Fuzzy EMG classification for prosthesis control

Embedded Machine Learning System for Muscle Patterns Detection in a Patient with Shoulder Disarticulation

The integration of artificial intelligence (AI) models in the classification of electromyographic (EMG) signals represents a significant advancement in the design of control systems for prostheses. This study explores the development of a portable system that classifies the electrical activity of three shoulder muscles in real time for actuator control, marking a milestone in the autonomy of prosthetic devices. Utilizing low-power microcontrollers, the system ensures continuous EMG signal recording, enhancing user mobility. Focusing on a case study-a 42-year-old man with left shoulder disarticulation-EMG activity was recorded over two days using a specifically designed electronic board. Data processing was performed using the Edge Impulse platform, renowned for its effectiveness in implementing AI on edge devices. The first day was dedicated to a training session with 150 repetitions spread across 30 trials and three different movements. Based on these data, the second day tested the AI model's ability to classify EMG signals in new movement executions in real time. The results demonstrate the potential of portable AI-based systems for prosthetic control, offering accurate and swift EMG signal classification that enhances prosthetic user functionality and experience. This study not only underscores the feasibility of real-time EMG signal classification but also paves the way for future research on practical applications and improvements in the quality of life for prosthetic users.

Classification of EMG signals with CNN features and voting ensemble classifier

Electromyography (EMG) signals are primarily used to control prosthetic hands. Classifying hand gestures efficiently with EMG signals presents numerous challenges. In addition to overcoming these challenges, a successful combination of feature extraction and classification approaches will improve classification accuracy. In the current work, convolutional neural network (CNN) features are used to reduce the redundancy problems associated with time and frequency domain features to improve classification accuracy. The features from the EMG signal are extracted using a CNN and are fed to the 'k' nearest neighbor (KNN) classifier with a different number of neighbors ( 1 N N , 3 N N , 5 N N , and   7 N N ) . It results in an ensemble of classifiers that are combined using a hard voting-based classifier. Based on the benchmark Ninapro DB4 database and CapgMyo database, the proposed framework obtained 91.3 % classification accuracy on CapgMyo and 89.5 % on Ninapro DB4.

Recent trends and challenges of surface electromyography in prosthetic applications

Surface electromyography (sEMG) meets extensive applications in the field of prosthesis in the current period. The effectiveness of sEMG in prosthesis applications has been verified by numerous revolutionary developments and extensive research attempts. A large volume of research and literature works have explored and validated the vast use of these signals in prostheses as an assistive technology. The objective of this paper is to conduct a systematic review and offer a detailed overview of the work record in the prosthesis and myoelectric interfaces framework. This review utilized a systematic search strategy to identify published articles discussing the state-of-the-art applications of sEMG in prostheses (including upper limb prosthesis and lower limb prostheses). Relevant studies were identified using electronic databases such as PubMed, IEEE Explore, SCOPUS, ScienceDirect, Google Scholar and Web of Science. Out of 3791 studies retrieved from the databases, 188 articles were found to be potentially relevant (after screening of abstracts and application of inclusion-exclusion criteria) and included in this review. This review presents an investigative analysis of sEMG-based prosthetic applications to assist the readers in making further advancements in this field. It also discusses the fundamental advantages and disadvantages of using sEMG in prosthetic applications. It also includes some important guidelines to follow in order to improve the performance of sEMG-based prosthesis. The findings of this study support the widespread use of sEMG in prosthetics. It is concluded that sEMG-based prosthesis technology, still in its sprouting phase, requires significant explorations for further development. Supplementary investigations are necessary in the direction of making a seamless mechanism of biomechatronics for sEMG-based prosthesis by cohesive efforts of robotic researchers and biomedical engineers.

Advances in EMG measurement techniques, analysis procedures, and the impact of muscle mechanics on future requirements for the methodology

Muscular coordination enables locomotion and interaction with the environment. For more than 50 years electromyography (EMG) has provided insights into the central nervous system control of individual muscles or muscle groups, enabling both fine and gross motor functions. This information is available either at individual motor units (Mus) level or on a more global level from the coordination of different muscles or muscle groups. In particular, non-invasive EMG methods such as surface EMG (sEMG) or, more recently, spatial mapping methods (High-Density EMG - HDsEMG) have found their place in research into biomechanics, sport and exercise, ergonomics, rehabilitation, diagnostics, and increasingly for the control of technical devices. With further technical advances and a growing understanding of the relationship between EMG and movement task execution, it is expected that with time, especially non-invasive EMG methods will become increasingly important in movement sciences. However, while the total number of publications per year on non-invasive EMG methods is growing exponentially, the number of publications on this topic in journals with a scope in movement sciences has stagnated in the last decade. This review paper contextualizes non-invasive EMG development over the last 50 years, highlighting methodological progress. Changes in research topics related to non-invasive EMG were identified. Today non-invasive EMG procedures are increasingly used to control technical devices, where muscle mechanics have a minor influence. In movement science, however, the effect of muscle mechanics on the EMG signal cannot be neglected. This explains why non-invasive EMG's relevance in movement sciences has not developed as expected.

