Resilient EMG Classification to Enable Reliable Upper-Limb Movement Intent Detection

A hierarchical dynamic Bayesian learning network for EMG-based early prediction of voluntary movement intention

Decoding human action intention prior to motion onset with surface electromyograms (sEMG) is an emerging neuroengineering topic with interesting clinical applications such as intelligent control of powered prosthesis/exoskeleton devices. Despite extensive prior works in the related fields, it remains a technical challenge due to considerable variability of complex multi-muscle activation patterns in terms of volatile spatio-temporal characteristics. To address this issue, we first hypothesize that the inherent variability of the idle state immediately preceding the motion initiation needs to be addressed explicitly. We therefore design a hierarchical dynamic Bayesian learning network model that integrates an array of Gaussian mixture model - hidden Markov models (GMM-HMMs), where each GMM-HMM learns the multi-sEMG processes either during the idle state, or during the motion initiation phase of a particular motion task. To test the hypothesis and evaluate the new learning network, we design and build a upper-limb sEMG-joystick motion study system, and collect data from 11 healthy volunteers. The data collection protocol adapted from the psychomotor vigilance task includes repeated and randomized binary hand motion tasks (push or pull) starting from either of two designated idle states: relaxed (with minimal muscle tones), or prepared (with muscle tones). We run a series of cross-validation tests to examine the performance of the method in comparison with the conventional techniques. The results suggest that the idle state recognition favors the dynamic Bayesian model over a static classification model. The results also show a statistically significant improvement in motion prediction accuracy by the proposed method (93.83±6.41%) in comparison with the conventional GMM-HMM method (89.71±8.98%) that does not explicitly account for the idle state. Moreover, we examine the progress of prediction accuracy over the course of motion initiation and identify the important hidden states that warrant future research.

A noise-suppressing neural network approach for upper limb human-machine interactive control based on sEMG signals

The use of upper limb rehabilitation robots to assist the affected limbs for active rehabilitation training is an inevitable trend in the field of rehabilitation medicine. In particular, the active motion intention-based control of the upper limb rehabilitation robots to assist subjects in rehabilitation training is a hot research topic in human-computer interaction control. Therefore, improving the accuracy of active motion intention recognition is the premise of the human-machine interaction controller design. Furthermore, there are external disturbances (bounded/unbounded disturbances) during rehabilitation training, which seriously threaten the safety of subjects. Thereby, eliminating external disturbances (especially unbounded disturbances) is the difficulty and key to the human-machine interaction control of the upper limb rehabilitation robots. In response to these problems, based on the surface electromyogram signal of the human upper limb, this paper proposes a fuzzy neural network active motion intention recognition method to explore the internal connection between the surface electromyogram signal of the human upper limb and active motion intention, and improve the real-time and accuracy of recognition. Based on this, two types of human-machine interaction controllers, which can be called as zeroing neural network controller and noise-suppressing zeroing neural network controller are designed to establish a safe and comfortable training environment to avoid secondary damage to the affected limb. Numerical experiments verify the feasibility and effectiveness of the proposed theories and methods.

Gesture Recognition by Ensemble Extreme Learning Machine Based on Surface Electromyography Signals

In the recent years, gesture recognition based on the surface electromyography (sEMG) signals has been extensively studied. However, the accuracy and stability of gesture recognition through traditional machine learning algorithms are still insufficient to some actual application scenarios. To enhance this situation, this paper proposed a method combining feature selection and ensemble extreme learning machine (EELM) to improve the recognition performance based on sEMG signals. First, the input sEMG signals are preprocessed and 16 features are then extracted from each channel. Next, features that mostly contribute to the gesture recognition are selected from the extracted features using the recursive feature elimination (RFE) algorithm. Then, several independent ELM base classifiers are established using the selected features. Finally, the recognition results are determined by integrating the results obtained by ELM base classifiers using the majority voting method. The Ninapro DB5 dataset containing 52 different hand movements captured from 10 able-bodied subjects was used to evaluate the performance of the proposed method. The results showed that the proposed method could perform the best (overall average accuracy 77.9%) compared with decision tree (DT), ELM, and random forest (RF) methods.

Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition

As a machine-learning-driven decision-making problem, the surface electromyography (sEMG)-based hand movement recognition is one of the key issues in robust control of noninvasive neural interfaces such as myoelectric prosthesis and rehabilitation robot. Despite the recent success in sEMG-based hand movement recognition using end-to-end deep feature learning technologies based on deep learning models, the performance of today's sEMG-based hand movement recognition system is still limited by the noisy, random, and nonstationary nature of sEMG signals and researchers have come up with a number of methods that improve sEMG-based hand movement via feature engineering. Aiming at achieving higher sEMG-based hand movement recognition accuracies while enabling a trade-off between performance and computational complexity, this study proposed a progressive fusion network (PFNet) framework, which improves sEMG-based hand movement recognition via integration of domain knowledge-guided feature engineering and deep feature learning. In particular, it learns high-level feature representations from raw sEMG signals and engineered time-frequency domain features via a feature learning network and a domain knowledge network, respectively, and then employs a 3-stage progressive fusion strategy to progressively fuse the two networks together and obtain the final decisions. Extensive experiments were conducted on five sEMG datasets to evaluate our proposed PFNet, and the experimental results showed that the proposed PFNet could achieve the average hand movement recognition accuracies of 87.8%, 85.4%, 68.3%, 71.7%, and 90.3% on the five datasets, respectively, which outperformed those achieved by the state of the arts.