GMM-Based Single-Joint Angle Estimation Using EMG Signals

Michieletto, Stefano; Tonin, Luca; Antonello, Mauro; Bortoletto, Roberto; Spolaor, Fabiola; Pagello, Enrico; Menegatti, Emanuele

doi:10.1007/978-3-319-08338-4_85

Cited by 18 publications

(16 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the rst case it was chosen the channel carrying out more information according to results showed in [36]. Wavelet transform is considered a exible technique because there is a wide variety of wavelet functions which could be used ( [14].…”

Section: Resultsmentioning

confidence: 99%

Processing of sEMG signals for online motion of a single robot joint through GMM modelization

Valentini

Michieletto

Spolaor

et al. 2015

2015 IEEE International Conference on Rehabilitation Robotics (ICORR)

Self Cite

View full text Add to dashboard Cite

At bottom, robotics is about us. It is the discipline of emulating our lives, of wondering how we work.Rod Grupen 3 4 SommarioLo scopo di questa tesi è di esplorare la possibilità di utilizzare i segnali elettromiograci (EMG) per allenare un modello di probabilità a componenti gaussiane (Gaussian Mixture Model) che riesca a stimare in tempo reale l'angolo di curvatura di un singolo giunto del corpo umano.Le informazioni del segnale sono state estratte utlizzando due approcci: il primo facente uso di trasformate nel dominio del tempo e nel dominio della frequenza, mentre il secondo utilizza la trasformata wavelet di cui è stata approfondita la migliore congurazione.Le funzioni wavelet di Daubechies Db2, Db4, Db6, Db7, Db44, Db45 sono state applicate ai segnali EMG corrispondenti a diversi muscoli della gamba a cui è seguita una aggregazione statistica dei dati da usare come input per la creazione del modello.Il modello GMM è stato validato su dati sconosciuti e le prestazioni sono state confrontate in base alla funzioni mother wavelet scelte per il calcolo della trasformata ed al numero di ripetizioni usate durante la fase di allenamento.La procedura migliore è stata utilizzata come base per sviluppare un software scritto in linguaggio C++ in grado di interfacciarsi con un robot umanoide a cui è stato fatto eseguire il movimento corrispondente a quello di una persona. Il software è stato sviluppato sotto forma di modulo ROS separando le varie fasi di elaborazione: generazione del segnale, acquisizione del segnale, analisi nel tempo e nella frequenza, sottomissione al modello e comunicazione del movimento al robot. Ogni fase è stata vericata indipendentemente dalle altre in modo da individuare la congurazione migliore per ciascuna. Il sistema è stato testato su un robot modello Aldebaran NAO.I risultati ottenuti mostrano come la procedura sia in grado di ottenere alte Achieved results showed that our procedure is able to obtain high perfor-

show abstract

Section: Resultsmentioning

confidence: 99%

Processing of sEMG signals for online motion of a single robot joint through GMM modelization

Valentini

Michieletto

Spolaor

et al. 2015

2015 IEEE International Conference on Rehabilitation Robotics (ICORR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…To improve clarity, we report both the polynomial model order and a description of the features used for estimation in Table 2. Prediction equations belonging to the ℙ class in this review include those resulting from Gaussian mixture regression [56], lasso [57] and ridge [58] regression, and an ensemble of polynomials [58] among others. The NN class is viewed as a special case where the basis functions are neural networks.…”

Section: Prediction Equation Classificationmentioning

confidence: 99%

“…These techniques have been shown to improve estimation performance compared to other methods [35,45]. Most papers used the standard highpass filter, rectify, lowpass filter processing to estimate sEMG amplitudes and a broad range of lowpass filter cutoff frequencies were used [15,46,48,53,54,56,57,62,68,70,71,73,84,92,95]. In addition to enveloping techniques, some incorporate the fact that the observed sEMG is the superposition of pattern to exist [97].…”

Section: Incorporating Domain Knowledgementioning

confidence: 99%

Estimating Biomechanical Time-Series with Wearable Sensors: A Systematic Review of Machine Learning Techniques

Gurchiek¹,

Cheney²,

McGinnis³

2019

Preprint

View full text Add to dashboard Cite

Wearable sensors have the potential to enable comprehensive patient characterization and optimized clinical intervention. Critical to realizing this vision is accurate estimation of biomechanical time-series in daily-life, including joint, segment, and muscle kinetics and kinematics, from wearable sensor data. The use of physical models for estimation of these quantities often requires many wearable devices making practical implementation more difficult. However, regression techniques may provide a viable alternative by allowing the use of a reduced number of sensors for estimating biomechanical time-series. Herein, we review 46 articles that used regression algorithms to estimate joint, segment, and muscle kinematics and kinetics. We present a high-level comparison of the many different techniques identified and discuss the implications of our findings concerning practical implementation and further improving estimation accuracy. In particular, we found that several studies report the incorporation of domain knowledge often yielded superior performance. Further, most models were trained on small datasets in which case nonparametric regression often performed best. No models were open-sourced, and most were subject-specific and not validated on impaired populations. Future research should focus on developing open-source algorithms using complementary physics-based and machine learning techniques that are validated in clinically impaired populations. This approach may further improve estimation performance and reduce barriers to clinical adoption.

show abstract

“…The GP model has superior flexibility when the parameters that directly determine the model performance can be adjusted through learning [17,18]. As for the mapping structure, one widely applied approach is to map muscle activation or neural signals to the joint angle [19]. When the history of the movements reflects the inherent dynamics of human motion [20], joint angle could also be predicted using autoregressive models.…”

Section: Introductionmentioning

confidence: 99%

“…For the input signal selection, electromyography (EMG) signals which reflect the muscle activation have been widely utilized in the fields of joint angle learning and prediction [19,24]. The EMG signal provides easy access to physiological processes that cause the muscle to generate force and produce movement.…”

Section: Introductionmentioning

confidence: 99%

Gaussian Process-Integrated State Space Model for Continuous Joint Angle Prediction from EMG and Interactive Force in a Human-Exoskeleton System

2019

View full text Add to dashboard Cite

As one of the most direct indicators of the transparency between a human and an exoskeleton, interactive force has rarely been fused with electromyography (EMG) in the control of human-exoskeleton systems, the performances of which are largely determined by the accuracy of the continuous joint angle prediction. To achieve intuitive and naturalistic human intent learning, a state space model (SSM) for continuous angle prediction of knee joint is developed. When the influence of the interactive force is often ignored in the existing models of human-exoskeleton systems, interactive force is applied as the measurement model output of the proposed SSM, and the EMG signal is used as the state model input signal to indicate muscle activation. The forward dynamics of joint motion and the human-machine interaction mechanism, i.e., the biomechanical interpretations of the interactive force generation mechanism, are derived as the bases for the state model and measurement model based on Hill’s muscle model and semiphenomenological (SP) muscular model, respectively. Gaussian process (GP)-based nonlinear autoregressive with the exogenous inputs (NARX) model and back-propagation neural network (BPNN) are applied to provide better adaptivity for the SSM in practical applications. Corresponding experimental results demonstrate the validity and superiority of the method.

show abstract

GMM-Based Single-Joint Angle Estimation Using EMG Signals

Cited by 18 publications

References 28 publications

Processing of sEMG signals for online motion of a single robot joint through GMM modelization

Processing of sEMG signals for online motion of a single robot joint through GMM modelization

Estimating Biomechanical Time-Series with Wearable Sensors: A Systematic Review of Machine Learning Techniques

Gaussian Process-Integrated State Space Model for Continuous Joint Angle Prediction from EMG and Interactive Force in a Human-Exoskeleton System

Contact Info

Product

Resources

About