Electromyogram Pattern Recognition Research Articles

Subject-transfer framework with unlabeled data based on multiple distance measures for surface electromyogram pattern recognition

To improve the initial accuracy of wearable sensor-driven human interfaces, inter-subject variabilities must be reduced through transfer learning. If subject transfer can be performed without labeling the target user’s calibration data, an interface that provides stable accuracy can be easily achieved without a cumbersome calibration protocol. Herein, we propose a subject-transfer framework based on multiple distance measures that enables subject transfer using only unlabeled calibration data by minimizing the distance between the data distributions of the target and the source. To assess the performance of this framework, we used two surface electromyogram databases (one private database and one public database called the NinaPro database 5) acquired from the same wearable sensor, the Myo Gesture Control Armband. The proposed framework improved the pattern recognition accuracy compared with well-established classifiers constructed from randomly selected source subject data. In the future, we will apply this framework to online human interfaces that are not based on a specific calibration protocol. The scripts used in this study can be downloaded from https://github.com/aistairc/Unlabeled_STM.

Forearm Orientation and Muscle Force Invariant Feature Selection Method for Myoelectric Pattern Recognition

Electromyogram (EMG) signal-based prosthetic hand can restore an amputee’s missing functionalities, which requires a faithful electromyogram pattern recognition (EMG-PR) system. However, forearm orientation and muscle force variation make the EMG-PR system more complex, and the problem becomes more complicated when muscle force levels and forearm orientations arise simultaneously. The problems can be minimized using a more significant number of features or high-density surface EMG, but it increases design complexity and needs higher computational power. In this regard, we propose a feature selection method that selects both feature and channel simultaneously. The proposed feature selection method selects only 7 to 20 features among 162 features with comparable or better performance. In this study, these selected features achieve a significant improvement in the accuracy, sensitivity, specificity, precision, F1 score, and Matthew correlation coefficient (MCC) by 3.18% to 4.28%, 9.14% to 12.85%, 1.83% to 2.57%, 8.30% to 10.99%, 9.22% to 13.92%, and 0.11 to 0.15, respectively comparing with four existing feature selection methods. In this research, the proposed feature selection method achieves a forearm orientation and muscle force invariant F1 score of 91.46% for training the k- nearest neighbor (KNN) classifier with two orientations, wrist fully supinated (O1) and wrist fully pronated (O3), with a medium force level. We also achieve an F1 score of 93.27% for training the KNN classifier with all orientations with a medium force level. So, the proposed feature selection method would be very much helpful for finding the least dimensional features and achieving improved EMG-PR performance with multiple limiting factors.

Towards Zero Retraining for Multiday Motion Recognition via a Fully Unsupervised Adaptive Approach and Fabric Myoelectric Armband.

Surface electromyogram pattern recognition (EMG-PR) requires time-consuming training and retraining procedures for long-term use, hindering the usability of myoelectric control. In this paper, we design a fabric myoelectric armband to reduce the electrode shifts. Furthermore, we propose a fully unsupervised adaptive approach called hybrid serial classifier (HSC) to eliminate the burden of retraining over multiply days. We investigated the performance of our approach with a dataset of ten types of forearm motion from ten male subjects over eight weeks (total ten days, including: from day 1 to day 7, day 14, day 28, day 56). The average inter-day classification accuracies of HSC without any new retraining data are 86.61% when trained exclusively with the first day's EMG data, and 94.77% when trained with other nine days' data. We compare our proposed HSC algorithm with linear discriminant analysis (LDA) without recalibration (BLDA) and supervised adaption LDA (ALDA) with just one trial of new retraining data. The inter-day classification accuracy of HSC is significantly higher than that of BLDA and ALDA. These results indicate that our novel armband sEMG device is feasible for long-term use in conjunction with the proposed HSC algorithm.

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.

EMG pattern recognition via Bayesian inference with scale mixture-based stochastic generative models

Electromyogram (EMG) has been utilized to interface signals for prosthetic hands and information devices owing to its ability to reflect human motion intentions. Although various EMG classification methods have been introduced into EMG-based control systems, they do not fully consider the stochastic characteristics of EMG signals. This paper proposes an EMG pattern classification method incorporating a scale mixture-based generative model. A scale mixture model is a stochastic EMG model in which the EMG variance is considered as a random variable, enabling the representation of uncertainty in the variance. This model is extended in this study and utilized for EMG pattern classification. The proposed method is trained by variational Bayesian learning, thereby allowing the automatic determination of the model complexity. Furthermore, to optimize the hyperparameters of the proposed method with a partial discriminative approach, a mutual information-based determination method is introduced. Simulation and EMG analysis experiments demonstrated the relationship between the hyperparameters and classification accuracy of the proposed method as well as the validity of the proposed method. The comparison using public EMG datasets revealed that the proposed method outperformed the various conventional classifiers. These results indicated the validity of the proposed method and its applicability to EMG-based control systems. In EMG pattern recognition, a classifier based on a generative model that reflects the stochastic characteristics of EMG signals can outperform the conventional general-purpose classifier.

