AI Insight
This study developed an explainable machine learning framework for classifying eye gaze direction using electrooculography (EOG) signals from nine participants. Four tree-based models (Decision Tree, Random Forest, XGBoost, and CatBoost) achieved very high accuracy in distinguishing nine gaze classes, with Random Forest performing best. Using SHAP and LIME interpretability methods, the researchers found that amplitude-related features, particularly channel means and medians, were the primary drivers of classification decisions.
Why it matters
EOG-based gaze tracking offers a low-cost alternative to traditional eye-tracking systems for human-computer interaction applications. The explainable AI approach enhances trustworthiness and allows researchers to verify that models are making physiologically meaningful decisions rather than exploiting data artifacts, which is critical for clinical and assistive technology applications.
Understand the Science
by Ayse Nur Ay Gul
Electrooculography (EOG) is a low-cost biosignal modality for gaze-based human–computer interaction, but reliable validation and model interpretability remain important challenges for machine learning-based gaze classification. This study proposes an explainable EOG gaze classification framework using UNIOVI-EOG dataset. Horizontal and vertical EOG recordings from nine participants were converted into 100 ms non-overlapping windows, and only stable windows with at least 90% label purity were retained. Time-domain window features were extracted and evaluated using Decision Tree, Random Forest, XGBoost, and CatBoost classifiers under subject-wise five-fold cross-validation, ensuring that participants in the validation folds were not included in training. The final dataset contained 81,481 accepted windows across nine gaze classes. All models achieved very high subject-wise performance, with Random Forest providing the strongest overall results. The high performance was consistent with the controlled fixation protocol and the strong separability of horizontal and vertical EOG amplitude patterns, as supported by simple mean-amplitude baseline and leakage diagnostic analyses. Model interpretability was assessed using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME). The explanations showed that amplitude-related features, especially channel means, medians, quantiles, and absolute mean values, were the main contributors to classification decisions. SHAP–LIME rank correlation and permutation-based faithfulness analysis provided additional quantitative support for the explanations. These findings suggest that leakage-controlled, window-level, explainable machine learning can provide accurate and physiologically interpretable EOG gaze classification in controlled experimental settings.
Source: Interpretable EOG-based gaze classification using tree-based models: A SHAP and LIME analysis