Feature Extraction and Selection for Myoelectric Control Based on Wearable EMG Sensors

Comparing online wrist and forearm EMG-based control using a rhythm game-inspired evaluation environment

Objective.The use of electromyogram (EMG) signals recorded from the wrist is emerging as a desirable input modality for human-machine interaction (HMI). Although forearm-based EMG has been used for decades in prosthetics, there has been comparatively little prior work evaluating the performance of wrist-based control, especially in online, user-in-the-loop studies. Furthermore, despite different motivating use cases for wrist-based control, research has mostly adopted legacy prosthesis control evaluation frameworks.Approach.Gaining inspiration from rhythm games and the Schmidt's law speed-accuracy tradeoff, this work proposes a new temporally constrained evaluation environment with a linearly increasing difficulty to compare the online usability of wrist and forearm EMG. Compared to the more commonly used Fitts' Law-style testing, the proposed environment may offer different insights for emerging use cases of EMG as it decouples the machine learning algorithm's performance from proportional control, is easily generalizable to different gesture sets, and enables the extraction of a wide set of usability metrics that describe a users ability to successfully accomplish a task at a certain time with different levels of induced stress.Main results.The results suggest that wrist EMG-based control is comparable to that of forearm EMG when using traditional prosthesis control gestures and can even be better when using fine finger gestures. Additionally, the results suggest that as the difficulty of the environment increased, the online metrics and their correlation to the offline metrics decreased, highlighting the importance of evaluating myoelectric control in real-time evaluations over a range of difficulties.Significance.This work provides valuable insights into the future design and evaluation of myoelectric control systems for emerging HMI applications.

Hand gesture recognition with deep residual network using Semg signal

OBJECTIVES

To design and develop a classifier, named Sewing Driving Training based Optimization-Deep Residual Network (SDTO_DRN) for hand gesture recognition.

METHODS

The electrical activity of forearm muscles generates the signals that can be captured with Surface Electromyography (sEMG) sensors and includes meaningful data for decoding both muscle actions and hand movement. This research develops an efficacious scheme for hand gesture recognition using SDTO_DRN. Here, signal pre-processing is done through Gaussian filtering. Thereafter, desired and appropriate features are extracted. Following that, effective features are chosen using SDTO. At last, hand gesture identification is accomplished based on DRN and this network is effectively fine-tuned by SDTO, which is a combination of Sewing Training Based Optimization (STBO) and Driving Training Based Optimization (DTBO). The datasets employed for the implementation of this work are MyoUP Dataset and putEMG: sEMG Gesture and Force Recognition Dataset.

RESULTS

The designed SDTO_DRN model has gained superior performance with magnificent results by delivering a maximum accuracy of 0.943, True Positive Rate (TPR) of 0.929, True Negative Rate (TNR) of 0.919, Positive Predictive Value (PPV) of 0.924, and Negative Predictive Value (NPV) of 0.924.

CONCLUSIONS

The hand gesture recognition using the proposed model is accurate and improves the effectiveness of the recognition.

Enhancing natural disaster analysis and waste classification: a novel VGG-FL approach

The study of natural disasters is a crucial field that involves analyzing the occurrence, impact, and aftermath of various natural hazards that can cause significant harm to communities and the environment. Efficient waste management and environmental protection require proper classification of waste. Analyzing natural disasters and categorizing waste can be a time-consuming task, and conventional methods often struggle with it. However, a new approach called Visual Geometry Group with Federated Learning (VGG-FL) has been introduced to address these challenges. This methodology uses the golden search optimization (GSO) algorithm for feature selection and leverages VGG with federated learning for feature extraction and classification. To test the effectiveness of this method, a disaster image dataset was used to train the VGG-FL model. The results showed that the VGG-FL model attained exceptional accuracy in discerning and categorizing various disaster scenarios. The waste classification dataset simultaneously trains the VGG-FL model to categorize waste based on its characteristics and potential hazards. To measure the model's performance, several evaluation metrics such as accuracy, specificity, precision, F1-score, and recall are utilized to assess the effectiveness of the proposed VGG-FL method. These results are then compared with existing methodologies. The VGG-FL method performs exceptionally well, achieving 98.52% accuracy, 97.48% precision, 97.83% recall, 97.58% F1-score, and 97.12% specificity. These experimental findings demonstrate the efficacy of the VGG-FL method in analyzing natural disasters and classifying waste materials.

Electromyography signal based hand gesture classification system using Hilbert Huang transform and deep neural networks

This research aims to provide the groundwork for smartly categorizing hand movements for use with prosthetic hands. The hand motions are classified using surface electromyography (sEMG) data. In reaction to a predetermined sequence of fibre activation, every single one of our muscles contracts. They could be useful in developing control protocols for bio-control systems, such human-computer interaction and upper limb prostheses. When focusing on hand gestures, data gloves and vision-based approaches are often used. The data glove technique requires tedious and unnatural user engagement, whereas the vision-based solution requires significantly more expensive sensors. This research offered a Deep Neural Network (DNN) automated hand gesticulation recognition system based on electromyography to circumvent these restrictions. This work primarily aims to augment the concert of the hand gesture recognition system via the use of an artificial classifier. To advance the recognition system's classification accuracy, this study explains how to build models of neural networks and how to use signal processing methods. By locating the Hilbert Huang Transform (HHT), one may get the essential properties of the signal. When training a DNN classifier, these characteristics are sent into it. The investigational results reveal that the suggested technique accomplishes a better categorization rate (98.5 % vs. the alternatives).

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks

BACKGROUND

In-home rehabilitation systems are a promising, potential alternative to conventional therapy for stroke survivors. Unfortunately, physiological differences between participants and sensor displacement in wearable sensors pose a significant challenge to classifier performance, particularly for people with stroke who may encounter difficulties repeatedly performing trials. This makes it challenging to create reliable in-home rehabilitation systems that can accurately classify gestures.

METHODS

Twenty individuals who suffered a stroke performed seven different gestures (mass flexion, mass extension, wrist volar flexion, wrist dorsiflexion, forearm pronation, forearm supination, and rest) related to activities of daily living. They performed these gestures while wearing EMG sensors on the forearm, as well as FMG sensors and an IMU on the wrist. We developed a model based on prototypical networks for one-shot transfer learning, K-Best feature selection, and increased window size to improve model accuracy. Our model was evaluated against conventional transfer learning with neural networks, as well as subject-dependent and subject-independent classifiers: neural networks, LGBM, LDA, and SVM.

RESULTS

Our proposed model achieved 82.2% hand-gesture classification accuracy, which was better (P<0.05) than one-shot transfer learning with neural networks (63.17%), neural networks (59.72%), LGBM (65.09%), LDA (63.35%), and SVM (54.5%). In addition, our model performed similarly to subject-dependent classifiers, slightly lower than SVM (83.84%) but higher than neural networks (81.62%), LGBM (80.79%), and LDA (74.89%). Using K-Best features improved the accuracy in 3 of the 6 classifiers used for evaluation, while not affecting the accuracy in the other classifiers. Increasing the window size improved the accuracy of all the classifiers by an average of 4.28%.