A new strategy based on feature filtering technique for improving the real-time control performance of myoelectric prostheses

Surface electromyogram pattern recognition (EMG-PR) has been considered as a promising approach for predicting amputees’ motion intentions to control myoelectric prostheses. However, EMG recordings are mostly contaminated by various interferences, which decay the motion prediction of EMG-PR methods, thus affecting the control performance of the prosthesis. One common way to solve this issue is to improve the quality of EMG signals via filtering methods. Unfortunately, complete attenuation of effects caused by contaminated EMG recordings remains a major challenge till date. In this study, besides the EMG signal filtering, an additional signal conditioning strategy, designated as feature filtering, was proposed and applied to the features that were extracted from EMG signals to improve the overall performance of EMG-PR. The proposed strategy’s performance was investigated in both offline analysis and real-time prosthesis control test for able bodied subjects and amputees. The experimental results showed that, by using the proposed feature filtering strategy, the offline motion classification accuracy was increased by 6.4% and 7.4% for able bodied subjects and amputees, respectively, and the real-time motion completion rate was increased by 12.5% and 14.6%. Furthermore, the performance of feature filtering strategy was compared with that of a commonly used post-processing strategy known as majority vote. It was observed that the proposed strategy achieved significantly better performance in both offline motion classification and real-time prosthetic control. Findings of this study suggest that the proposed strategy could potentially enhance the robustness and reliability of EMG-PR method in the control of prostheses and other human–machine interaction systems.

A long short-term recurrent spatial-temporal fusion for myoelectric pattern recognition

Current state-of-the-art myoelectric interfaces employ traditional pattern recognition (PR) algorithms to decode the Electromyogram (EMG) signals into hand movements for controlling artificial limbs. Recently, deep learning (DL) models have also been exploited for EMG feature learning/extraction. Models like Convolutional Neural Networks (CNN), which capture the spatial correlations, and Long Short-Term Memory (LSTM), which capture the non-linear temporal dynamics of EMG time-series data, have been shown to outperform traditional EMG PR systems. Nevertheless, the large number of model parameters, long training times, and large amounts of data required to train these DL models remain limiting factors that may hinder their translation into clinically viable prostheses. Consequently, rather than applying DL directly, this paper leverages concepts derived from these models to build upon our proposed concept of a Fusion of Time Domain Descriptors (FTDD). The FTDD are augmented with Range Spatial Filtering (RSF) to capture the spatial correlations and combined into an LSTM-style framework. This process, denoted as Recurrent Spatial-Temporal Fusion (RSTF), can be applied in combination with any traditional feature extraction method to exploit temporal and spatial correlations, with the potential for bi-directional applications. The advantages of the proposed RSTF method include (1) the memory concept, capturing long- and short-term spatial and temporal dependencies of the EMG signals, (2) significantly improved performance outperforming other state-of-the-art models and (3) the simplicity and the fairly low computational costs for feature extraction. Results are bench-marked against several feature extraction methods, proving the power of the RSTF using data from 82 subjects from five EMG databases with varying recording characteristics. The proposed method significantly outperforms all other methods tested for EMG pattern recognition, including a deep LSTM and other CNN methods previously reported in the literature and at a fracture of the computational cost. On the most challenging dataset, improvements of as much as 15% were found.