Design and Implementation of a Prosthesis System Controlled by Electromyographic Signals Means, Characterized with Artificial Neural Networks

Around the world many people loss a body member for many reasons, where advances of technology may be useful to help these people to improve the quality of their lives. Then, designing a technologically advanced prosthesis with natural movements is worthy for scientific, commercial, and social reasons. Thus, research of manufacturing, designing, and signal processing may lead up to a low-cost affordable prosthesis. This manuscript presents a low-cost design proposal for an electromyographic electronic system, which is characterized by a neural network based process. Moreover, a hand-type prosthesis is presented and controlled by using the processed electromyographic signals for a required particular use. For this purpose, the user performs several movements by using the healthy-hand to get some electromyographic signals. After that, the obtained signals are processed in a neural network based controller. Once an usable behavior is obtained, an exact replica of controlled motions are adapted for the other hand by using the designed prosthesis. The characterization process of bioelectrical signals was performed by training twenty characteristics obtained from the original raw signal in contrast with other papers in which seven characteristics have been tested on average. The proposed model reached a 95.2% computer test accuracy and 93% accuracy in a real environment experiment. The platform was tested via online and offline, where the best response was obtained in the online execution time.

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.

Wearable Sensor for Forearm Motion Detection Using a Carbon-Based Conductive Layer-Polymer Composite Film

In this study, we developed a fabrication method for a bracelet-type wearable sensor to detect four motions of the forearm by using a carbon-based conductive layer-polymer composite film. The integral material used for the composite film is a polyethylene terephthalate polymer film with a conductive layer composed of a carbon paste. It is capable of detecting the resistance variations corresponding to the flexion changes of the surface of the body due to muscle contraction and relaxation. To effectively detect the surface resistance variations of the film, a small sensor module composed of mechanical parts mounted on the film was designed and fabricated. A subject wore the bracelet sensor, consisting of three such sensor modules, on their forearm. The surface resistance of the film varied corresponding to the flexion change of the contact area between the forearm and the sensor modules. The surface resistance variations of the film were converted to voltage signals and used for motion detection. The results demonstrate that the thin bracelet-type wearable sensor, which is comfortable to wear and easily applicable, successfully detected each motion with high accuracy.

A generic neural network model to estimate populational neural activity for robust neural decoding

BACKGROUND

Robust and continuous neural decoding is crucial for reliable and intuitive neural-machine interactions. This study developed a novel generic neural network model that can continuously predict finger forces based on decoded populational motoneuron firing activities.

METHOD

We implemented convolutional neural networks (CNNs) to learn the mapping from high-density electromyogram (HD-EMG) signals of forearm muscles to populational motoneuron firing frequency. We first extracted the spatiotemporal features of EMG energy and frequency maps to improve learning efficiency, given that EMG signals are intrinsically stochastic. We then established a generic neural network model by training on the populational neuron firing activities of multiple participants. Using a regression model, we continuously predicted individual finger forces in real-time. We compared the force prediction performance with two state-of-the-art approaches: a neuron-decomposition method and a classic EMG-amplitude method.

RESULTS

Our results showed that the generic CNN model outperformed the subject-specific neuron-decomposition method and the EMG-amplitude method, as demonstrated by a higher correlation coefficient between the measured and predicted forces, and a lower force prediction error. In addition, the CNN model revealed more stable force prediction performance over time.

CONCLUSIONS

Overall, our approach provides a generic and efficient continuous neural decoding approach for real-time and robust human-robot interactions.

Modeling-Based EMG Signal (MBES) Classifier for Robotic Remote-Control Purposes

The fast-growing human–robot collaboration predicts that a human operator could command a robot without mechanical interface if effective communication channels are established. In noisy, vibrating and light sensitive environments, some sensors for detecting the human intention could find critical issues to be adopted. On the contrary, biological signals, as electromyographic (EMG) signals, seem to be more effective. In order to command a laboratory collaborative robot powered by McKibben pneumatic muscles, promising actuators for human–robot collaboration due to their inherent compliance and safety features have been researched, a novel modeling-based electromyographic signal (MBES) classifier has been developed. It is based on one EMG sensor, a Myotrac one, an Arduino Uno and a proper code, developed in the Matlab environment, that performs the EMG signal recognition. The classifier can recognize the EMG signals generated by three hand-finger movements, regardless of the amplitude and time duration of the signal and the muscular effort, relying on three mathematical models: exponential, fractional and Gaussian. These mathematical models have been selected so that they are the best fitting with the EMG signal curves. Each of them can be assigned a consent signal for performing the wanted pick-and-place task by the robot. An experimental activity was carried out to test and achieve the best performance of the classifier. The validated classifier was applied for controlling three pressure levels of a McKibben-type pneumatic muscle. Encouraging results suggest that the developed classifier can be a valid command interface for robotic purposes.

Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method

A high-accuracy gait data prediction model can be used to design prosthesis and orthosis for people having amputations or ailments of the lower limb. The objective of this study is to observe the gait data of different subjects and design a neural network to predict future gait angles for fixed speeds. The data were recorded via a Biometrics goniometer, while the subjects were walking on a treadmill for 20 seconds each at 2.4 kmph, 3.6 kmph, and 5.4 kmph. The data were then imported into Matlab, filtered to remove movement artifacts, and then used to design a neural network with 60% data for training, 20% for validation, and remaining 20% for testing using the LevenbergMarquardt method. The mean-squared error for all the cases was in the order of 10-3 or lower confirming that our method is correct. For further comparison, we randomly tested the neural network function with untrained data and compared the expected output with actual output of the neural network function using Pearson's correlation coefficient and correlation plots. We conclude that our framework can be successfully used to design prosthesis and orthosis for lower limb. It can also be used to validate gait data and compare it to expected data in rehabilitation engineering.

A Position Weight Matrix Feature Extraction Algorithm Improves Hand Gesture Recognition

Recent advances in the biomedical field have generated a massive amount of data and records (signals) that are collected for diagnosis purposes. The correct interpretation and understanding of these signals present a big challenge for digital health vision. In this work, Quantization-based position Weight Matrix (QuPWM) feature extraction method for multiclass classification is proposed to improve the interpretation of biomedical signals. This method is validated on surface Electromyogram (sEMG) signals recognition for eight different hand gestures. The used CapgMyo dataset consists of high-density sEMG signals across 128 channels acquired from 9 intact subjects. Our pilot results show that an accuracy of up to 83% can be achieved for some subjects using a support vector machine classifier, and an average accuracy of 75% has been reached for all studied subjects using the CapgMyo dataset. The proposed method shows a good potential in extracting relevant features from different biomedical signals such as Electroencephalogram (EEG) and Magnetoencephalogram (MEG) signals.

Enhanced Performance for Multi-Forearm Movement Decoding Using Hybrid IMU-sEMG Interface

Control of active prosthetic hands using surface electromyography (sEMG) signals is an active research area; despite the advances in sEMG pattern recognition and classification techniques, none of the commercially available prosthetic hands provide the user with an intuitive control. One of the major reasons for this disparity between academia and industry is the variation of sEMG signals in a dynamic environment as opposed to the controlled laboratory conditions. This research investigated the effects of sEMG signal variation on the performance of a hand motion classifier due to arm position variation and also explored the effect of static position and dynamic movement strategies for classifier training. A wearable system is used to measure the electrical activity of the muscles and the position of the forearm while performing six classes of hand motions. The system is made position aware (POS) using inertial measurement units (IMUs) for different arm movement gestures. The hand gestures are decoded under both static and dynamic forearm movements. Four time domain (TD) features are extracted from the sEMG signals along with IMU-based arm position information. The features are trained and tested using linear discriminant analysis (LDA) and support vector machine (SVM) for both TD and TD-POS features. The results for the SVM show a significant difference between the static and dynamic approaches, while the TD-POS features show enhanced classification performance in comparison to the TD-based classification. Results have shown the effectiveness of the dynamic training approach and sensor fusion techniques to improve the performance of existing stand-alone sEMG-based prosthetic control systems.

Classification and regression of spatio-temporal signals using NeuCube and its realization on SpiNNaker neuromorphic hardware

OBJECTIVE

The objective of this work is to use the capability of spiking neural networks to capture the spatio-temporal information encoded in time-series signals and decode them without the use of hand-crafted features and vector-based learning and the realization of the spiking model on low-power neuromorphic hardware.

APPROACH

The NeuCube spiking model was used to classify different grasp movements directly from raw surface electromyography signals (sEMG), the estimations of the applied finger forces as well as the classification of two motor imagery movements from raw electroencephalography (EEG). In a parallel investigation, the designed spiking decoder was implemented on SpiNNaker neuromorphic hardware, which allows low-energy real-time processing.

