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

Abstract

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.

Variability of Muscle Synergies in Hand Grasps: Analysis of Intra- and Inter-Session Data

“…Finally, these results are related to NNMF and might differ for other algorithms and models. Therefore, while the introduced concept may have impact for the field of muscle synergies and rehabilitation, the presented results generalize only for the forearm and hand applications and may find applications including prosthesis [55] and movement intention detection [56]. This work will be the starting point for a more detailed analysis of hand grasps based both on muscle and kinematic patterns, as done on previous pioneering work [57], where it was demonstrated that a more compact representation and a higher decoding capacity of grasping tasks is found when movements are expressed in the muscle kinematics domain rather than kinematic alone.…”

Biometric handwriting analysis to support Parkinson’s Disease assessment and grading

“…We used a Multi-Objective Genetic Algorithm (MOGA) to find the optimal network topology. A genetic algorithm is a powerful optimization technique that reflects the process of natural selection where the fittest individuals are selected for reproduction in order to produce offspring of the next generation, thus explaining its feasibility in several research domains [40, 41]. The MOGA algorithm was configured to find the optimum varying the following network parameters: (i) number of hidden layers (integer interval: 1 to 3), (ii) number of neurons per layer (integer interval: 1 to 256 for the first hidden layer and 0 to 255 for other ones), and (iii) activation functions for each layer (one among: log-sigmoid - logsig, hyperbolic tangent sigmoid -tansig, pure linear - purelin and symmetric saturating linear - satlins).…”

A comparison between two semantic deep learning frameworks for the autosomal dominant polycystic kidney disease segmentation based on magnetic resonance images

“…In this work, we designed and tested several CNNs architectures for the segmentation of the images. Since optimising the architecture of classifiers is still an open problem [34–36], often faced with evolutionary approaches, we decided to start from a well-known general CNN, the VGG-16 [37], and modify its structure varying several parameters.…”