CONCLUSION

Our proposed model showed significant improvements in hand-gesture recognition accuracy in individuals who have had a stroke as compared with conventional transfer learning, neural networks and traditional machine learning approaches. In addition, K-Best feature selection and increased window size can further improve the accuracy. This approach could help to alleviate the impact of physiological differences and create a subject-independent model for stroke survivors that improves the classification accuracy of wearable sensors.

TRIAL REGISTRATION NUMBER

The study was registered in Chinese Clinical Trial Registry with registration number CHiCTR1800017568 in 2018/08/04.

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition

Discrete myoelectric control-based gesture recognition has recently gained interest as a possible input modality for many emerging ubiquitous computing applications. Unlike the continuous control commonly employed in powered prostheses, discrete systems seek to recognize the dynamic sequences associated with gestures to generate event-based inputs. More akin to those used in general-purpose human-computer interaction, these could include, for example, a flick of the wrist to dismiss a phone call or a double tap of the index finger and thumb to silence an alarm. Moelectric control systems have been shown to achieve near-perfect classification accuracy, but in highly constrained offline settings. Real-world, online systems are subject to 'confounding factors' (i.e. factors that hinder the real-world robustness of myoelectric control that are not accounted for during typical offline analyses), which inevitably degrade system performance, limiting their practical use. Although these factors have been widely studied in continuous prosthesis control, there has been little exploration of their impacts on discrete myoelectric control systems for emerging applications and use cases. Correspondingly, this work examines, for the first time, three confounding factors and their effect on the robustness of discrete myoelectric control: (1)limb position variability, (2)cross-day use, and a newly identified confound faced by discrete systems (3)gesture elicitation speed. Results from four different discrete myoelectric control architectures: (1) Majority Vote LDA, (2) Dynamic Time Warping, (3) an LSTM network trained with Cross Entropy, and (4) an LSTM network trained with Contrastive Learning, show that classification accuracy is significantly degraded (p<0.05) as a result of each of these confounds. This work establishes that confounding factors are a critical barrier that must be addressed to enable the real-world adoption of discrete myoelectric control for robust and reliable gesture recognition.

Reliability and validity of muscle activity analysis using wearable electromyographs

[Purpose] The aim of this study was to develop a novel wearable surface electromyograph called NOK, and compare its reliability and validity to an existing electromyograph. [Participants and Methods] The study participants were 23 healthy university students (Seven males and 16 females; age 20.3 ± 1.1 years [mean ± standard deviation]; height 162.0 ± 6.7 cm; weight 58.4 ± 10.1 kg) who all gave informed written consent. The newly developed electromyograph (NOK) features a rubberized skin contact surface that requires no electrodes and allows the acquisition of up to 10 channels of muscle waveforms on a portable personal computer. After measuring maximal isometric elbow extension and flexion, we examined muscle waveforms during isometric contractions of elbow joint flexion and extension at approximately 50% of maximal voluntary contraction using both NOK and Delsys electromyographs and compared the results of the two devices. [Results] We found a significant moderate correlation between the measurements by the two devices for biceps and triceps. The measurements by the two devices also showed strong measure-retest reliability. Systematic errors were observed for elbow flexion and extension in the two measurements, indicating limited agreement between the two measurement methods. [Conclusion] Although the new device also has high repeatability and reliability, it is unsuitable for analyzing detailed muscle activity. However, since it can measure up to 10 channels of muscle activity, it is expected to be used in the rehabilitation and sports field in the future.

An Optimized Stimulation Control System for Upper Limb Exoskeleton Robot-Assisted Rehabilitation Using a Fuzzy Logic-Based Pain Detection Approach

The utilization of robotic systems in upper limb rehabilitation has shown promising results in aiding individuals with motor impairments. This research introduces an innovative approach to enhance the efficiency and adaptability of upper limb exoskeleton robot-assisted rehabilitation through the development of an optimized stimulation control system (OSCS). The proposed OSCS integrates a fuzzy logic-based pain detection approach designed to accurately assess and respond to the patient's pain threshold during rehabilitation sessions. By employing fuzzy logic algorithms, the system dynamically adjusts the stimulation levels and control parameters of the exoskeleton, ensuring personalized and optimized rehabilitation protocols. This research conducts comprehensive evaluations, including simulation studies and clinical trials, to validate the OSCS's efficacy in improving rehabilitation outcomes while prioritizing patient comfort and safety. The findings demonstrate the potential of the OSCS to revolutionize upper limb exoskeleton-assisted rehabilitation by offering a customizable and adaptive framework tailored to individual patient needs, thereby advancing the field of robotic-assisted rehabilitation.

Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification

Introduction

Muscular activation sequences have been shown to be suitable time-domain features for classification of motion gestures. However, their clinical application in myoelectric prosthesis control was never investigated so far. The aim of the paper is to evaluate the robustness of these features extracted from the EMG signal in transient state, on the forearm, for classifying common hand tasks.

Methods

The signal associated to four hand gestures and the rest condition were acquired from ten healthy people and two persons with trans-radial amputation. A feature extraction algorithm allowed for encoding the EMG signals into muscular activation sequences, which were used to train four commonly used classifiers, namely Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Non-linear Logistic Regression (NLR) and Artificial Neural Network (ANN). The offline performances were assessed with the entire sample of recruited people. The online performances were assessed with the amputee subjects. Moreover, a comparison of the proposed method with approaches based on the signal envelope in the transient state and in the steady state was conducted.

Results

The highest performance were obtained with the NLR classifier. Using the sequences, the offline classification accuracy was higher than 93% for healthy and amputee subjects and always higher than the approach with the signal envelope in transient state. As regards the comparison with the steady state, the performances obtained with the proposed method are slightly lower (<4%), but the classification occurred at least 200 ms earlier. In the online application, the motion completion rate reached up to 85% of the total classification attempts, with a motion selection time that never exceeded 218 ms.

Discussion

Muscular activation sequences are suitable alternatives to the time-domain features commonly used in classification problems belonging to the sole EMG transient state and could be potentially exploited in control strategies of myoelectric prosthesis hands.

Empirical Myoelectric Feature Extraction and Pattern Recognition in Hemiplegic Distal Movement Decoding

In myoelectrical pattern recognition (PR), the feature extraction methods for stroke-oriented applications are challenging and remain discordant due to a lack of hemiplegic data and limited knowledge of skeletomuscular function. Additionally, technical and clinical barriers create the need for robust, subject-independent feature generation while using supervised learning (SL). To the best of our knowledge, we are the first study to investigate the brute-force analysis of individual and combinational feature vectors for acute stroke gesture recognition using surface electromyography (EMG) of 19 patients. Moreover, post-brute-force singular vectors were concatenated via a Fibonacci-like spiral net ranking as a novel, broadly applicable concept for feature selection. This semi-brute-force navigated amalgamation in linkage (SNAiL) of EMG features revealed an explicit classification rate performance advantage of 10-17% compared to canonical feature sets, which can drastically extend PR capabilities in biosignal processing.