A Novel Signal Normalization Approach to Improve the Force Invariant Myoelectric Pattern Recognition of Transradial Amputees

Variation in the electromyogram pattern recognition (EMG-PR) performance with the muscle contraction force is a key limitation of the available prosthetic hand. To alleviate this problem, we propose a scheme to realize electromyogram signal normalization across channels before feature extraction. The proposed signal normalization scheme is validated over a dataset of nine transradial amputees that includes three force levels with six hand gestures. Moreover, we employ three classifiers, namely, linear discriminant analysis (LDA), support vector machine (SVM) and k-nearest neighbour (KNN), to evaluate the EMG-PR performance. In addition to the signal normalization scheme, we perform nonlinear transformation of the features by using the logarithm function. Both schemes facilitate merging of the muscle activation patterns of different force levels. The experimental results indicate that the force invariant EMG-PR performance (F1 score of at least 3.24% to 4.34%) of the proposed schemes is significantly enhanced compared to that obtained in recent studies. Therefore, we recommend using these features along with the proposed signal normalization scheme and nonlinear transformation of the features to improve the force invariant EMG-PR performance. The proposed feature extraction method achieves the highest F1 score of 91.28%, 91.39% and 90.56% when using the LDA, SVM and KNN classifiers, respectively.

Dimensionality Reduction in EMG-Based Estimation of Wrist Kinematics.

Pattern recognition has shown remarkable success in decoding motor information from electromyogram (EMG) signals. To decrease the computational complexity in EMG pattern recognition, it may be useful to reduce the dimensionality of the model input. This paper investigates the effect of reducing the dimensionality of EMG features in a regression-based motion intent estimation model. Ten able-bodied subjects participated in this analytic study. EMG signals from the right forearm and angle of the left wrist in three degrees of freedom (DoF) were measured, concurrently. The TD features were extracted from eight EMG channels, resulting in a total of 32 features. Three dimensionality reduction methods including principal component analysis (PCA), non-negative matrix factorization (NNMF), and canonical correlation analysis (CCA) were applied to the EMG features. Reducing the dimension of the EMG features below a certain threshold degraded the performance of the EMG pattern recognition model. Otherwise, dimensionality reduction did not change the performance. These thresholds for the PCA, NNMF, and CCA methods were 25, 26, and 13, respectively. Based on the results, CCA substantially outperformed PCA and NNMF, as it allowed a significant reduction of the EMG features size, from 32 to 13, with no adverse impact on the performance.

A Novel Postprocessing Method for Robust Myoelectric Pattern-Recognition Control Through Movement Pattern Transition Detection

Pattern-recognition-based myoelectric control systems are not yet widely available due to their limited robustness in real-life situations. Some postprocessing methods were introduced to improve the robustness in previous studies, but there is lack of investigation into movement transition phases. This article presents a novel postprocessing method based on movement pattern transition (MPT) detection. An image-based index is used to quantify the similarity of adjacent feature matrices from high-density surface electromyogram (EMG) signals. MPT detection is implemented by applying a double threshold to the calculated index. The proposed postprocessing method is used to rectify the EMG pattern recognition decisions from the classifier by incorporating the detected information. Two representative testing schemes are used to verify the robustness of the proposed method against force level variation and consecutive nonstop task performance. The proposed method achieved mean classification accuracy improvements of 7.33% and 10.91% with respect to the baseline performance of a raw classifier (without any postprocessing) in the two testing schemes. It also outperformed other common postprocessing methods ( p < 0.05). Considering both the accuracy improvement and time efficiency for rapid responses to MPT, the proposed method could be a potential option for postprocessing to enhance the robustness of myoelectric control.

EMG Pattern Recognition for Persons with Cervical Spinal Cord Injury.

Pattern recognition based myoelectric control has been widely explored in the field of prosthetics, but little work has extended to other patient groups. Individuals with neurological injuries such as spinal cord injury may also benefit from more intuitive control that may facilitate more interactive treatments or improved control of functional electrical stimulation (FES) systems or assistive technologies. This work presents a pilot study with 10 individuals with cervical spinal cord injury between A and C on the American Spinal Injury Association Impairment Scale. Subjects attempted to elicit 10 classes of forearm and hand movements while their electromyogram (EMG) was recorded using a cuff of eight electrodes. Various well-known EMG features were evaluated using a linear discriminant analysis classifier, yielding classification error rates as low as 4.3% ± 3.9 across the 10 classes. Reducing the number of classes to five, those required to control a commercial therapeutic FES device, further reduced the error rates to (2.2% ± 4.4). Results from this study provide evidence supporting continued exploration of EMG pattern recognition techniques for use by high-level spinal cord injured populations as a method of intuitive control over interactive FES systems or assistive devices.

