Publications

Filter by type:

Eye tracking has been used in many scientific fields, such as behavioral sciences, education, marketing, and sports. Visualization usually plays an important role in the analysis of eye tracking data. In this presentation, we will briefly introduce the EyeTrackR R package that was developed for processing and visualizing eye tracking data from people looking at scientific posters. We will then present some of our first results of a study that tries to determine where people are looking when ranking the stability of a model holding certain postures. A portable eye-tracker was used to record the original video data of the study participants looking at the human postures. We use a modified version of the Syrjala test and a Voronoi-tessellation-based approach to determine whether study participants from two different groups have similar viewing patterns of these postures.
In ISPC, 2020

Determining whether two spatial distributions are statistically equivalent is the goal of the Syrjala test. When using continuous bivariate data, we show that the original Syrjala test produces different results depending on the data aggregation steps. In this article, we propose modifications to the previous version of the Syrjala test and make comparisons via simulations and an application. Simulation results indicate greater power and a more appropriate type one error rate for our modified Syrjala test. Furthermore, our new approach can be used for environmental data (for which the Syrjala test was originally developed), but also for data that originates from an eye-tracking study conducted at Utah State University.
In JSM, 2019

In this paper, Principal Component Analysis (PCA), and Sparse Principal Component Analysis (SPCA) are employed on different sets of candidate variables, amongst the material and sectional properties from the database compiled by Maguire et al. [18]. Predictions of ∆fps are made via Principal Component Regression models, and the method proposed, a linear model using SPCA on variables with a significant level of correlation with ∆fps, is shown to improve over current models without increasing complexity.
In IJCSM, 2019

Eye tracking has been used in many scientific fields, such as behavioral sciences, education, marketing, and sports. Visualization usually plays an important role in the analysis of eye tracking data. In this presentation, I will first introduce the EyeTrackR R package that was developed for processing and visualizing eye tracking data from people looking at scientific posters. I will then present our first results of a study that tries to determine where people are looking when ranking the stability of a model holding certain postures. A portable eye-tracker is used to record the original video data of people looking at human postures. Image processing is used to extract statistical information from the video data.
In ISSAS, 2018

In this article, we present preliminary results of a study that tries to determine where people are looking when ranking the stability of a model holding certain postures. A portable eye-tracker is used to record the original video data of people looking at human postures. Image processing is used to extract statistical information from the video data. Visualization and the Syrjala test are used for the statistical analyses.
In JSM, 2018

In this article, we present our first results of a study that tries to determine where people are looking when ranking the stability of an actor holding certain postures. A mobile eye-tracker is used to record the original video data of people looking at human postures. Image processing methods are employed to extract statistical information from the video data. The statistical analyses are based on visualization and machine learning approaches.
In JSM, 2017