MAIN RESULTS

Experimental results reveal a better classification accuracy using the NeuCube model compared to traditional machine learning methods. For sEMG classification, we reached a training accuracy of 85% and a test accuracy of 84.8%, as well as less than 19% of relative root mean square error (rRMSE) when estimating finger forces from six subjects. For the EEG classification, a mean accuracy of 75% was obtained when tested on raw EEG data from nine subjects from the existing 2b dataset from 'BCI competition IV'.

SIGNIFICANCE

This work provides a proof of concept for a successful implementation of the NeuCube spiking model on the SpiNNaker neuromorphic platform for raw sEMG and EEG decoding, which could chart a route ahead for a new generation of portable closed-loop and low-power neuroprostheses.

Multiday Evaluation of Techniques for EMG-Based Classification of Hand Motions

Currently, most of the adopted myoelectric schemes for upper limb prostheses do not provide users with intuitive control. Higher accuracies have been reported using different classification algorithms but investigation on the reliability over time for these methods is very limited. In this study, we compared for the first time the longitudinal performance of selected state-of-the-art techniques for electromyography (EMG) based classification of hand motions. Experiments were conducted on ten able-bodied and six transradial amputees for seven continuous days. Linear discriminant analysis (LDA), artificial neural network (ANN), support vector machine (SVM), K-nearest neighbor (KNN), and decision trees (TREE) were compared. Comparative analysis showed that the ANN attained highest classification accuracy followed by LDA. Three-way repeated ANOVA test showed a significant difference (P < 0.001) between EMG types (surface, intramuscular, and combined), days (1-7), classifiers, and their interactions. Performance on the last day was significantly better (P < 0.05) than the first day for all classifiers and EMG types. Within-day, classification error (WCE) across all subject and days in ANN was: surface (9.12 ± 7.38%), intramuscular (11.86 ± 7.84%), and combined (6.11 ± 7.46%). The between-day analysis in a leave-one-day-out fashion showed that the ANN was the optimal classifier (surface (21.88 ± 4.14%), intramuscular (29.33 ± 2.58%), and combined (14.37 ± 3.10%). Results indicate that within day performances of classifiers may be similar but over time, it may lead to a substantially different outcome. Furthermore, training ANN on multiple days might allow capturing time-dependent variability in the EMG signals and thus minimizing the necessity for daily system recalibration.

Adaptive Bayesian inference system for recognition of walking activities and prediction of gait events using wearable sensors

In this paper, a novel approach for recognition of walking activities and gait events with wearable sensors is presented. This approach, called adaptive Bayesian inference system (BasIS), uses a probabilistic formulation with a sequential analysis method, for recognition of walking activities performed by participants. Recognition of gait events, needed to identify the state of the human body during the walking activity, is also provided by the proposed method. In addition, the BasIS system includes an adaptive action-perception method for the prediction of gait events. The adaptive approach uses the knowledge gained from decisions made over time by the inference system. The action-perception method allows the BasIS system to autonomously adapt its performance, based on the evaluation of its own predictions and decisions made over time. The proposed approach is implemented in a layered architecture and validated with the recognition of three walking activities:level-ground, ramp ascent and ramp descent. The validation process employs real data from three inertial measurements units attached to the thigh, shanks and foot of participants while performing walking activities. The experiments show that mean decision times of 240 ms and 40 ms are needed to achieve mean accuracies of 99.87% and 99.82% for recognition of walking activities and gait events, respectively. The validation experiments also show that the performance, in accuracy and speed, is not significantly affected when noise is added to sensor measurements. These results show that the proposed adaptive recognition system is accurate, fast and robust to sensor noise, but also capable to adapt its own performance over time. Overall, the adaptive BasIS system demonstrates to be a robust and suitable computational approach for the intelligent recognition of activities of daily living using wearable sensors.

From Electromyogram to Password

With the increasing popularity of augmented reality (AR) services, providing seamless human-computer interactions in the AR setting has received notable attention in the industry. Gesture control devices have recently emerged to be the next great gadgets for AR due to their unique ability to enable computer interaction with day-to-day gestures. While these AR devices are bringing revolutions to our interaction with the cyber world, it is also important to consider potential privacy leakages from these always-on wearable devices. Specifically, the coarse access control on current AR systems could lead to possible abuse of sensor data.

Although the always-on gesture sensors are frequently quoted as a privacy concern, there has not been any study on information leakage of these devices. In this article, we present our study on side-channel information leakage of the most popular gesture control device, Myo. Using signals recorded from the electromyography (EMG) sensor and accelerometers on Myo, we can recover sensitive information such as passwords typed on a keyboard and PIN sequence entered through a touchscreen. EMG signal records subtle electric currents of muscle contractions. We design novel algorithms based on dynamic cumulative sum and wavelet transform to determine the exact time of finger movements. Furthermore, we adopt the Hudgins feature set in a support vector machine to classify recorded signal segments into individual fingers or numbers. We also apply coordinate transformation techniques to recover fine-grained spatial information with low-fidelity outputs from the sensor in keystroke recovery.

