Continuous and simultaneous estimation of finger kinematics using inputs from an EMG-to-muscle activation model

Abstract

BackgroundSurface electromyography (EMG) signals are often used in many robot and rehabilitation applications because these reflect motor intentions of users very well. However, very few studies have focused on the accurate and proportional control of the human hand using EMG signals. Many have focused on discrete gesture classification and some have encountered inherent problems such as electro-mechanical delays (EMD). Here, we present a new method for estimating simultaneous and multiple finger kinematics from multi-channel surface EMG signals.MethodIn this study, surface EMG signals from the forearm and finger kinematic data were extracted from ten able-bodied subjects while they were tasked to do individual and simultaneous multiple finger flexion and extension movements in free space. Instead of using traditional time-domain features of EMG, an EMG-to-Muscle Activation model that parameterizes EMD was used and shown to give better estimation performance. A fast feed forward artificial neural network (ANN) and a nonparametric Gaussian Process (GP) regressor were both used and evaluated to estimate complex finger kinematics, with the latter rarely used in the other related literature.ResultsThe estimation accuracies, in terms of mean correlation coefficient, were 0.85±0.07, 0.78±0.06 and 0.73±0.04 for the metacarpophalangeal (MCP), proximal interphalangeal (PIP) and the distal interphalangeal (DIP) finger joint DOFs, respectively. The mean root-mean-square error in each individual DOF ranged from 5 to 15%. We show that estimation improved using the proposed muscle activation inputs compared to other features, and that using GP regression gave better estimation results when using fewer training samples.ConclusionThe proposed method provides a viable means of capturing the general trend of finger movements and shows a good way of estimating finger joint kinematics using a muscle activation model that parameterizes EMD. The results from this study demonstrates a potential control strategy based on EMG that can be applied for simultaneous and continuous control of multiple DOF(s) devices such as robotic hand/finger prostheses or exoskeletons.Electronic supplementary materialThe online version of this article (doi:10.1186/1743-0003-11-122) contains supplementary material, which is available to authorized users.

Evaluation of regression methods for the continuous decoding of finger movement from surface EMG and accelerometry

“…For within-movement generalization, the overall decoding performance was R 2 = 0.70 ± 0.04 for LR, and R 2 = 0.79 ± 0.04 for KRR, which is higher than R 2 = 0.55 reported by Smith et al [7]. Comparison to other studies is more challenging, due to differences in electrode placement [8,9].…”

“…Previous work has shown that the use of nonparametric methods, such as Gaussian Process regression, can improve decoding performance, especially in the case of limited availability of training data [9]. We argue, however, that any algorithmic comparison should be assessed on both within-, as well as across-movement generalization.…”

“…Hioki and Kawasaki [8] used a time-delayed, recurrent neural network, to estimate finger joint angles also in a non-amputee subject. Finally, Ngeo et al [9] used a muscle activation (MA) model to reconstruct finger kinematics from sEMG, and demonstrated that a non-parametric (Gaussian Process) regression method outperformed artificial neural network (ANN) regression.…”

Human-in-the-loop assistive cyber physical system control using physiological signals

“…A few studies have tackled the problem of estimating finger movement from sEMG [82]. In [83], a time-delayed neural network was used to estimate finger joint angles while [72] showed that a Gaussian process regression model outperformed the neural network one. Gaussian mixture model on top of the RNN, we show that we can build a probabilistic model that can successfully reconstruct hand kinematics.…”

“…Non-invasive surface electromyogram (sEMG) recordings on the forearm contain useful information for decoding muscle activity and hand kinematics [71,72]. sEMG has been used by researchers to develop intuitive robotic prosthesis interfaces either via pattern recognition using physiological features or via classical control schemes [73,74].…”