Muscles Alive: Their Functions Revealed by Electromyography

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human-computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning--based HAR.

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances.

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human-computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR. 

/pdf/deep-learning-in-human-activity-recognition-with-wearable-2n4xie8e.pdf

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Human machine interfaces (HMIs) are employed in a broad range of applications, spanning from assistive devices for disability to remote manipulation and gaming controllers. In this study, a new piezoresistive sensors array armband is proposed for hand gesture recognition. The armband encloses only three sensors targeting specific forearm muscles, with the aim to discriminate eight hand movements. Each sensor is made by a force-sensitive resistor (FSR) with a dedicated mechanical coupler and is designed to sense muscle swelling during contraction. The armband is designed to be easily wearable and adjustable for any user and was tested on 10 volunteers. Hand gestures are classified by means of different machine learning algorithms, and classification performances are assessed applying both, the 10-fold and leave-one-out cross-validations. A linear support vector machine provided 96% mean accuracy across all participants. Ultimately, this classifier was implemented on an Arduino platform and allowed successful control for videogames in real-time. The low power consumption together with the high level of accuracy suggests the potential of this device for exergames commonly employed for neuromotor rehabilitation. The reduced number of sensors makes this HMI also suitable for hand-prosthesis control.

/pdf/a-piezoresistive-array-armband-with-reduced-number-of-2ku6u1xcpc.pdf

A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition.

The electromyography (EMG) signal has great potential to determine the hand gestures automatically before the actual move begins. However, parameters of the sliding window along with the EMG signal, such as window size and overlapping size, as well as the number of votes in post-processing, such as majority voting, can significantly influence the gesture recognition accuracy. These phenomena have been investigated only in a few studies on a small number of subjects. The aim of this study is two-fold. First, to determine the influence of different window and overlapping sizes on the machine-learning performance using a large database consists of forty healthy subjects. Second, to develop a novel multi-window scheme to accumulate a large number of votes compared to the conventional single-window majority voting to improve gesture recognition accuracy. A large publicly available EMG dataset was used in this study. The window and overlapping sizes were varied between 50ms and 500ms, and between 0% and 80%, respectively. Six machine-learning algorithms, including k-Nearest Neighbor, Linear Discriminant Analysis, Logistic Regression, Naive Bayes, Support Vector Machine, and Random Forest were used to classify six different hand gestures. Results show that the overall classification accuracy can be substantially improved by increasing the window size, overlapping size, and the number of votes in the majority voting strategy (p < 0.05). The maximum accuracy was achieved using the Random Forest algorithm. The two-way repeated measure analysis of variance shows that the proposed multi-window scheme substantially improved the overall accuracy of the machine-learning algorithms compared to the conventional majority voting. The proposed method can be instrumental for efficient control of prosthetic or exoskeleton devices.

A Multi-Window Majority Voting Strategy to Improve Hand Gesture Recognition Accuracies Using Electromyography Signal

Upper limb amputation is a condition that significantly restricts the amputees from performing their daily activities. The myoelectric prosthesis, using signals from residual stump muscles, is aimed at restoring the function of such lost limbs seamlessly. Unfortunately, the acquisition and use of such myosignals are cumbersome and complicated. Furthermore, once acquired, it usually requires heavy computational power to turn it into a user control signal. Its transition to a practical prosthesis solution is still being challenged by various factors particularly those related to the fact that each amputee has different mobility, muscle contraction forces, limb positional variations and electrode placements. Thus, a solution that can adapt or otherwise tailor itself to each individual is required for maximum utility across amputees. Modified machine learning schemes for pattern recognition have the potential to significantly reduce the factors (movement of users and contraction of the muscle) affecting the traditional electromyography (EMG)-pattern recognition methods. Although recent developments of intelligent pattern recognition techniques could discriminate multiple degrees of freedom with high-level accuracy, their efficiency level was less accessible and revealed in real-world (amputee) applications. This review paper examined the suitability of upper limb prosthesis (ULP) inventions in the healthcare sector from their technical control perspective. More focus was given to the review of real-world applications and the use of pattern recognition control on amputees. We first reviewed the overall structure of pattern recognition schemes for myo-control prosthetic systems and then discussed their real-time use on amputee upper limbs. Finally, we concluded the paper with a discussion of the existing challenges and future research recommendations.

Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation

Active hand prostheses are usually controlled by electromyography (EMG) signals acquired from few muscles available in the residual limb. In general, it is necessary to estimate the envelope of the EMG in real-time to implement the control of the prosthesis. Recently, sensors based on Force Sensitive Resistor (FSR) proved to be a valid alternative to monitor muscle contraction. However, FSR-based sensors measure the mechanical phenomena related to muscle contraction rather than those electrical. The aim of this study is to test the difference between the EMG and force signal in controlling a prosthetic hand. Particular emphasis has been placed on verify the prosthesis activation speed and their application to fast grabbing hand prosthesis as the "Federica" hand. Indeed, there is an intrinsic electro-mechanical delay during muscle contraction, since the electrical activation of muscle fibres always precedes their mechanical contraction. However, the EMG signal needs to be processed to control prosthesis and such filtering unavoidably causes a delay. On the contrary the force signal doesn’t need any processing. Both EMG and force signals were simultaneously recorded from the flexor carpi ulnaris muscle, while subject performed wrist flexions. The raw EMG signals were rectified and low-pass filtered to extract their envelopes. Different widespread operators were used: Moving Average, Root Mean Square, Butterworth low-pass; the cut-off frequency was set to 5 Hz. Afterward, a classic double threshold method was used to compute the muscle contraction onsets (i.e. the signal should exceed a threshold level for a certain time period). Results showed that the lag introduced by the low-pass filtering of the rectified EMG, generates delays greater than those associated with the force sensor. This analysis confirms the possibility of using force sensors as a convenient alternative to EMG signals in the control of prostheses.

Measurement of muscle contraction timing for prosthesis control: a comparison between electromyography and force-myography

From the evaluation of electrical activity of muscles to the development of myoelectric prosthetic control/manmachine interfaces, the electromyography (EMG) signal has always been the first choice for both clinicians and engineers. However, due to the many drawbacks of EMG (e.g. skin preparation, electromagnetic interferences, high sample rate, etc.), researchers have strived to find suitable alternatives. We propose as a valid alternative, the dry-contact, low-cost sensor based on a force sensitive resistor (FSR). This sensor applied to the skin through a hard, circular base senses the muscle contraction mechanically and this signal can be actually employed to directly replace the EMG linear envelope (EMGLE) that is typically used as a control signal in prosthetics applications. To reduce the output drift (resistance) caused by FSR edges and to maintain the FSR sensitivity over a wide input force range, its signal conditioning is implemented with a reference voltage strategy (voltage output proportional to force). In this paper, we focus on the validation experiments aimed at finding the best FSR position(s) to replace a single EMG lead. Simultaneous recording of EMG and FSR, using up to three FSRs placed directly over the EMG electrodes, in the middle of the targeted muscle was performed on a small sample of two volunteer subjects. Our results show a high correlation (up to 0.92) between FSR output and EMG linear envelope.

Nawadita Parajuli

Papers

Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation

Measurement of muscle contraction timing for prosthesis control: a comparison between electromyography and force-myography

Electrodeless FSR Linear Envelope Signal for Muscle Contraction Measurement