Surgical Instrument Signaling Gesture Recognition Using Surface Electromyography Signals

Surgical Instrument Signaling (SIS) is compounded by specific hand gestures used by the communication between the surgeon and surgical instrumentator. With SIS, the surgeon executes signals representing determined instruments in order to avoid error and communication failures. This work presented the feasibility of an SIS gesture recognition system using surface electromyographic (sEMG) signals acquired from the Myo armband, aiming to build a processing routine that aids telesurgery or robotic surgery applications. Unlike other works that use up to 10 gestures to represent and classify SIS gestures, a database with 14 selected gestures for SIS was recorded from 10 volunteers, with 30 repetitions per user. Segmentation, feature extraction, feature selection, and classification were performed, and several parameters were evaluated. These steps were performed by taking into account a wearable application, for which the complexity of pattern recognition algorithms is crucial. The system was tested offline and verified as to its contribution for all databases and each volunteer individually. An automatic segmentation algorithm was applied to identify the muscle activation; thus, 13 feature sets and 6 classifiers were tested. Moreover, 2 ensemble techniques aided in separating the sEMG signals into the 14 SIS gestures. Accuracy of 76% was obtained for the Support Vector Machine classifier for all databases and 88% for analyzing the volunteers individually. The system was demonstrated to be suitable for SIS gesture recognition using sEMG signals for wearable applications.

A 3D Printed, Bionic Hand Powered by EMG Signals and Controlled by an Online Neural Network

About 8% of the Ecuadorian population suffers some type of amputation of upper or lower limbs. Due to the high cost of a prosthesis and the fact that the salary of an average worker in the country reached 248 USD in August 2021, they experience a great labor disadvantage and only 17% of them are employed. Thanks to advances in 3D printing and the accessibility of bioelectric sensors, it is now possible to create economically accessible proposals. This work proposes the design of a hand prosthesis that uses electromyography (EMG) signals and neural networks for real-time control. The integrated system has a mechanical and electronic design, and the latter integrates artificial intelligence for control. To train the algorithm, an experimental methodology was developed to record muscle activity in upper extremities associated with specific tasks, using three EMG surface sensors. These data were used to train a five-layer neural network. the trained model was compressed and exported using TensorflowLite. The prosthesis consisted of a gripper and a pivot base, which were designed in Fusion 360 considering the movement restrictions and the maximum loads. It was actuated in real time thanks to the design of an electronic circuit that used an ESP32 development board, which was responsible for recording, processing and classifying the EMG signals associated with a motor intention, and to actuate the hand prosthesis. As a result of this work, a database with 60 electromyographic activity records from three tasks was released. The classification algorithm was able to detect the three muscle tasks with an accuracy of 78.67% and a response time of 80 ms. Finally, the 3D printed prosthesis was able to support a weight of 500 g with a safety factor equal to 15.

Wearable Electromyography Classification of Epileptic Seizures: A Feasibility Study

Accurate diagnosis and classification of epileptic seizures can greatly support patient treatments. As many epileptic seizures are convulsive and have a motor component, the analysis of muscle activity can provide valuable information for seizure classification. Therefore, this paper present a feasibility study conducted on healthy volunteers, focusing on tracking epileptic seizures movements using surface electromyography signals (sEMG) measured on human limb muscles. For the experimental studies, first, compact wireless sensor nodes were developed for real-time measurement of sEMG on the gastrocnemius, flexor carpi ulnaris, biceps brachii, and quadriceps muscles on the right side and the left side. For the classification of the seizure, a machine learning model has been elaborated. The 16 common sEMG time-domain features were first extracted and examined with respect to discrimination and redundancy. This allowed the features to be classified into irrelevant features, important features, and redundant features. Redundant features were examined with the Big-O notation method and with the average execution time method to select the feature that leads to lower complexity and reduced processing time. The finally selected six features were explored using different machine learning classifiers to compare the resulting classification accuracy. The results show that the artificial neural network (ANN) model with the six features: IEMG, WAMP, MYOP, SE, SKEW, and WL, had the highest classification accuracy (99.95%). A further study confirms that all the chosen eight sensors are necessary to reach this high classification accuracy.

High-Performance Surface Electromyography Armband Design for Gesture Recognition

Wearable surface electromyography (sEMG) signal-acquisition devices have considerable potential for medical applications. Signals obtained from sEMG armbands can be used to identify a person's intentions using machine learning. However, the performance and recognition capabilities of commercially available sEMG armbands are generally limited. This paper presents the design of a wireless high-performance sEMG armband (hereinafter referred to as the α Armband), which has 16 channels and a 16-bit analog-to-digital converter and can reach 2000 samples per second per channel (adjustable) with a bandwidth of 0.1-20 kHz (adjustable). The α Armband can configure parameters and interact with sEMG data through low-power Bluetooth. We collected sEMG data from the forearms of 30 subjects using the α Armband and extracted three different image samples from the time-frequency domain for training and testing convolutional neural networks. The average recognition accuracy for 10 hand gestures was as high as 98.6%, indicating that the α Armband is highly practical and robust, with excellent development potential.

Physiological and Biomechanical Monitoring in American Football Players: A Scoping Review

American football is the sport with the highest rates of concussion injuries. Biomedical engineering applications may support athletes in monitoring their injuries, evaluating the effectiveness of their equipment, and leading industrial research in this sport. This literature review aims to report on the applications of biomedical engineering research in American football, highlighting the main trends and gaps. The review followed the PRISMA guidelines and gathered a total of 1629 records from PubMed (n = 368), Web of Science (n = 665), and Scopus (n = 596). The records were analyzed, tabulated, and clustered in topics. In total, 112 studies were selected and divided by topic in the biomechanics of concussion (n = 55), biomechanics of footwear (n = 6), biomechanics of sport-related movements (n = 6), the aerodynamics of football and catch (n = 3), injury prediction (n = 8), heat monitoring of physiological parameters (n = 8), and monitoring of the training load (n = 25). The safety of players has fueled most of the research that has led to innovations in helmet and footwear design, as well as improvements in the understanding and prevention of injuries and heat monitoring. The other important motivator for research is the improvement of performance, which has led to the monitoring of training loads and catches, and studies on the aerodynamics of football. The main gaps found in the literature were regarding the monitoring of internal loads and the innovation of shoulder pads.

Detecting Safety Anomalies in pHRI Activities via Force Myography

The potential application of using a wearable force myography (FMG) band for monitoring the occupational safety of a human participant working in collaboration with an industrial robot was studied. Regular physical human–robot interactions were considered as activities of daily life in pHRI (pHRI-ADL) to recognize human-intended motions during such interactions. The force myography technique was used to read volumetric changes in muscle movements while a human participant interacted with a robot. Data-driven models were used to observe human activities for useful insights. Using three unsupervised learning algorithms, isolation forest, one-class SVM, and Mahalanobis distance, models were trained to determine pHRI-ADL/regular, preset activities by learning the latent features’ distributions. The trained models were evaluated separately to recognize any unwanted interactions that differed from the normal activities, i.e., anomalies that were novel, inliers, or outliers to the normal distributions. The models were able to detect unusual, novel movements during a certain scenario that was considered an unsafe interaction. Once a safety hazard was detected, the control system generated a warning signal within seconds of the event. Hence, this study showed the viability of using FMG biofeedback to indicate risky interactions to prevent injuries, improve occupational health, and monitor safety in workplaces that require human participation.