We evaluated the information leakage using data collected from a group of volunteers. Our results show that there is severe privacy leakage from these commodity wearable sensors. Our system recovers complex passwords constructed with lowercase letters, uppercase letters, numbers, and symbols with a mean success rate of 91%.

Design of a Soft Robotic Elbow Sleeve with Passive and Intent-Controlled Actuation

The provision of continuous passive, and intent-based assisted movements for neuromuscular training can be incorporated into a robotic elbow sleeve. The objective of this study is to propose the design and test the functionality of a soft robotic elbow sleeve in assisting flexion and extension of the elbow, both passively and using intent-based motion reinforcement. First, the elbow sleeve was developed, using elastomeric and fabric-based pneumatic actuators, which are soft and lightweight, in order to address issues of non-portability and poor alignment with joints that conventional robotic rehabilitation devices are faced with. Second, the control system was developed to allow for: (i) continuous passive actuation, in which the actuators will be activated in cycles, alternating between flexion and extension; and (ii) an intent-based actuation, in which user intent is detected by surface electromyography (sEMG) sensors attached to the biceps and triceps, and passed through a logic sequence to allow for flexion or extension of the elbow. Using this setup, the elbow sleeve was tested on six healthy subjects to assess the functionality of the device, in terms of the range of motion afforded by the device while in the continuous passive actuation. The results showed that the elbow sleeve is capable of achieving approximately 50% of the full range of motion of the elbow joint among all subjects. Next, further experiments were conducted to test the efficacy of the intent-based actuation on these healthy subjects. The results showed that all subjects were capable of achieving electromyography (EMG) control of the elbow sleeve. These preliminary results show that the elbow sleeve is capable of carrying out continuous passive and intent-based assisted movements. Further investigation of the clinical implementation of the elbow sleeve for the neuromuscular training of neurologically-impaired persons, such as stroke survivors, is needed.

Concurrent surface electromyography and force myography classification during times of prosthetic socket shift and user fatigue

Objective

Surface electromyography has been a long-standing source of signals for control of powered prosthetic devices. By contrast, force myography is a more recent alternative to surface electromyography that has the potential to enhance reliability and avoid operational challenges of surface electromyography during use. In this paper, we report on experiments conducted to assess improvements in classification of surface electromyography signals through the addition of collocated force myography consisting of piezo-resistive sensors.

Methods

Force sensors detect intrasocket pressure changes upon muscle activation due to changes in muscle volume during activities of daily living. A heterogeneous sensor configuration with four surface electromyography-force myography pairs was investigated as a control input for a powered upper limb prosthetic. Training of two different multilevel neural perceptron networks was employed during classification and trained on data gathered during experiments simulating socket shift and muscle fatigue.

Results

Results indicate that intrasocket pressure data used in conjunction with surface EMG data can improve classification of human intent and control of a powered prosthetic device compared to traditional, surface electromyography only systems.

Significance

Additional sensors lead to significantly better signal classification during times of user fatigue, poor socket fit, as well as radial and ulnar wrist deviation. Results from experimentally obtained training data sets are presented.

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN

BACKGROUND

The computer mouse is an important human-computer interaction device. But patients with physical finger disability are unable to operate this device. Surface EMG (sEMG) can be monitored by electrodes on the skin surface and is a reflection of the neuromuscular activities. Therefore, we can control limbs auxiliary equipment by utilizing sEMG classification in order to help the physically disabled patients to operate the mouse.

OBJECTIVE

To develop a new a method to extract sEMG generated by finger motion and apply novel features to classify sEMG.

METHODS

A window-based data acquisition method was presented to extract signal samples from sEMG electordes. Afterwards, a two-dimensional matrix image based feature extraction method, which differs from the classical methods based on time domain or frequency domain, was employed to transform signal samples to feature maps used for classification. In the experiments, sEMG data samples produced by the index and middle fingers at the click of a mouse button were separately acquired. Then, characteristics of the samples were analyzed to generate a feature map for each sample. Finally, the machine learning classification algorithms (SVM, KNN, RBF-NN) were employed to classify these feature maps on a GPU.

RESULTS

The study demonstrated that all classifiers can identify and classify sEMG samples effectively. In particular, the accuracy of the SVM classifier reached up to 100%.

