Revisiting Echo State Networks for Continuous Gesture Recognition

Abstract

Smartphones are equipped with Inertial Measurement Units (IMUs) that can capture user gesture data. Continuous gesture recognition is essential as it can be utilized and enhance human-computer interaction. Echo State Networks (ESNs) and Long Short-Term Memory (LSTM) models are well suited to performing this task. They have been successfully applied to the task in previous research, with LSTMs outperforming ESNs while having a considerably longer training time. However, the application of ESNs to continuous gesture recognition has not been fully explored as only the leaky integrator ESN has been used without hyperparameter optimization. In this study, we attempt to improve the ESN performance on the continuous gesture recognition task by experimenting with different model architectures and hyperparameter tuning. The performance of ESN models is significantly enhanced in terms of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F_{1}$</tex> -score to 0.88, which is higher than the previously best performance of 0.87 using an LSTM model on continuous gesture recognition. The significant improvement is in training time, which is approximately 13 seconds for the ESN model compared to 89 seconds for the LSTM model in past research.