Large-Scale Ultra-Robust MoS2 Patterns Directly Synthesized on Polymer Substrate for Flexible Sensing Electronics

Synthesis of large-area patterned MoS₂ is considered the principle base for realizing high-performance MoS₂ -based flexible electronic devices. Patterning and transferring MoS₂ films to target flexible substrates, however, require conventional multi-step photolithography patterning and transferring process, despite tremendous progress in the facilitation of practical applications. Herein, an approach to directly synthesize large-scale MoS₂ patterns that combines inkjet printing and thermal annealing is reported. An optimal precursor ink is prepared that can deposit arbitrary patterns on polyimide films. By introducing a gas atmosphere of argon/hydrogen (Ar/H₂ ), thermal treatment at 350 °C enables an in situ decomposition and crystallization in the patterned precursors and, consequently, results in the formation of MoS₂ . Without complicated processes, patterned MoS₂ is obtained directly on polymer substrate, exhibiting superior mechanical flexibility and durability (≈2% variation in resistance over 10,000 bending cycles), as well as excellent chemical stability, which is attributed to the generated continuous and thin microstructures, as well as their strong adhesion with the substrate. As a step further, this approach is employed to manufacture various flexible sensing devices that are insensitive to body motions and moisture, including temperature sensors and biopotential sensing systems for real-time, continuously monitoring skin temperature, electrocardiography, and electromyography signals.

A Novel Screen-Printed Textile Interface for High-Density Electromyography Recording

Recording electrical muscle activity using a dense matrix of detection points (high-density electromyography, EMG) is of interest in a range of different applications, from human-machine interfacing to rehabilitation and clinical assessment. The wider application of high-density EMG is, however, limited as the clinical interfaces are not convenient for practical use (e.g., require conductive gel/cream). In the present study, we describe a novel dry electrode (TEX) in which the matrix of sensing pads is screen printed on textile and then coated with a soft polymer to ensure good skin-electrode contact. To benchmark the novel solution, an identical electrode was produced using state-of-the-art technology (polyethylene terephthalate with hydrogel, PET) and a process that ensured a high-quality sample. The two electrodes were then compared in terms of signal quality as well as functional application. The tests showed that the signals collected using PET and TEX were characterised by similar spectra, magnitude, spatial distribution and signal-to-noise ratio. The electrodes were used by seven healthy subjects and an amputee participant to recognise seven hand gestures, leading to similar performance during offline analysis and online control. The comprehensive assessment, therefore, demonstrated that the proposed textile interface is an attractive solution for practical applications.

SE-TCN network for continuous estimation of upper limb joint angles

The maturity of human-computer interaction technology has made it possible to use surface electromyographic signals (sEMG) to control exoskeleton robots and intelligent prostheses. However, the available upper limb rehabilitation robots controlled by sEMG have the shortcoming of inflexible joints. This paper proposes a method based on a temporal convolutional network (TCN) to predict upper limb joint angles by sEMG. The raw TCN depth was expanded to extract the temporal features and save the original information. The timing sequence characteristics of the muscle blocks that dominate the upper limb movement are not apparent, leading to low accuracy of the joint angle estimation. Therefore, this study squeeze-and-excitation networks (SE-Net) to improve the network model of the TCN. Finally, seven movements of the human upper limb were selected for ten human subjects, recording elbow angle (EA), shoulder vertical angle (SVA), and shoulder horizontal angle (SHA) values during their movements. The designed experiment compared the proposed SE-TCN model with the backpropagation (BP) and long short-term memory (LSTM) networks. The proposed SE-TCN systematically outperformed the BP network and LSTM model by the mean RMSE values: by 25.0 and 36.8% for EA, by 38.6 and 43.6% for SHA, and by 45.6 and 49.5% for SVA, respectively. Consequently, its R² values exceeded those of BP and LSTM by 13.6 and 39.20% for EA, 19.01 and 31.72% for SHA, and 29.22 and 31.89% for SVA, respectively. This indicates that the proposed SE-TCN model has good accuracy and can be used to estimate the angles of upper limb rehabilitation robots in the future.

Assessment of Vestigial Auriculomotor Activity to Acoustic Stimuli Using Electrodes In and Around the Ear

Recently, it has been demonstrated that electromyographic (EMG) activity of auricular muscles in humans, especially the postauricular muscle (PAM), depends on the spatial location of auditory stimuli. This observation has only been shown using wet electrodes placed directly on auricular muscles. To move towards a more applied, out-of-the-laboratory setting, this study aims to investigate if similar results can be obtained using electrodes placed in custom-fitted earpieces. Furthermore, with the exception of the ground electrode, only dry-contact electrodes were used to record EMG signals, which require little to no skin preparation and can therefore be applied extremely fast. In two experiments, auditory stimuli were presented to ten participants from different spatial directions. In experiment 1, stimuli were rapid onset naturalistic stimuli presented in silence, and in experiment 2, the corresponding participant's first name, presented in a "cocktail party" environment. In both experiments, ipsilateral responses were significantly larger than contralateral responses. Furthermore, machine learning models objectively decoded the direction of stimuli significantly above chance level on a single trial basis (PAM: ≈ 80%, in-ear: ≈ 69%). There were no significant differences when participants repeated the experiments after several weeks. This study provides evidence that auricular muscle responses can be recorded reliably using an almost entirely dry-contact in-ear electrode system. The location of the PAM, and the fact that in-ear electrodes can record comparable signals, would make hearing aids interesting devices to record these auricular EMG signals and potentially utilize them as control signals in the future.

Correlation Analysis of In-Vehicle Sensors Data and Driver Signals in Identifying Driving and Driver Behaviors

Today's cars have dozens of sensors to monitor vehicle performance through different systems, most of which communicate via vehicular networks (CAN). Many of these sensors can be used for applications other than the original ones, such as improving the driver experience or creating new safety tools. An example is monitoring variables that describe the driver's behavior. Interactions with the pedals, speed, and steering wheel, among other signals, carry driving characteristics. However, not always all variables related to these interactions are available in all vehicles; for example, the excursion of the brake pedal. Using an acquisition module, data from the in-vehicle sensors were obtained from the CAN bus, the brake pedal (externally instrumented), and the driver's signals (instrumented with an inertial sensor and electromyography of their leg), to observe the driver and car information and evaluate the correlation hypothesis between these data, as well as the importance of the brake pedal signal not usually available in all car models. Different sets of sensors were evaluated to analyze the performance of three classifiers when analyzing the driver's driving mode. It was found that there are superior results in classifying identity or behavior when driver signals are included. When the vehicle and driver attributes were used, hits above 0.93 were obtained in the identification of behavior and 0.96 in the identification of the driver; without driver signals, accuracy was more significant than 0.80 in identifying behavior. The results show a good correlation between vehicle data and data obtained from the driver, suggesting that further studies may be promising to improve the accuracy of rates based exclusively on vehicle characteristics, both for behavior identification and driver identification, thus allowing practical applications in embedded systems for local signaling and/or storing information about the driving mode, which is important for logistics companies.

