Two-channel surface electromyography for individual and combined finger movements

Comparing Machine Learning Methods and Feature Extraction Techniques for the EMG Based Decoding of Human Intention

With an increasing number of robotic and prosthetic devices, there is a need for intuitive Muscle-Machine Interfaces (MuMIs) that allow the user to have an embodied interaction with the devices they are controlling. Such MuMIs can be developed using machine learning based methods that utilize myoelectric activations from the muscles of the user to decode their intention. However, the choice of the learning method is subjective and depends on the features extracted from the raw Electromyography signals as well as on the intended application. In this work, we compare the performance of five machine learning methods and eight time-domain feature extraction techniques in discriminating between different gestures executed by the user of an EMG based MuMI. From the results, it can be seen that the Willison Amplitude performs consistently better for all the machine learning methods compared in this study, while the Zero Crossings achieves the worst results for the Decision Trees and the Random Forests and the Variance offers the worst performance for all the other learning methods. The Random Forests method is shown to achieve the best results in terms of achieved accuracies (has the lowest variance between subjects). In order to experimentally validate the efficiency of the Random Forest classifier and the Willison Amplitude technique, a series of gestures were decoded in a real-time manner from the myoelectric activations of the operator and they were used to control a robot hand.

Recurrent Fusion of Time-Domain Descriptors Improves EMG-based Hand Movement Recognition

Controlling powered prostheses with myoelectric pattern recognition (PR) provides a natural human-robot interfacing scheme for amputees who lost their limbs. Research in this direction reveals that the challenges prohibiting reliable clinical translation of myoelectric interfaces are mainly driven by the quality of the extracted features. Hence, developing accurate and reliable feature extraction techniques is of vital importance for facilitating clinical implementation of Electromyogram (EMG) PR systems. To overcome this challenge, we proposed a combination of Range Spatial Filtering (RSF) and Recurrent Fusion of Time Domain Descriptors (RFTDD) in order to improve the classifier performance and make the prosthetic hand control more appropriate for clinical applications. RSF is used to increase the number of EMG signals available for feature extraction by focusing on the spatial information between all possible logical combinations of the physical EMG channels. RFTDD is then used to capture the temporal information by applying a recurrent data fusion process on the resulting orientation-based time-domain (TD) features, with a sigmoidal function to limit the features range and overcome the vanishing amplitudes problem. The main advantages of the proposed method include 1) its potential in capturing the temporal-spatial dependencies of the EMG signals, leading to reduced classification errors, and 2) the simplicity with which the features are extracted, as any kind of simple TD features can be adopted with this method. The performance of the proposed RFTDD is then benchmarked across many well-known TD features individually and as sets to prove the power of the RFTDD method on two EMG datasets with a total of 31 subjects. Testing results revealed an approximate reduction of 12% in classification errors across all subjects when using the proposed method against traditional feature extraction methods.Clinical Relevance-Establishing significance and importance of RFTDD, with simple time-domain features, for robust and low-cost clinical applications.

Classification of Electromyographic Hand Gesture Signals Using Modified Fuzzy C-Means Clustering and Two-Step Machine Learning Approach

Understanding and classifying electromyogram (EMG) signals is of significance for dexterous prosthetic hand control, sign languages, grasp recognition, human-machine interaction, etc.. The existing research of EMG-based hand gesture classification faces the challenges of unsatisfied classification accuracy, insufficient generalization ability, lack of training data and weak robustness. To address these problems, this paper combines unsupervised and supervised learning methods to classify an EMG dataset consisting of 10 classes of hand gestures. To lessen the difficulty of classification, clustering methods including subtractive clustering and fuzzy c-means (FCM) clustering algorithms are employed first to obtain the initial partition of the inputs. In particular, modified FCM algorithm is proposed to accustom the conventional FCM to the multi-class classification problem. Based on the grouping information obtained from clustering, a type of two-step supervised learning approach is proposed. Specifically, a top-classifier and three sub-classifiers integrated with windowing method and majority voting are employed to accomplish the two-step classification. The results demonstrate that the proposed method achieves 100% test accuracy and the strongest robustness compared to the conventional machine learning approaches, which shows the potential for industrial and healthcare applications, such as movement intention detection, grasp recognition and dexterous prostheses control.

Spatially Filtered Low-Density EMG and Time-Domain Descriptors Improves Hand Movement Recognition

Surface Electromyogram (EMG) pattern recognition has long been utilized for controlling multifunctional myoelectric prostheses. In such an application, a number of EMG channels are usually utilized to acquire more information about the underlying activity of the remaining muscles in the amputee stump. However, despite the multichannel nature of this application, the extracted features are usually acquired from each channel individually, without consideration for the interaction between the different muscles recruited to achieve a specific movement. In this paper, we proposed an approach of spatial filtering, denoted as Range Spatial Filtering (RSF), to increase the number of EMG channels available for feature extraction, by considering the range of all possible logical combinations of each n channels. The proposed RSF method is then combined with conventional time-domain (TD) feature extraction, as an extension of the conventional single channel TD features that are heavily considered in this field. We then show how the addition of a new feature, specifically the minimum absolute value of the range of each two windowed EMG signals, can significantly reduce the different patterns misclassification rate achieved by conventional TD features (with and without our RSF method). The performance of the proposed method is verified on EMG data collected from nine transradial amputees (seven traumatic and two congenital), with six grip and finger movements, for three different levels of forces (low, medium, and high). The classification results showed significant reduction in classification error rates compared to other methods (nearly 10% for some individual TD features and 5% for combined TD features, with Bonferroni corrected p-values <; 0.01).

