Predicting Unmeasured Muscle Activations for the Upper Extremity



Journal Title

Journal ISSN

Volume Title



Patients with neuromuscular disease struggle to produce necessary muscle force and have trouble maintaining joint moments required to perform activities of daily living. Measuring muscle force values in patients with neuromuscular disease is important but challenging. Electromyography (EMG) can be used to obtain muscle activation values, which can be converted to muscle forces and joint torques. Surface electrodes can measure superficial muscles, but fine-wire electrodes are needed for deep muscles, although it is invasive and requires skilled personnel and preparation time. EMG-driven modeling with surface electrodes alone could underestimate the net torque. This research proposes two methodologies to predict unmeasured muscle activations from deeper muscles of the upper extremity. The first method finds unmeasured missing muscle activations one at a time by combining an EMG-driven musculoskeletal model and muscle synergies. This method will track inverse dynamics joint moments to determine synergy vector weights and predict muscle activations of selected shoulder and elbow muscles of a healthy subject. In addition, muscle-tendon parameter values (optimal fiber length, tendon slack length and maximum isometric force) have been personalized to the experimental subject. The methodology is tested for a wide range of rehabilitation tasks of the upper extremity across multiple healthy subjects. The study employs a methodology rooted in optimization principles, which involves comparing local and global optimization approaches while also exploring the impact of varying the number of target muscles. A second method is also implemented to derive unmeasured muscle activation patterns using machine learning algorithms based on anthropometric and kinematic features. Muscle activation data from healthy subjects were utilized for training two distinct networks: one employing the random forest algorithm and the other utilizing the artificial neural network. The networks then determine muscle activations of an unforeseen subject based on input features.

Embargo status: Restricted until 09/2025. To request the author grant access, click on the PDF link to the left.



muscle activation, EMG driven modeling, musculoskeletal modeling, machine learning, artificial neural networks (ANN) algorithm, random forest (RF) algorithm