Machine Learning-Based Classification of Subjective Cognitive Decline, Mild Cognitive Impairment, and Alzheimer's Dementia Using Neuroimage and Plasma Biomarkers

Alzheimer's disease (AD) progresses relentlessly from the preclinical to the dementia stage. The process begins decades before the diagnosis of dementia. Therefore, it is crucial to detect early manifestations to prevent cognitive decline. Recent advances in artificial intelligence help tackle the complex high-dimensional data encountered in clinical decision-making. In total, we recruited 206 subjects, including 69 cognitively unimpaired, 40 subjective cognitive decline (SCD), 34 mild cognitive impairment (MCI), and 63 AD dementia (ADD). We included 3 demographic, 1 clinical, 18 brain-image, and 3 plasma biomarker (Aß_1-42, Aß_1-40, and tau protein) features. We employed the linear discriminant analysis method for feature extraction to make data more distinguishable after dimension reduction. The sequential forward selection method was used for feature selection to identify the 12 best features for machine learning classifiers. We used both random forest and support vector machine as classifiers. The area under the receiver operative curve (AUROC) was close to 0.9 between diseased (combining ADD and MCI) and the controls. AUROC was higher than 0.85 between SCD and controls, 0.90 between MCI and SCD, and above 0.85 between ADD and MCI. We can differentiate between adjacent phases of the AD spectrum with blood biomarkers and brain MR images with the help of machine learning algorithms.

Multi-day dataset of forearm and wrist electromyogram for hand gesture recognition and biometrics

Surface electromyography (sEMG) signals have been used for advanced prosthetics control, hand-gesture recognition (HGR), and more recently as a novel biometric trait. For these sEMG-based applications, the translation from laboratory research setting to real-life scenarios suffers from two major limitations: (1) a small subject pool, and (2) single-session data recordings, both of which prevents acceptable generalization ability. In this longitudinal database, forearm and wrist sEMG data were collected from 43 participants over three different days with long separation (Days 1, 8, and 29) while they performed static hand/wrist gestures. The objective of this dataset is to provide a comprehensive dataset for the development of robust machine learning algorithms of sEMG, for both HGR and biometric applications. We demonstrated the high quality of the current dataset by comparing with the Ninapro dataset. And we presented its usability for both HGR and biometric applications. Among other applications, the dataset can also be used for developing electrode-shift invariant generalized models, which can further bolster the development of wristband and forearm-bracelet sensors.

Supervised Myoelectrical Hand Gesture Recognition in Post-Acute Stroke Patients with Upper Limb Paresis on Affected and Non-Affected Sides

In clinical practice, acute post-stroke paresis of the extremities fundamentally complicates timely rehabilitation of motor functions; however, recently, residual and distorted musculoskeletal signals have been used to initiate feedback-driven solutions for establishing motor rehabilitation. Here, we investigate the possibilities of basic hand gesture recognition in acute stroke patients with hand paresis using a novel, acute stroke, four-component multidomain feature set (ASF-4) with feature vector weight additions (ASF-14NP, ASF-24P) and supervised learning algorithms trained only by surface electromyography (sEMG). A total of 19 (65.9 ± 12.4 years old; 12 men, seven women) acute stroke survivors (12.4 ± 6.3 days since onset) with hand paresis (Brunnstrom stage 4 ± 1/4 ± 1, SIAS 3 ± 1/3 ± 2, FMA-UE 40 ± 20) performed 10 repetitive hand movements reflecting basic activities of daily living (ADLs): rest, fist, pinch, wrist flexion, wrist extension, finger spread, and thumb up. Signals were recorded using an eight-channel, portable sEMG device with electrode placement on the forearms and thenar areas of both limbs (four sensors on each extremity). Using data preprocessing, semi-automatic segmentation, and a set of extracted feature vectors, support vector machine (SVM), linear discriminant analysis (LDA), and k-nearest neighbors (k-NN) classifiers for statistical comparison and validity (paired t-tests, p-value < 0.05), we were able to discriminate myoelectrical patterns for each gesture on both paretic and non-paretic sides. Despite any post-stroke conditions, the evaluated total accuracy rate by the 10-fold cross-validation using SVM among four-, five-, six-, and seven-gesture models were 96.62%, 94.20%, 94.45%, and 95.57% for non-paretic and 90.37%, 88.48%, 88.60%, and 89.75% for paretic limbs, respectively. LDA had competitive results using PCA whereas k-NN was a less efficient classifier in gesture prediction. Thus, we demonstrate partial efficacy of the combination of sEMG and supervised learning for upper-limb rehabilitation procedures for early acute stroke motor recovery and various treatment applications.

A Novel Method for Hand Movement Recognition Based on Wavelet Packet Transform and Principal Component Analysis with Surface Electromyogram

As an input method of signal language, the hand movement classification technology has developed into one of the ways of natural human-computer interaction. The surface electromyogram (sEMG) signal contains abundant human movement information and has significant advantages as the input signal of human-computer interaction. However, how to effectively extract components from sEMG signals to improve the accuracy of hand motion classification is a difficult problem. Therefore, this work proposes a novel method based on wavelet packet transform (WPT) and principal component analysis (PCA) to classify six kinds of hand motions. The method applies WPT to decompose the sEMG signal into multiple sub-band signals. To efficiently extract the intrinsic components of the sEMG signal, the classification performance of different wavelet packet basis functions is evaluated. The PCA algorithm is used to reduce the dimension of the feature space composed of the features reflecting hand motions extracted from each sub-band signal. Besides, to ensure higher classification performance while reducing the dimension of the feature space by the PCA algorithm, the classification performance of different dimensions of the feature space is compared. In addition, the effects of the variability of the sEMG signal and the size of the window on the proposed method are further analyzed. The proposed method was tested on the sEMG for Basic Hand Movements Data Set and achieved an average accuracy of 96.03%. Compared with the existing research, the proposed method has better classification performance, which indicates that the research results can be applied to the fields of exoskeleton robot, rehabilitation training, and intelligent prosthesis.

Low-Cost Wearable Band Sensors of Surface Electromyography for Detecting Hand Movements

Surface electromyography (sEMG) is a non-invasive measure of electrical activity generated due to muscle contraction. In recent years, sEMG signals have been increasingly used in diverse applications such as rehabilitation, pattern recognition, and control of orthotic and prosthetic systems. This study presents the development of a versatile multi-channel sEMG low-cost wearable band system to acquire 4 signals. In this case, the signals acquired with the proposed device have been used to detect hand movements. However, the WyoFlex band could be used in some sections of the arm or the leg if the section's diameter matches the diameter of the WyoFlex band. The designed WyoFlex band was fabricated using three-dimensional (3D) printing techniques employing thermoplastic polyurethane and polylactic acid as manufacturing materials. Then, the proposed wearable electromyographic system (WES) consists of 2 WyoFlex bands, which simultaneously allow the wireless acquisition of 4 sEMG channels of each forearm. The collected sEMG can be visualized and stored for future post-processing stages using a graphical user interface designed in Node-RED. Several experimental tests were conducted to verify the performance of the WES. A dataset with sEMG collected from 15 healthy humans has been obtained as part of the presented results. In addition, a classification algorithm based on artificial neural networks has been implemented to validate the usability of the collected sEMG signals.

Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography

Many researchers have used machine learning models to control artificial hands, walking aids, assistance suits, etc., using the biological signal of electromyography (EMG). The use of such devices requires high classification accuracy. One method for improving the classification performance of machine learning models is normalization, such as z-score. However, normalization is not used in most EMG-based motion prediction studies because of the need for calibration and fluctuation of reference value for calibration (cannot re-use). Therefore, in this study, we proposed a normalization method that combines sliding-window and z-score normalization that can be implemented in real-time processing without need for calibration. The effectiveness of this normalization method was confirmed by conducting a single-joint movement experiment of the elbow and predicting its rest, flexion, and extension movements from the EMG signal. The proposed method achieved 77.7% accuracy, an improvement of 21.5% compared to the non-normalization (56.2%). Furthermore, when using a model trained by other people’s data for application without calibration, the proposed method achieved 63.1% accuracy, an improvement of 8.8% compared to the z-score (54.4%). These results showed the effectiveness of the simple and easy-to-implement method, and that the classification performance of the machine learning model could be improved.

A Real-Time EMG-Based Fixed-Bandwidth Frequency-Domain Embedded System for Robotic Hand

The signals from electromyography (EMG) have been used for volitional control of robotic assistive devices with the challenges of performance improvement. Currently, the most common method of EMG signal processing for robot control is RMS (root mean square)-based algorithm, but system performance accuracy can be affected by noise or artifacts. This study hypothesized that the frequency bandwidths of noise and artifacts are beyond the main EMG signal frequency bandwidth, hence the fixed-bandwidth frequency-domain signal processing methods can filter off the noise and artifacts only by processing the main frequency bandwidth of EMG signals for robot control. The purpose of this study was to develop a cost-effective embedded system and short-time Fourier transform (STFT) method for an EMG-controlled robotic hand. Healthy volunteers were recruited in this study to identify the optimal myoelectric signal frequency bandwidth of muscle contractions. The STFT embedded system was developed using the STM32 microcontroller unit (MCU). The performance of the STFT embedded system was compared with RMS embedded system. The results showed that the optimal myoelectric signal frequency band responding to muscle contractions was between 60 and 80 Hz. The STFT embedded system was more stable than the RMS embedded system in detecting muscle contraction. Onsite calibration was required for RMS embedded system. The average accuracy of the STFT embedded system is 91.55%. This study presents a novel approach for developing a cost-effective and less complex embedded myoelectric signal processing system for robot control.

A Systematic Study on Electromyography-Based Hand Gesture Recognition for Assistive Robots Using Deep Learning and Machine Learning Models

Upper limb amputation severely affects the quality of life and the activities of daily living of a person. In the last decade, many robotic hand prostheses have been developed which are controlled by using various sensing technologies such as artificial vision and tactile and surface electromyography (sEMG). If controlled properly, these prostheses can significantly improve the daily life of hand amputees by providing them with more autonomy in physical activities. However, despite the advancements in sensing technologies, as well as excellent mechanical capabilities of the prosthetic devices, their control is often limited and usually requires a long time for training and adaptation of the users. The myoelectric prostheses use signals from residual stump muscles to restore the function of the lost limbs seamlessly. However, the use of the sEMG signals in robotic as a user control signal is very complicated due to the presence of noise, and the need for heavy computational power. In this article, we developed motion intention classifiers for transradial (TR) amputees based on EMG data by implementing various machine learning and deep learning models. We benchmarked the performance of these classifiers based on overall generalization across various classes and we presented a systematic study on the impact of time domain features and pre-processing parameters on the performance of the classification models. Our results showed that Ensemble learning and deep learning algorithms outperformed other classical machine learning algorithms. Investigating the trend of varying sliding window on feature-based and non-feature-based classification model revealed interesting correlation with the level of amputation. The study also covered the analysis of performance of classifiers on amputation conditions since the history of amputation and conditions are different to each amputee. These results are vital for understanding the development of machine learning-based classifiers for assistive robotic applications.

Review on electromyography based intention for upper limb control using pattern recognition for human-machine interaction

Upper limb myoelectric prosthetic control is an essential topic in the field of rehabilitation. The technique controls prostheses using surface electromyogram (sEMG) and intramuscular EMG (iEMG) signals. EMG signals are extensively used in controlling prosthetic upper and lower limbs, virtual reality entertainment, and human-machine interface (HMI). EMG signals are vital parameters for machine learning and deep learning algorithms and help to give an insight into the human brain’s function and mechanisms. Pattern recognition techniques pertaining to support vector machine (SVM), k-nearest neighbor (KNN) and Bayesian classifiers have been utilized to classify EMG signals. This paper presents a review on current EMG signal techniques, including electrode array utilization, signal acquisition, signal preprocessing and post-processing, feature selection and extraction, data dimensionality reduction, classification, and ultimate application to the community. The paper also discusses using alternatives to EMG signals, such as force sensors, to measure muscle activity with reliable results. Future implications for EMG classification include employing deep learning techniques such as artificial neural networks (ANN) and recurrent neural networks (RNN) for achieving robust results.

LSTM Network Classification of Dexterous Individual Finger Movements

Electrical activity is generated in the forearm muscles during muscular contractions that control dexterous movements of a human finger and thumb. Using this electrical activity as an input to train a neural network for the purposes of classifying finger movements is not straightforward. Low cost wearable sensors i.e., a Myo Gesture control armband (www.bynorth.com), generally have a lower sampling rate when compared with medical grade EMG detection systems e.g., 200 Hz vs 2000 Hz. Using sensors such as the Myo coupled with the lower amplitude generated by individual finger movements makes it difficult to achieve high classification accuracy. Low sampling rate makes it challenging to distinguish between large quantities of subtle finger movements when using a single network. This research uses two networks which enables for the reduction in the number of movements in each network that are being classified; in turn improving the classification. This is achieved by developing and training LSTM networks that focus on the extension and flexion signals of the fingers and a separate network that is trained using thumb movement signal data. By following this method, this research have increased classification of the individual finger movements to between 90 and 100%.

Recurrent Convolutional Neural Networks as an Approach to Position-Aware Myoelectric Prosthesis Control

OBJECTIVE

Persons with normal arm function can perform complex wrist and hand movements over a wide range of limb positions. However, for those with transradial amputation who use myoelectric prostheses, control across multiple limb positions can be challenging, frustrating, and can increase the likelihood of device abandonment. In response, the goal of this research was to investigate recurrent convolutional neural network (RCNN)-based position-aware myoelectric prosthesis control strategies.

METHODS

Surface electromyographic (EMG) and inertial measurement unit (IMU) signals, obtained from 16 non-disabled participants wearing two Myo armbands, served as inputs to RCNN classification and regression models. Such models predicted movements (wrist flexion/extension and forearm pronation/supination), based on a multi-limb-position training routine. RCNN classifiers and RCNN regressors were compared to linear discriminant analysis (LDA) classifiers and support vector regression (SVR) regressors, respectively. Outcomes were examined to determine whether RCNN-based control strategies could yield accurate movement predictions, while using the fewest number of available Myo armband data streams.

