Predicting Selection Intention in Real-Time with Bayesian-based ML Model in Unimodal Gaze Interaction

TL;DR

This paper introduces a Bayesian-based machine learning model that predicts user selection intentions in real-time using only gaze data, improving interaction comfort and accuracy in XR environments.

Contribution

The study presents a novel Bayesian ML approach for real-time gaze-based selection prediction, eliminating the need for manual selection techniques in XR.

Findings

Achieved 97% accuracy and 96% F1 score in real-time inference.

Enabled more comfortable and accurate interactions compared to traditional methods.

Validated effectiveness through two empirical studies.

Abstract

Eye gaze is considered a promising interaction modality in extende reality (XR) environments. However, determining selection intention from gaze data often requires additional manual selection techniques. We present a Bayesian-based machine learning (ML) model to predict user selection intention in real-time using only gaze data. Our model uses a Bayesian approach to transform gaze data into selection probabilities, which are then fed into an ML model to discriminate selection intentions. In Study 1, our model achieved real-time inference with an accuracy of 0.97 and an F1 score of 0.96. In Study 2, we found that the selection intention inferred by our model enables more comfortable and accurate interactions compared to traditional techniques.