Intelligent EMG Pattern Recognition Control Method for Upper-Limb Multifunctional Prostheses: Advances, Current Challenges, and Future Prospects

Upper-limb amputation imposes significant burden on amputees thereby restricting them from fully exploring their environments during activities of daily living. The use of intelligent learning algorithm for electromyogram-pattern recognition (EMG-PR)-based control in upper-limb prostheses is considered as an important clinical option. Though the existing EMG-PR prostheses could discriminate multiple degrees of freedom (DOF) limb movements, their transition to clinically viable option is still being challenged by some confounding factors. Toward realizing a clinically viable multiple DOF prostheses, this paper first explored the principles and dynamics of the existing intelligently driven EMG-PR-based prostheses control scheme. Then, investigations on core issues including variation in muscle contraction force, electrode shift, and subject mobility affecting the existing EMG-PR prosthetic control scheme were reported. For instance, variation in muscle contraction force and subject mobility led to degradation in the performance of the EMG-PR controlled prostheses with approximately 17.00% and 8.98% error values, respectively, which are still challenging issues among others. Thus, this paper reports core issues and best practices with respect to intelligent EMG-PR controlled prosthesis, the major challenges in implementing adaptively robust control scheme and provides future research directions that may result in the clinical realization of intuitively dexterous multiple DOF EMG-PR-based prostheses in the near future.

A Study on An EMG Sensor with High Gain and Low Noise for Measuring Human Muscular Movement Patterns for Smart Healthcare.

The form of the collection of bio-signals is becoming increasingly integrated and smart to meet the demands of the age of smart healthcare and the Fourth Industrial Revolution. In addition, the movement patterns of human muscles are also becoming more complex due to diversification of the human living environment. An analysis of the movement patterns of normal people’s muscles contracting with age and that of patients who are being treated in a hospital, including the disabled, will help improve life patterns, medical treatment patterns, and quality of life. In this study, the researchers developed a smart electromyogram (EMG) sensor which can improve human life patterns through EMG range and pattern recognition, which is beyond the conventional simple EMG measurement level. The developed sensor has a high gain of 10,000 times or more, noise of 500 uVrms or less, and common mode rejection ratio (CMRR) of 100 dB or more for EMG level and pattern recognition. The pattern recognition time of the sensor is 30 s. All the circuits developed in this study have a phase margin of 75 degrees or more for stability. Standard 0.25 μm complementary metal oxide semiconductor (CMOS) technology was used for the integrated circuit design. The system error rate was confirmed to be 1% or less through a clinical trial conducted on five males in their 40s and three females in their 30s for the past two years. The muscle activities of all subjects of the clinical trial were improved by about 21% by changing their life patterns based on EMG pattern recognition.

A Novel Time-Domain Descriptor for Improved Prediction of Upper Limb Movement Intent in EMG-PR System.

Electromyogram pattern recognition (EMG-PR) based control is a potential method capable of providing intuitively dexterous control functions in upper limb prostheses. Meanwhile, the feature extraction method adopted in EMG-PR based control is considered as an important factor that influences the performance of the prostheses. By exploiting the limitations of the existing feature extraction methods, this study proposed a new feature extraction method to effectively characterize EMG signal patterns associated with different limb movement intent. The performance of the proposed 2-dimensional novel time-domain feature set (NTDFS) was investigated using classification accuracy and feature space separability metrics across five subjects' EMG recordings, and compared with four different existing methods. In comparison to four other previously proposed feature extraction methods, the NTDFS achieved significantly better performance with increment in accuracy in the range of 5.20% ∼ 8.40% at p<0.05. Additionally, by applying principal component analysis (PCA) technique, the PCA feature space for NTDFS show obvious class separability in comparison to the other existing feature extraction methods. Thus, the proposed NTDFS may facilitate the development of accurate and robust clinically viable EMG-PR based prostheses.

Evaluation of EMG pattern recognition for upper limb prosthesis control: a case study in comparison with direct myoelectric control