RESULTS

An RCNN classifier (trained with forearm EMG data, and forearm and upper arm IMU data) predicted movements with 99.00% accuracy (versus the LDAs 97.67%). An RCNN regressor (trained with forearm EMG and IMU data) predicted movements with R2 values of 84.93% for wrist flexion/extension and 84.97% for forearm pronation/supination (versus the SVRs 77.26% and 60.73%, respectively). The control strategies that employed these models required fewer than all available data streams.

CONCLUSION

RCNN-based control strategies offer novel means of mitigating limb position challenges.

SIGNIFICANCE

This research furthers the development of improved position-aware myoelectric prosthesis control.

Electromyogram-Based Classification of Hand and Finger Gestures Using Artificial Neural Networks

Electromyogram (EMG) signals have been increasingly used for hand and finger gesture recognition. However, most studies have focused on the wrist and whole-hand gestures and not on individual finger (IF) gestures, which are considered more challenging. In this study, we develop EMG-based hand/finger gesture classifiers based on fixed electrode placement using machine learning methods. Ten healthy subjects performed ten hand/finger gestures, including seven IF gestures. EMG signals were measured from three channels, and six time-domain (TD) features were extracted from each channel. A total of 18 features was used to build personalized classifiers for ten gestures with an artificial neural network (ANN), a support vector machine (SVM), a random forest (RF), and a logistic regression (LR). The ANN, SVM, RF, and LR achieved mean accuracies of 0.940, 0.876, 0.831, and 0.539, respectively. One-way analyses of variance and F-tests showed that the ANN achieved the highest mean accuracy and the lowest inter-subject variance in the accuracy, respectively, suggesting that it was the least affected by individual variability in EMG signals. Using only TD features, we achieved a higher ratio of gestures to channels than other similar studies, suggesting that the proposed method can improve the system usability and reduce the computational burden.

Spatio-temporal warping for myoelectric control: an offline, feasibility study

Objective.The efficacy of an adopted feature extraction method directly affects the classification of the electromyographic (EMG) signals in myoelectric control applications. Most methods attempt to extract the dynamics of the multi-channel EMG signals in the time domain and on a channel-by-channel, or at best pairs of channels, basis. However, considering multi-channel information to build a similarity matrix has not been taken into account.Approach.Combining methods of long and short-term memory (LSTM) and dynamic temporal warping, we developed a new feature, called spatio-temporal warping (STW), for myoelectric signals. This method captures the spatio-temporal relationships of multi-channels EMG signals.Main results. Across four online databases, we show that in terms of average classification error and standard deviation values, the STW feature outperforms traditional features by 5%-17%. In comparison to the more recent deep learning models, e.g. convolutional neural networks (CNNs), STW outperformed by 5%-18%. Also, STW showed enhanced performance when compared to the CNN + LSTM model by 2%-14%. All differences were statistically significant with a large effect size.Significance.This feasibility study provides evidence supporting the hypothesis that the STW feature of the EMG signals can enhance the classification accuracy in an explainable way when compared to recent deep learning methods. Future work includes real-time implementation of the method and testing for prosthesis control.

sEMG-Based Hand Posture Recognition Considering Electrode Shift, Feature Vectors, and Posture Groups

Surface electromyography (sEMG)-based gesture recognition systems provide the intuitive and accurate recognition of various gestures in human-computer interaction. In this study, an sEMG-based hand posture recognition algorithm was developed, considering three main problems: electrode shift, feature vectors, and posture groups. The sEMG signal was measured using an armband sensor with the electrode shift. An artificial neural network classifier was trained using 21 feature vectors for seven different posture groups. The inter-session and inter-feature Pearson correlation coefficients (PCCs) were calculated. The results indicate that the classification performance improved with the number of training sessions of the electrode shift. The number of sessions necessary for efficient training was four, and the feature vectors with a high inter-session PCC (r > 0.7) exhibited high classification accuracy. Similarities between postures in a posture group decreased the classification accuracy. Our results indicate that the classification accuracy could be improved with the addition of more electrode shift training sessions and that the PCC is useful for selecting the feature vector. Furthermore, hand posture selection was as important as feature vector selection. These findings will help in optimizing the sEMG-based pattern recognition algorithm more easily and quickly.

Genetic Algorithm for Feature Selection in Lower Limb Pattern Recognition

Choosing the right features is important to optimize lower limb pattern recognition, such as in prosthetic control. EMG signals are noisy in nature, which makes it more challenging to extract useful information. Many features are used in the literature, which raises the question which features are most suited for use in lower limb myoelectric control. Therefore, it is important to find combinations of best performing features. One way to achieve this is by using a genetic algorithm, a meta-heuristic capable of searching vast feature spaces. The goal of this research is to demonstrate the capabilities of a genetic algorithm and come up with a feature set that has a better performance than the state-of-the-art feature set. In this study, we collected a dataset containing ten able-bodied subjects who performed various gait-related activities while measuring EMG and kinematics. The genetic algorithm selected features based on the performance on the training partition of this dataset. The selected feature sets were evaluated on the remaining test set and on the online benchmark dataset ENABL3S, against a state-of-the-art feature set. The results show that a feature set based on the selected features of a genetic algorithm outperforms the state-of-the-art set. The overall error decreased up to 0.54% and the transitional error by 2.44%, which represent a relative decrease in overall errors up to 11.6% and transitional errors up to 14.1%, although these results were not significant. This study showed that a genetic algorithm is capable of searching a large feature space and that systematic feature selection shows promising results for lower limb myoelectric control.

A Weak Monotonicity Based Muscle Fatigue Detection Algorithm for a Short-Duration Poor Posture Using sEMG Measurements

Muscle fatigue is usually defined as a decrease in the ability to produce force. The surface electromyography (sEMG) signals have been widely used to provide information about muscle activities including detecting muscle fatigue by various data-driven techniques such as machine learning and statistical approaches. However, it is well-known that sEMGs are usually weak signals with a smaller amplitude and a lower signal-to-noise ratio, making it difficult to apply the traditional signal processing techniques. In particular, the existing methods cannot work well to detect muscle fatigue coming from static poses. This work exploits the concept of weak monotonicity, which has been observed in the process of fatigue, to robustly detect muscle fatigue in the presence of measurement noises and human variations. Such a population trend methodology has shown its potential in muscle fatigue detection as demonstrated by the experiment of a static pose.

Rejecting Impulse Artifacts from Surface EMG Signals using Real-time Cumulative Histogram Filtering

This paper presents a cumulative histogram filtering (CHF) algorithm to filter impulsive artifacts within surface electromyograhy (sEMG) signal for time-domain signal feature extraction. The proposed CHF algorithm filters sEMG signals by extracting a continuous subset of amplitude-sorted values within a real-time window of measured samples using information about the probabilistic distribution of sEMG amplitude. For real-time deployment of the proposed CHF algorithm on an embedded computing platform, we also present an efficient, iterative implementation of the proposed algorithm. The proposed CHF algorithm was evaluated on synthetic impulse artifacts superimposed upon undisturbed sEMG recorded from a subject with transtibial amputation. Results suggest that the CHF algorithm effectively suppresses the simulated impulse artifacts while preserving a minimum signal-to-noise ratio of 95% and an average Pearson correlation of 0.99 compared to the undisturbed sEMG recordings.