CONCLUSIONS

The signal separation method is a convenient, efficient and quick method, which can effectively extract the sEMG samples produced by fingers. In addition, unlike the classical methods, the new method enables to extract features by enlarging sample signals' energy appropriately. The classical machine learning classifiers all performed well by using these features.

RECOGNITION OF FINGER/HAND GRIP MECHANISM BY COMPUTING S-TRANSFORM FEATURES OF SURFACE ELECTROMYOGRAM SIGNAL FROM HEALTHY AND AMPUTEE

Accurate identification of intended grip actions using the myoelectric signal recorded from the surface of the residual muscles can facilitate natural control of a prosthetic hand for an amputee. However, this is not trivial due to the complexity of the hand muscles. To overcome these shortcomings, there is the need for determining features of the myoelectric recordings that can be used for accurate identification of the grip actions. This study reports the use of S-transform (ST) of the surface myoelectric recordings for recognizing the intent of the user to generate a set of grip patterns. Surface Electromyogram (sEMG) recorded while performing five different hand/finger grip patterns was analyzed. ST of the signal was computed to analyze the signal in a windowed time–frequency domain. The energy and mean amplitude of the transformed signal were classified using a neural network. The method was tested for able-hand and trans-radial amputee subjects. The results show that ST showed improved sensitivity, specificity and accuracy for both healthy and amputee people.

Electromyographic Patterns during Golf Swing: Activation Sequence Profiling and Prediction of Shot Effectiveness

This study analyzes muscle activity, recorded in an eight-channel electromyographic (EMG) signal stream, during the golf swing using a 7-iron club and exploits information extracted from EMG dynamics to predict the success of the resulting shot. Muscles of the arm and shoulder on both the left and right sides, namely flexor carpi radialis, extensor digitorum communis, rhomboideus and trapezius, are considered for 15 golf players (∼5 shots each). The method using Gaussian filtering is outlined for EMG onset time estimation in each channel and activation sequence profiling. Shots of each player revealed a persistent pattern of muscle activation. Profiles were plotted and insights with respect to player effectiveness were provided. Inspection of EMG dynamics revealed a pair of highest peaks in each channel as the hallmark of golf swing, and a custom application of peak detection for automatic extraction of swing segment was introduced. Various EMG features, encompassing 22 feature sets, were constructed. Feature sets were used individually and also in decision-level fusion for the prediction of shot effectiveness. The prediction of the target attribute, such as club head speed or ball carry distance, was investigated using random forest as the learner in detection and regression tasks. Detection evaluates the personal effectiveness of a shot with respect to the player-specific average, whereas regression estimates the value of target attribute, using EMG features as predictors. Fusion after decision optimization provided the best results: the equal error rate in detection was 24.3% for the speed and 31.7% for the distance; the mean absolute percentage error in regression was 3.2% for the speed and 6.4% for the distance. Proposed EMG feature sets were found to be useful, especially when used in combination. Rankings of feature sets indicated statistics for muscle activity in both the left and right body sides, correlation-based analysis of EMG dynamics and features derived from the properties of two highest peaks as important predictors of personal shot effectiveness. Activation sequence profiles helped in analyzing muscle orchestration during golf shot, exposing a specific avalanche pattern, but data from more players are needed for stronger conclusions. Results demonstrate that information arising from an EMG signal stream is useful for predicting golf shot success, in terms of club head speed and ball carry distance, with acceptable accuracy. Surface EMG data, collected with a goal to automatically evaluate golf player's performance, enables wearable computing in the field of ambient intelligence and has potential to enhance exercising of a long carry distance drive.

Impact of Load Variation on Joint Angle Estimation From Surface EMG Signals

Many studies use surface electromyogram (sEMG) signals to estimate the joint angle, for control of upper-limb exoskeletons and prostheses. However, several practical factors still affect its clinical applicability. One of these factors is the load variation during daily use. This paper demonstrates that the load variation can have a substantial impact on performance of elbow angle estimation. This impact leads an increase in mean RMSE (Root-Mean-Square Error) from 7.86 ^° to 20.44 ^° in our experimental test. Therefore, we propose three methods to address this issue: 1) pooling the training data from all loads together to form the pooled training data for the training model; 2) adding the measured load value (force sensor) as an additional input; and 3) developing a two-step hybrid estimation approach based on load and sEMG. Experiments are conducted with five subjects to investigate the feasibility of the proposed three methods. The results show that the mean RMSE is reduced from 20.44 ^° to 13.54 ^° using method one, 10.47 ^° using method two, and 8.48 ^° using method three, respectively. Our study indicates that 1) the proposed methods can improve performance and stability on joint angle estimation and 2) sensor fusion (sEMG sensor and force sensor) is an efficient way to resolve the adverse effect of load variation.