BackgroundAlthough electromyogram (EMG) pattern recognition (PR) for multifunctional upper limb prosthesis control has been reported for decades, the clinical benefits have rarely been examined. The study purposes were to: 1) compare self-report and performance outcomes of a transradial amputee immediately after training and one week after training of direct myoelectric control and EMG pattern recognition (PR) for a two-degree-of-freedom (DOF) prosthesis, and 2) examine the change in outcomes one week after pattern recognition training and the rate of skill acquisition in two subjects with transradial amputations.MethodsIn this cross-over study, participants were randomized to receive either PR control or direct control (DC) training of a 2 DOF myoelectric prosthesis first. Participants were 2 persons with traumatic transradial (TR) amputations who were 1 DOF myoelectric users. Outcomes, including measures of dexterity with and without cognitive load, activity performance, self-reported function, and prosthetic satisfaction were administered immediately and 1 week after training. Speed of skill acquisition was assessed hourly. One subject completed training under both PR control and DC conditions. Both subjects completed PR training and testing. Outcomes of test metrics were analyzed descriptively.ResultsComparison of the two control strategies in one subject who completed training in both conditions showed better scores in 2 (18%) dexterity measures, 1 (50%) dexterity measure with cognitive load, and 1 (50%) self-report functional measure using DC, as compared to PR. Scores of all other metrics were comparable. Both subjects showed decline in dexterity after training. Findings related to rate of skill acquisition varied considerably by subject.ConclusionsOutcomes of PR and DC for operating a 2-DOF prosthesis in a single subject cross-over study were similar for 74% of metrics, and favored DC in 26% of metrics. The two subjects who completed PR training showed decline in dexterity one week after training ended. Findings related to rate of skill acquisition varied considerably by subject. This study, despite its small sample size, highlights a need for additional research quantifying the functional and clinical benefits of PR control for upper limb prostheses.

Robust EMG pattern recognition in the presence of confounding factors: features, classifiers and adaptive learning

Traditional electromyogram (EMG) pattern recognition does not take into account the effect of confounding factors, preventing its effective clinical application. In this paper, we investigated EMG pattern recognition of compound confounding factors including electrode shift, force variation, limb posture and temporary drift. We started with feature extraction, to identify suitable representations to resolve classification degradation caused by electrode doffing. Then, we proceeded to examine a variety of classifiers, to achieve a favorable classification accuracy (CA) when switching the control arms (dominant and nondominant) without additional calibration. Lastly, we investigated adaptive learning strategies, to mitigate the decline in CA over a relatively long duration (one day) of use. Two data-collection protocols (electrode doffing and donning, and one-day-long collection) were applied, and EMG datasets collected in these two protocols were arranged into three scenarios for progressive validation of the features, classifiers, and adaptive learning methods. Our results showed that the features extracted from the frequency domain improved the CA by 30% in comparison with their original time-domain representations (14 motions, 67.5 ± 9.8%, p < .001). When alternating the control arms, the performance achieved by the classifiers all declined and no method appeared to be more reliable than the others (14 motions, the best 45.5 ± 8.4%, probabilistic neural network; 7 motions, the best 70.4 ± 10.6%, linear discriminant analysis). At last, the new adaptive learning method utilizing representative samples could effectively mitigate classification degradation by updating the classifier's training samples in real-time.

Improving the Robustness of Electromyogram-Pattern Recognition for Prosthetic Control by a Postprocessing Strategy.

Electromyogram (EMG) contains rich information for motion decoding. As one of its major applications, EMG-pattern recognition (PR)-based control of prostheses has been proposed and investigated in the field of rehabilitation robotics for decades. These prostheses can offer a higher level of dexterity compared to the commercially available ones. However, limited progress has been made toward clinical application of EMG-PR-based prostheses, due to their unsatisfactory robustness against various interferences during daily use. These interferences may lead to misclassifications of motion intentions, which damage the control performance of EMG-PR-based prostheses. A number of studies have applied methods that undergo a postprocessing stage to determine the current motion outputs, based on previous outputs or other information, which have proved effective in reducing erroneous outputs. In this study, we proposed a postprocessing strategy that locks the outputs during the constant contraction to block out occasional misclassifications, upon detecting the motion onset using a threshold. The strategy was investigated using three different motion onset detectors, namely mean absolute value, Teager–Kaiser energy operator, or mechanomyogram (MMG). Our results indicate that the proposed strategy could suppress erroneous outputs, during rest and constant contractions in particular. In addition, with MMG as the motion onset detector, the strategy was found to produce the most significant improvement in the performance, reducing the total errors up to around 50% (from 22.9 to 11.5%) in comparison to the original classification output in the online test, and it is the most robust against threshold value changes. We speculate that motion onset detectors that are both smooth and responsive would further enhance the efficacy of the proposed postprocessing strategy, which would facilitate the clinical application of EMG-PR-based prosthetic control.