Combined Dynamic Time Warping and Spatiotemporal Attention for Myoelectric Control

The success of pattern recognition based upper-limb prostheses control is linked to their ability to extract appropriate features from the electromyogram (EMG) signals. Traditional EMG feature extraction (FE) algorithms fail to extract spatial and inter-temporal information from the raw data, as they consider the EMG channels individually across a set of sliding windows with some degree of overlapping. To tackle these limitations, this paper presents a method that considers the spatial information of multi-channel EMG signals by utilising dynamic time warping (DTW). To satisfy temporal considerations, inspired by Long Short-Term Memory (LSTM) neural networks, our algorithm evolves the DTW feature representation across long and short-term components to capture the temporal dynamics of the EMG signal. As such the contribution of this paper is the development of a recursive spatio-temporal FE method, denoted as Recursive Temporal Warping (RTW). To investigate the performance of the proposed method, an offline EMG pattern recognition study with 53 movement classes performed by 10 subjects wearing 8 to 16 EMG channels was considered with the results compared against several conventional as well as deep learning-based models. We show that the use of the RTW can reduce classification errors significantly, paving the way for future real-time implementation.

Evaluation of User-Prosthesis-Interfaces for sEMG-Based Multifunctional Prosthetic Hands

The complexity of the user interfaces and the operating modes present in numerous assistive devices, such as intelligent prostheses, influence patients to shed them from their daily living activities. A methodology to evaluate how diverse aspects impact the workload evoked when using an upper-limb bionic prosthesis for unilateral transradial amputees is proposed and thus able to determine how user-friendly an interface is. The evaluation process consists of adapting the same 3D-printed terminal device to the different user-prosthesis-interface schemes to facilitate running the tests and avoid any possible bias. Moreover, a study comparing the results gathered by both limb-impaired and healthy subjects was carried out to contrast the subjective opinions of both types of volunteers and determines if their reactions have a significant discrepancy, as done in several other studies.

Quantitatively Recognizing Stimuli Intensity of Primary Taste Based on Surface Electromyography

A novel approach to quantitatively recognize the intensity of primary taste stimuli was explored based on surface electromyography (sEMG). We captured sEMG samples under stimuli of primary taste with different intensities and quantitatively recognized preprocessed samples with Support Vector Machine (SVM). The feasibility of quantitatively recognizing the intensity of Sour, Bitter, and Salty was verified. The sEMG signals were acquired under the stimuli of citric acid (aq), sucrose (aq), magnesium chloride (aq), sodium chloride (aq), and sodium glutamate (aq) with different concentrations, for five types of primary tastes: Sour, Sweet, Bitter, Salty, and Umami, whose order was fixed in this article. The acquired signals were processed with a method called Quadratic Variation Reduction to remove baseline wandering, and an adaptive notch to remove power frequency interference. After extracting 330 features for each sample, an SVM regressor with five-fold cross-validation was performed and the model reached R2 scores of 0.7277, 0.1963, 0.7450, 0.7642, and 0.5055 for five types of primary tastes, respectively, which manifested the feasibilities of the quantitative recognitions of Sour, Bitter, and Salty. To explore the facial responses to taste stimuli, we summarized and compared the muscle activities under stimuli of different taste types and taste intensities. To further simplify the model, we explored the impact of feature dimensionalities and optimized the feature combination for each taste in a channel-wise manner, and the feature dimensionality was reduced from 330 to 210, 120, 210, 260, 170 for five types of primary tastes, respectively. Lastly, we analyzed the model performance on multiple subjects and the relation between the model’s performance and the number of experiment subjects. This study can provide references for further research and applications on taste stimuli recognition with sEMG.

Pattern recognition of EMG signals for low level grip force classification

Grasping of the objects is the most frequent activity performed by the human upper limb. The amputations of the upper limb results in the need for prosthetic devices. The myoelectric prosthetic devices use muscle signals and apply control techniques for identification of different levels of hand gesture and force levels. In this study; a different level force contraction experiment was performed in which Electromyography (EMGs) signals and fingertip force signals were acquired. Using this experimental data; a two-step feature selection process is applied for the designing of a pattern recognition algorithm for the classification of different force levels. The two step feature selection process consist of generalized feature ranking using ReliefF, followed by personalized feature selection using Neighborhood Component Analysis (NCA) from the shortlisted features by earlier technique. The classification algorithms applied in this study were Support Vector Machines (SVM) and Random Forest (RF). Besides feature selection; optimization of the number of muscles during classification of force levels was also performed using designed algorithm. Based on this algorithm; the maximum classification accuracy using SVM classifier and two muscle set was achieved as high as 99%. The optimal feature set consisted features such as Auto Regressive coefficients, Willison Amplitude and Slope Sign Change. The mean classification accuracy for different subjects, achieved using SVM and RF was 94.5% and 91.7% respectively.

Dimensionality reduction for classification of object weight from electromyography

Electromyography (EMG) is a simple, non-invasive, and cost-effective technology for measuring muscle activity. However, multi-muscle EMG is also a noisy, complex, and high-dimensional signal. It has nevertheless been widely used in a host of human-machine-interface applications (electrical wheelchairs, virtual computer mice, prosthesis, robotic fingers, etc.) and, in particular, to measure the reach-and-grasp motions of the human hand. Here, we developed an automated pipeline to predict object weight in a reach-grasp-lift task from an open dataset, relying only on EMG data. In doing so, we shifted the focus from manual feature-engineering to automated feature-extraction by using pre-processed EMG signals and thus letting the algorithms select the features. We further compared intrinsic EMG features, derived from several dimensionality-reduction methods, and then ran several classification algorithms on these low-dimensional representations. We found that the Laplacian Eigenmap algorithm generally outperformed other dimensionality-reduction methods. What is more, optimal classification accuracy was achieved using a combination of Laplacian Eigenmaps (simple-minded) and k-Nearest Neighbors (88% F1 score for 3-way classification). Our results, using EMG alone, are comparable to other researchers', who used EMG and EEG together, in the literature. A running-window analysis further suggests that our method captures information in the EMG signal quickly and remains stable throughout the time that subjects grasp and move the object.

Reduce Surface Electromyography Channels for Gesture Recognition by Multitask Sparse Representation and Minimum Redundancy Maximum Relevance

Surface electromyography- (sEMG-) based gesture recognition is widely used in rehabilitation training, artificial prosthesis, and human-computer interaction. The purpose of this study is to simplify the sEMG devices by reducing channels while achieving comparably high gesture recognition accuracy. We propose a compound channel selection scheme by combining the variable selection algorithms based on multitask sparse representation (MTSR) and minimum Redundancy Maximum Relevance (mRMR). Specifically, channelwise features are first extracted to compose channel-feature paired variables, for which variable selection procedures by MTSR and mRMR are carried out, respectively. Then, we rank all the channels according to their occurrences in each variable selection procedure and figure out a certain number of informative channels by fusing these rankings of channels. Finally, the gesture classification performance using the selected channels is evaluated by the support vector machine (SVM) classifier. Experiment results validate the effectiveness of this proposed method.