A dynamical model improves reconstruction of handwriting from multichannel electromyographic recordings

In recent years, several assistive devices have been proposed to reconstruct arm and hand movements from electromyographic (EMG) activity. Although simple to implement and potentially useful to augment many functions, such myoelectric devices still need improvement before they become practical. Here we considered the problem of reconstruction of handwriting from multichannel EMG activity. Previously, linear regression methods (e.g., the Wiener filter) have been utilized for this purpose with some success. To improve reconstruction accuracy, we implemented the Kalman filter, which allows to fuse two information sources: the physical characteristics of handwriting and the activity of the leading hand muscles, registered by the EMG. Applying the Kalman filter, we were able to convert eight channels of EMG activity recorded from the forearm and the hand muscles into smooth reconstructions of handwritten traces. The filter operates in a causal manner and acts as a true predictor utilizing the EMGs from the past only, which makes the approach suitable for real-time operations. Our algorithm is appropriate for clinical neuroprosthetic applications and computer peripherals. Moreover, it is applicable to a broader class of tasks where predictive myoelectric control is needed.

Compensation of the effects of muscle fatigue on EMG-based control using fuzzy rules based scheme

Estimation of the correct motion intention of the user is very important for most of the Electromyography (EMG) based control applications such as prosthetics, power-assist exoskeletons, rehabilitation and teleoperation robots. On the other hand, safety and long term reliability are also vital for those applications, as they interact with human users. By considering these requirements, many EMG-based control applications have been proposed and developed. However, there are still many challenges to be addressed in the case of EMG based control systems. One of the challenges that had not been considered in such EMG-based control in common is the muscle fatigue. The muscle fatiguing effects of the user can deteriorate the effectiveness of the EMG-based control in the long run, which makes the EMG-based control to produce less accurate results. Therefore, in this study we attempted to develop a fuzzy rule based scheme to compensate the effects of muscle fatigues on EMG based control. Fuzzy rule based weights have been estimated based on time and frequency domain features of the EMG signals. Eventually, these weights have been used to modify the controller output according with the muscle fatigue condition in the muscles. The effectiveness of the proposed method has been evaluated by experiments.

Upper-limb movement classification based on sEMG signal validation with continuous channel selection

This paper aims to provide an efficient, automatic and auto-adaptive approach to establish a continuous electromyography (EMG) signal monitoring, to constantly identify an optimal electrode assortment to use as input of a pattern recognition method through time. The average classification accuracy for the adaptive input selection method was 83,96±5,79% against 72,06±7,15% in a non-adaptive system. Both systems make use of a neural network to classify 9 distinguish upper-limb movements.

An adaptation strategy of using LDA classifier for EMG pattern recognition

The time-varying character of myoelectric signal usually causes a low classification accuracy in traditional supervised pattern recognition method. In this work, an unsupervised adaptation strategy of linear discriminant analysis (ALDA) based on probability weighting and cycle substitution was suggested in order to improve the performance of electromyography (EMG)-based motion classification in multifunctional myoelectric prostheses control in changing environment. The adaptation procedure was firstly introduced, and then the proposed ALDA classifier was trained and tested with surface EMG recordings related to multiple motion patterns. The accuracies of the ALDA classifier and traditional LDA classifier were compared when the EMG recordings were added with different degrees of noise. The experimental results showed that compared to the LDA method, the suggested ALDA method had a better performance in improving the classification accuracy of sEMG pattern recognition, in both stable situation and noise added situation.

User adaptation in long-term, open-loop myoelectric training: implications for EMG pattern recognition in prosthesis control

OBJECTIVE

Recent studies have reported that the classification performance of electromyographic (EMG) signals degrades over time without proper classification retraining. This problem is relevant for the applications of EMG pattern recognition in the control of active prostheses.

APPROACH

In this study we investigated the changes in EMG classification performance over 11 consecutive days in eight able-bodied subjects and two amputees.

MAIN RESULTS

It was observed that, when the classifier was trained on data from one day and tested on data from the following day, the classification error decreased exponentially but plateaued after four days for able-bodied subjects and six to nine days for amputees. The between-day performance became gradually closer to the corresponding within-day performance.

SIGNIFICANCE

These results indicate that the relative changes in EMG signal features over time become progressively smaller when the number of days during which the subjects perform the pre-defined motions are increased. The performance of the motor tasks is thus more consistent over time, resulting in more repeatable EMG patterns, even if the subjects do not have any external feedback on their performance. The learning curves for both able-bodied subjects and subjects with limb deficiencies could be modeled as an exponential function. These results provide important insights into the user adaptation characteristics during practical long-term myoelectric control applications, with implications for the design of an adaptive pattern recognition system.

