Scalability of Random Forest in Myoelectric Control

Abstract

ObjectiveMyoelectric control systems translate electromyographic (EMG) signals into control commands, enabling immersive human-robot interactions in the real world and the Metaverse. The variability of EMG due to various confounding factors leads to significant performance degradation. Such variability can be mitigated by training a highly generalisable but massively parameterized deep neural network, which can be effectively scaled using a vast dataset. We aim to find an alternative simple, explainable, efficient and parallelisable model, which can flexibly scale up with a larger dataset and scale down to reduce model size, will significantly facilitate the practical implementation of myoelectric control. ApproachIn this work, we discuss the scalability of a random forest (RF) for myoelectric control. We show how to scale an RF up and down during the process of pre-training, fine-tuning, and automatic self-calibration. The effects of diverse factors such as bootstrapping, decision tree editing (pre-training, pruning, grafting, appending), and the size of training data are systematically studied using EMG data from 106 participants including both low- and high-density electrodes. Main resultsWe examined several factors that affect the size and accuracy of the model. The best solution could reduce the size of RF models by{approx} 500 x, with the accuracy reduced by only 1.5%. Importantly, for the first time we report the unique merit of RF that with more EMG electrodes (higher input dimension), the RF model size would be reduced, contrasting all other models. SignificanceAll of these findings unlock the full potential of RF in real-world applications.