Optimal feature set for finger movement classification based on sEMG

One of the most important electrophysiological signal is the Electromyography (EMG) signal, which is widely used in medical and engineering studies. This signal contains a wealth of information about muscle functions. Therefore, the EMG signal is becoming increasingly important and has started to be used in many applications like finger movement rehabilitation. However, an advanced EMG signal analysis method is required for efficient usage of such applications. This signal analysis can include signal detection, decomposition, processing, and classification. There are many approaches in studying the EMG signals, however, one of the important factor of analyzing is to get the most efficient and effective features that can be extracted from the raw signal. This paper presents the best feature extraction set compared to previous studies. Where eighteen well-known features algorithm has been tested using the sequential forward searching (SFS) method to get excellent classification accuracy in a minimum processing time. Among these novel features only four combinations have been selected with perfect results, which are; Hjorth Time Domain parameters (HTD), Mean Absolute Value (MAV), Root Mean Square (RMS) and Wavelet Packet Transform (WPT). The superiority of this feature set has been proven experimentally, and the results show that the classification accuracy could reach up to 99% to recognize the individual and combined for ten classes of finger movements using only two EMG channels.

Adaptive Windowing Framework for Surface Electromyogram-Based Pattern Recognition System for Transradial Amputees

Electromyogram (EMG)-based Pattern Recognition (PR) systems for upper-limb prosthesis control provide promising ways to enable an intuitive control of the prostheses with multiple degrees of freedom and fast reaction times. However, the lack of robustness of the PR systems may limit their usability. In this paper, a novel adaptive time windowing framework is proposed to enhance the performance of the PR systems by focusing on their windowing and classification steps. The proposed framework estimates the output probabilities of each class and outputs a movement only if a decision with a probability above a certain threshold is achieved. Otherwise (i.e., all probability values are below the threshold), the window size of the EMG signal increases. We demonstrate our framework utilizing EMG datasets collected from nine transradial amputees who performed nine movement classes with Time Domain Power Spectral Descriptors (TD-PSD), Wavelet and Time Domain (TD) feature extraction (FE) methods and a Linear Discriminant Analysis (LDA) classifier. Nonetheless, the concept can be applied to other types of features and classifiers. In addition, the proposed framework is validated with different movement and EMG channel combinations. The results indicate that the proposed framework works well with different FE methods and movement/channel combinations with classification error rates of approximately 13% with TD-PSD FE. Thus, we expect our proposed framework to be a straightforward, yet important, step towards the improvement of the control methods for upper-limb prostheses.

Evaluation of extreme learning machine for classification of individual and combined finger movements using electromyography on amputees and non-amputees

The success of myoelectric pattern recognition (M-PR) mostly relies on the features extracted and classifier employed. This paper proposes and evaluates a fast classifier, extreme learning machine (ELM), to classify individual and combined finger movements on amputees and non-amputees. ELM is a single hidden layer feed-forward network (SLFN) that avoids iterative learning by determining input weights randomly and output weights analytically. Therefore, it can accelerate the training time of SLFNs. In addition to the classifier evaluation, this paper evaluates various feature combinations to improve the performance of M-PR and investigate some feature projections to improve the class separability of the features. Different from other studies on the implementation of ELM in the myoelectric controller, this paper presents a complete and thorough investigation of various types of ELMs including the node-based and kernel-based ELM. Furthermore, this paper provides comparisons of ELMs and other well-known classifiers such as linear discriminant analysis (LDA), k-nearest neighbour (kNN), support vector machine (SVM) and least-square SVM (LS-SVM). The experimental results show the most accurate ELM classifier is radial basis function ELM (RBF-ELM). The comparison of RBF-ELM and other well-known classifiers shows that RBF-ELM is as accurate as SVM and LS-SVM but faster than the SVM family; it is superior to LDA and kNN. The experimental results also indicate that the accuracy gap of the M-PR on the amputees and non-amputees is not too much with the accuracy of 98.55% on amputees and 99.5% on the non-amputees using six electromyography (EMG) channels.

A robust myoelectric pattern recognition using online sequential extreme learning machine for finger movement classification

A robust myoelectric pattern-recognition-system requires a system that should work in the real application as good as in the laboratory. However, this demand should be handled properly and rigorously to achieve a robust myoelectric system. Electrode shift is an issue that usually emerges when dealing with robustness issue. In daily life, the placement of electrodes becomes a significant issue that can downgrade the performance of the system. This paper proposed a new way to overcome the robustness issue by conducting an update to the system to anticipate changes in the future such as electrode shift, improvement in muscle strength or any other issue. Such update will be used to generate an adaptation. The adaptation is done according to the user's need by employing an online sequential extreme learning (OS-ELM) to learn the training data chunk by chunk. OS-ELM enables the myoelectric system to learn from a small number of data to avoid cumbersome training process. The day-to-day experiment shows that the proposed system can maintain its performance on average accuracy around 85% whereas the non-adaptive system could not.

Swarm-wavelet based extreme learning machine for finger movement classification on transradial amputees

The use of a small number of surface electromyography (EMG) channels on the transradial amputee in a myoelectric controller is a big challenge. This paper proposes a pattern recognition system using an extreme learning machine (ELM) optimized by particle swarm optimization (PSO). PSO is mutated by wavelet function to avoid trapped in a local minima. The proposed system is used to classify eleven imagined finger motions on five amputees by using only two EMG channels. The optimal performance of wavelet-PSO was compared to a grid-search method and standard PSO. The experimental results show that the proposed system is the most accurate classifier among other tested classifiers. It could classify 11 finger motions with the average accuracy of about 94 % across five amputees.