A Fuzzy Kernel Motion Classifier for Autonomous Stroke Rehabilitation

Autonomous poststroke rehabilitation systems which can be deployed outside hospital with no or reduced supervision have attracted increasing amount of research attentions due to the high expenditure associated with the current inpatient stroke rehabilitation systems. To realize an autonomous systems, a reliable patient monitoring technique which can automatically record and classify patient's motion during training sessions is essential. In order to minimize the cost and operational complexity, the combination of nonvisual-based inertia sensing devices and pattern recognition algorithms are often considered more suitable in such applications. However, the high motion irregularity due to stroke patients' body function impairment has significantly increased the classification difficulty. A novel fuzzy kernel motion classifier specifically designed for stroke patient's rehabilitation training motion classification is presented in this paper. The proposed classifier utilizes geometrically unconstrained fuzzy membership functions to address the motion class overlapping issue, and thus, it can achieve highly accurate motion classification even with poorly performed motion samples. In order to validate the performance of the classifier, experiments have been conducted using real motion data sampled from stroke patients with a wide range of impairment level and the results have demonstrated that the proposed classifier is superior in terms of error rate compared to other popular algorithms.

Using thin-film piezoelectret to detect tactile and slip signals for restoring sensation of prosthetic hands

Most of the currently available prosthetic hands do not have a proper sensation of touching and slipping. Thus it is not easy for arm amputees to grasp objects properly only with an assistance of visual feedback. In this pilot work, a sensor based on thin-film piezoelectret was used to detect the possible tactile and slip information of a prosthetic hand. The piezoelectret sensor is flexible and is able to be bended, and therefore it could be properly mounted on the surface of prosthetic finger. Our preliminary results demonstrated that both the tactile and slip information could be acquired with the same sensor unit. For a grasp without slippage, the tactile signal was usually a single large peak, whereas the slip signal was a series of vibrations in a small range. Thus these two types of signals could be easily separated based on their different characteristics. This study suggested that by using thin-film piezoelectret sensor, a primary control with involuntary feedback might be achieved for the present prosthetic hands. More studies would be required on the detailed signal processing and control strategy for the restoration of sensation function in prosthetic hands.

User training for pattern recognition-based myoelectric prostheses: improving phantom limb movement consistency and distinguishability

We assessed the ability of four transradial amputees to control a virtual prosthesis capable of nine classes of movement both before and after a two-week training period. Subjects attended eight one-on-one training sessions that focused on improving the consistency and distinguishability of their hand and wrist movements using visual biofeedback from a virtual prosthesis. The virtual environment facilitated the precise quantification of three prosthesis control measures. During a final evaluation, the subject population saw an average increase in movement completion percentage from 70.8% to 99.0%, an average improvement in normalized movement completion time from 1.47 to 1.13, and an average increase in movement classifier accuracy from 77.5% to 94.4% (p<0.001). Additionally, all four subjects were reevaluated after eight elapsed hours without retraining the classifier, and all subjects demonstrated minimal decreases in performance. Our analysis of the underlying sources of improvement for each subject examined the sizes and separation of high-dimensional data clusters and revealed that each subject formed a unique and effective strategy for improving the consistency and/or distinguishability of his or her phantom limb movements. This is the first longitudinal study designed to examine the effects of user training in the implementation of pattern recognition-based myoelectric prostheses.

A fuzzy controller for lower limb exoskeletons during sit-to-stand and stand-to-sit movement using wearable sensors

Human motion is a daily and rhythmic activity. The exoskeleton concept is a very positive scientific approach for human rehabilitation in case of lower limb impairment. Although the exoskeleton shows potential, it is not yet applied extensively in clinical rehabilitation. In this research, a fuzzy based control algorithm is proposed for lower limb exoskeletons during sit-to-stand and stand-to-sit movements. Surface electromyograms (EMGs) are acquired from the vastus lateralis muscle using a wearable EMG sensor. The resultant acceleration angle along the z-axis is determined from a kinematics sensor. Twenty volunteers were chosen to perform the experiments. The whole experiment was accomplished in two phases. In the first phase, acceleration angles and EMG data were acquired from the volunteers during both sit-to-stand and stand-to-sit motions. During sit-to-stand movements, the average acceleration angle at activation was 11°-48° and the EMG varied from -0.19 mV to +0.19 mV. On the other hand, during stand-to-sit movements, the average acceleration angle was found to be 57.5°-108° at the activation point and the EMG varied from -0.32 mV to +0.32 mV. In the second phase, a fuzzy controller was designed from the experimental data. The controller was tested and validated with both offline and real time data using LabVIEW.