and customize the classifier, leading to a unique ease of use. The system including training of the classifier can be set up within less than one minute. Results demonstrated that: (1) the proposed algorithm can classify five gestures with an accuracy of 98%, (2) the final system can online classify three gestures with an accuracy of 94.3% and, in a preliminary test, (3) classify three gestures from data acquired from mildly to severely impaired stroke survivors with an accuracy of over 78.8%. These results highlight the potential of the presented system for electromyography-based intention detection for stroke survivors and, with the integration of the system into a robotic hand orthosis, the potential for a wearable platform for all day robot-assisted home rehabilitation.

Using non-iterative methods and random weight networks to classify upper-limb movements through sEMG signals

This paper presents the use of two non-iterative methods to perform the classification of 17 different upper-limb movements through sEMG signal processing. The two methods were compared with a SVM classifier using three different databases involving amputee subjects. The non-iterative methods presented equivalent or superior classification accuracy than SVM method. Thereafter a stage of PCA pre-processing method was used in order to promote a better class separation prior the non-iterative classifiers. The best accuracy result without PCA was achieved by the Regularized Extreme Learning Machines algorithm (88,4% for non-amputee subjects and 79,4% for the amputee). The PCA method used boosted the accuracy of the two non-iterative methods which the mean accuracy was 94% for the non-amputee subjects and 85% for the amputee subjects.

Support vectors machine classification of surface electromyography for non-invasive naturally controlled hand prostheses

The scientific researches in human rehabilitation techniques have continually evolved to offer again the mobility and freedom lost to disability. Many systems managed by myoelectric signals intended to mimic the movement of the human arm still have results considered partial, which makes it subject of many researches. The use of Natural Interfaces Signal Processing methods makes possible to design systems capable of offering prosthesis in a more natural and intuitive way. This paper presents a study investigating the use of forearm surface electromyography (sEMG) signals for classification of specific movements of hand using 12 sEMG channels and support vector machine (SVM). The system acquired the sEMG signal using a virtual model as a visual stimulus in order to demonstrate to the volunteer the hand movements which must be replicated by them. The Root Mean Square (RMS) value feature is extracted of the signal and it serves as input data for the classification with SVM. The classification stage used three types of kernel functions (linear, polynomial, radial basis) for comparison of the results. The average accuracy reached for the classification of seventeen distinct movements of 83.7% was achieved using the SVM linear classifier, 80.8% was achieved using the SVM polynomial classifier and 85.1% was achieved using the SVM radial basis classifier.

Classification of hand movements in amputated subjects by sEMG and accelerometers

Numerous recent studies have aimed to improve myoelectric control of prostheses. However, the majority of these studies is characterized by two problems that could be easily fulfilled with recent resources supplied by the scientific literature. First, the majority of these studies use only intact subjects, with the unproved assumption that the results apply equally to amputees. Second, usually only electromyography data are used, despite other sensors (e.g., accelerometers) being easy to include into a real life prosthesis control system. In this paper we analyze the mentioned problems by the classification of 40 hand movements in 5 amputated and 40 intact subjects, using both sEMG and accelerometry data and applying several different state of the art methods. The datasets come from the NinaPro database, which supplies publicly available sEMG data to develop and test machine learning algorithms for prosthetics. The number of subjects can seem small at first sight, but it is not considering the literature of the field (which has to face the difficulty of recruiting trans-radial hand amputated subjects). Our results indicate that the maximum average classification accuracy for amputated subjects is 61.14%, which is just 15.86% less than intact subjects, and they show that intact subjects results can be used as proxy measure for amputated subjects. Finally, our comparison shows that accelerometry as a modality is less affected by amputation than electromyography, suggesting that real life prosthetics performance may easily be improved by inclusion of accelerometers.

Natural control capabilities of robotic hands by hand amputated subjects

People with transradial hand amputations who own a myoelectric prosthesis currently have some control capabilities via sEMG. However, the control systems are still limited and not natural. The Ninapro project is aiming at helping the scientific community to overcome these limits through the creation of publicly available electromyography data sources to develop and test machine learning algorithms. In this paper we describe the movement classification results gained from three subjects with an homogeneous level of amputation, and we compare them with the results of 40 intact subjects. The number of considered subjects can seem small at first sight, but it is not considering the literature of the field (which has to face the difficulty of recruiting trans-radial hand amputated subjects). The classification is performed with four different classifiers and the obtained balanced classification rates are up to 58.6% on 50 movements, which is an excellent result compared to the current literature. Successively, for each subject we find a subset of up to 9 highly independent movements, (defined as movements that can be distinguished with more than 90% accuracy), which is a deeply innovative step in literature. The natural control of a robotic hand in so many movements could lead to an immediate progress in robotic hand prosthetics and it could deeply change the quality of life of amputated subjects.

Extraction and Classification of Multichannel Electromyographic Activation Trajectories for Hand Movement Recognition

This paper proposes a system for hand movement recognition using multichannel electromyographic (EMG) signals obtained from the forearm surface. This system can be used to control prostheses or to provide inputs for a wide range of human computer interface systems. In this work, the hand movement recognition problem is formulated as a multi-class distance based classification of multi-dimensional sequences. More specifically, the extraction of multi-channel EMG activation trajectories underlying hand movements, and classifying the extracted trajectories using a metric based on multi-dimensional dynamic time warping are investigated. The developed methods are evaluated using the publicly available NINAPro database comprised of 40 different hand movements performed by 40 subjects. The average movement error rate obtained across the 40 subjects is 0.09±0.047. The low error rate demonstrates the efficacy of the proposed trajectory extraction method and the discriminability of the utilized distance metric.