Resolving the adverse impact of mobility on myoelectric pattern recognition in upper-limb multifunctional prostheses

Electromyogram pattern recognition (EMG-PR) based control for upper-limb prostheses conventionally focuses on the classification of signals acquired in a controlled laboratory setting. In such a setting, relatively stable and high performances are often reported because subjects could consistently perform muscle contractions corresponding to a targeted limb motion. Meanwhile the clinical implementation of EMG-PR method is characterized by degradations in stability and classification performances due to the disparities between the constrained laboratory setting and clinical use. One of such disparities is the mobility of subject that would cause changes in the EMG signal patterns when eliciting identical limb motions in mobile scenarios. In this study, the effect of mobility on the performance of EMG-PR motion classifier was firstly investigated based on myoelectric and accelerometer signals acquired from six upper-limb amputees across four scenarios. Secondly, three methods were proposed to mitigate such effect on the EMG-PR motion classifier. From the obtained results, an average classification error (CE) of 9.50% (intra-scenario) was achieved when data from the same scenarios were used to train and test the EMG-PR classifier, while the CE increased to 18.48% (inter-scenario) when trained and tested with dataset from different scenarios. This implies that mobility would significantly lead to about 8.98% increase of classification error (p < 0.05). By applying the proposed methods, the degradation in classification performance was significantly reduced from 8.98% to 1.86% (Dual-stage sequential method), 3.17% (Hybrid strategy), and 4.64% (Multi-scenario strategy). Hence, the proposed methods may potentially improve the clinical robustness of the currently available multifunctional prostheses. Trial registrationThe study was approved by the ethics committee of Institutional Review Board of Shenzhen Institutes of Advanced Technology, and the reference number is SIAT-IRB-150515-H0077.

Combined influence of forearm orientation and muscular contraction on EMG pattern recognition

The performance of intelligent electromyogram (EMG)-driven prostheses, functioning as artificial alternatives to missing limbs, is influenced by several dynamic factors including: electrode position shift, varying muscle contraction level, forearm orientation, and limb position. The impact of these factors on EMG pattern recognition has been previously studied in isolation, with the combined effect of these factors being understudied. However, it is likely that a combination of these factors influences the accuracy. We investigated the combined effect of two dynamic factors, namely, forearm orientation and muscle contraction levels, on the generalizability of the EMG pattern recognition. A number of recent time- and frequency-domain EMG features were utilized to study the EMG classification accuracy. Twelve intact-limbed and one bilateral transradial (below-elbow) amputee subject were recruited. They performed six classes of wrist and hand movements at three muscular contraction levels with three forearm orientations (nine conditions). Results indicate that a classifier trained by features that quantify the angle, rather than amplitude, of the muscle activation patterns perform better than other feature sets across different contraction levels and forearm orientations. In addition, a classifier trained with the EMG signals collected at multiple forearm orientations with medium muscular contractions can generalize well and achieve classification accuracies of up to 91%. Furthermore, inclusion of an accelerometer to monitor wrist movement further improved the EMG classification accuracy. The results indicate that the proposed methodology has the potential to improve robustness of myoelectric pattern recognition.

A Low-Cost Real-Time Research Platform for EMG Pattern Recognition-Based Prosthetic Hand

The focus of this paper is the development of a low-cost research platform for a surface electromyogram (EMG)-based prosthetic hand control to evaluate various pattern recognition techniques and to study the real-time implementation. This comprehensible research platform may enlighten the biomedical research in developing countries for analyzing and evaluating the surface EMG signals. Major challenges in this work were as follows: the design and development of an EMG signal conditioning module, a pattern recognition module, and a prosthetic hand at low cost. Besides, EMG pattern recognition techniques were evaluated for identifying six hand motions in offline with signals acquired from ten healthy subjects and two transradial amputees. Features calculated from EMG signals were grouped into six ensembles to apprehend the vitality of the ensemble in classifiers namely simple logistic regression (SLR), J48 algorithm for decision tree, logistic model tree, neural network, linear discriminant analysis, and support vector machine. The classification performance was also evaluated with the prolonged EMG data recorded on a day at every 1 h interval to study the robustness of the classifier. The results show the average classification accuracy, processing time and memory requirement of the SLR was found to be better and robust with time-domain features consisting of statistical as well as autoregression coefficients. The statistical analysis of variance test also showed that computation time and memory space required for SLR were significantly less compared to the other classifiers. The performance of the classifier was tested in online with transradial amputee for actuation of prosthetic hand for two intended motions with a TMS320F28335 controller. This proposed research platform for evaluation of EMG pattern recognition and real-time implementation has been achieved at a cost of 25 000 Indian rupee (INR).