A Linear Optimization Procedure for an EMG-driven NeuroMusculoSkeletal Model Parameters Adjusting: Validation Through a Myoelectric Exoskeleton Control

Buongiorno, Domenico; Barone, Francesco; Solazzi, Massimiliano; Bevilacqua, Vitoantonio; Frisoli, Antonio

doi:10.1007/978-3-319-42324-1_22

Cited by 15 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way it is possible to compare a really fast approach (LO) which optimizes only the basic model parameters (i.e., body mass and maximum muscle's force) against one which takes into account a bigger set of the muscle variables and non-linear relationships (GA-based). This manuscript extends our previous works (Buongiorno et al, 2015 , 2016 ) under three main aspects: increasing the number of tested subjects for both methods, extending the investigation of the LO method from the elbow joint only to both the elbow and shoulder joints and, reporting a structured comparison between the two methods. It is worth mentioning that both methods have been applied on a simplified upper limb model featuring only four muscles for the shoulder and two muscles for the elbow.…”

Section: Introductionsupporting

confidence: 55%

“…Although the isometric condition is far from the natural functioning of the muscles in daily-life activities (Merletti and Farina, 2016 ), we considered and optimized the model in isometric conditions with the goal of reducing the model complexity, that is in line with the main rationale of the study. This choice has been done already in previous works (Manal et al, 2012 ; Buongiorno et al, 2016 ), in which a model optimized in isometric conditions was used in quasi-static conditions for the real-time estimation of joint torques. The linear optimization approach has been compared with a GA-based optimization one.…”

Section: Discussionmentioning

confidence: 99%

“…For future studies, the two proposed optimization techniques may be compared in dynamic conditions and tested within a myo-control scheme. However, we have previously tested both optimization methods in a myoelectric control scenario with promising results (Buongiorno et al, 2015 , 2016 ). In particular, we proposed an admittance control able to generate the desired trajectory of an upper limb exoskeleton according to the EMG-based motion intention detection of the user (Figure 3 ).…”

Section: Discussionmentioning

confidence: 99%

“…As example, a trigger-based control scheme allows the user to start a predefined robot movement without being able of controlling the speed or the direction of the movement once it is started (Barsotti et al, 2015 ). It follows that simultaneous and proportional control paradigms have been gaining attention over the last years (Jiang et al, 2012 ; Buongiorno et al, 2015 , 2016 , 2017 ; Lobo-Prat et al, 2017 ), establishing themselves as promising tools to reduce the gap between research and commercial applications (Roche et al, 2014 ).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints

et al. 2018

Self Cite

View full text Add to dashboard Cite

The growing interest of the industry production in wearable robots for assistance and rehabilitation purposes opens the challenge for developing intuitive and natural control strategies. Myoelectric control, or myo-control, which consists in decoding the human motor intent from muscular activity and its mapping into control outputs, represents a natural way to establish an intimate human-machine connection. In this field, model based myo-control schemes (e.g., EMG-driven neuromusculoskeletal models, NMS) represent a valid solution for estimating the moments of the human joints. However, a model optimization is needed to adjust the model's parameters to a specific subject and most of the optimization approaches presented in literature consider complex NMS models that are unsuitable for being used in a control paradigm since they suffer from long-lasting setup and optimization phases. In this work we present a minimal NMS model for predicting the elbow and shoulder torques and we compare two optimization approaches: a linear optimization method (LO) and a non-linear method based on a genetic algorithm (GA). The LO optimizes only one parameter per muscle, whereas the GA-based approach performs a deep customization of the muscle model, adjusting 12 parameters per muscle. EMG and force data have been collected from 7 healthy subjects performing a set of exercises with an arm exoskeleton. Although both optimization methods substantially improved the performance of the raw model, the findings of the study suggest that the LO might be beneficial with respect to GA as the latter is much more computationally heavy and leads to minimal improvements with respect to the former. From the comparison between the two considered joints, it emerged also that the more accurate the NMS model is, the more effective a complex optimization procedure could be. Overall, the two optimized NMS models were able to predict the shoulder and elbow moments with a low error, thus demonstrating the potentiality for being used in an admittance-based myo-control scheme. Thanks to the low computational cost and to the short setup phase required for wearing and calibrating the system, obtained results are promising for being introduced in industrial or rehabilitation real time scenarios.

show abstract

Section: Introductionsupporting

confidence: 55%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, we also calculated the linear envelope (LE) of the EMG signal, which is an intuitive processing method of EMG reflecting the muscle force level [56]. Specifically, a full-wave rectification and a lowpass filter with a cutoff frequency of 3 Hz were used to obtain the LE, as previous research has evidenced the ability of the 3 Hz cutoff frequency to provide good relations with muscle force [56][57][58][59][60].…”

Section: Data Pre-processingmentioning

confidence: 99%

A Smart Terrain Identification Technique Based on Electromyography, Ground Reaction Force, and Machine Learning for Lower Limb Rehabilitation

et al. 2020

View full text Add to dashboard Cite

Automatic terrain classification in lower limb rehabilitation systems has gained worldwide attention. In this field, a simple system architecture and high classification accuracy are two desired attributes. In this article, a smart neuromuscular–mechanical fusion and machine learning-based terrain classification technique utilizing only two electromyography (EMG) sensors and two ground reaction force (GRF) sensors is reported for classifying three different terrains (downhill, level, and uphill). The EMG and GRF signals from ten healthy subjects were collected, preprocessed and segmented to obtain the EMG and GRF profiles in each stride, based on which twenty-one statistical features, including 9 GRF features and 12 EMG features, were extracted. A support vector machine (SVM) machine learning model is established and trained by the extracted EMG features, GRF features and the fusion of them, respectively. Several methods or statistical metrics were used to evaluate the goodness of the proposed technique, including a paired-t-test and Kruskal–Wallis test for correlation analysis of the selected features and ten-fold cross-validation accuracy, confusion matrix, sensitivity and specificity for the performance of the SVM model. The results show that the extracted features are highly correlated with the terrain changes and the fusion of the EMG and GRF features produces the highest accuracy of 96.8%. The presented technique allows simple system construction to achieve the precise detection of outcomes, potentially advancing the development of terrain classification techniques for rehabilitation.

show abstract

A Survey on Deep Learning in Electromyographic Signal Analysis

Buongiorno

Cascarano

Brunetti

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A Linear Optimization Procedure for an EMG-driven NeuroMusculoSkeletal Model Parameters Adjusting: Validation Through a Myoelectric Exoskeleton Control

Cited by 15 publications

References 23 publications

A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints

A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints

A Smart Terrain Identification Technique Based on Electromyography, Ground Reaction Force, and Machine Learning for Lower Limb Rehabilitation

A Survey on Deep Learning in Electromyographic Signal Analysis

Contact Info

Product

Resources

About