Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms

Christopher Gundler; Matthias Temmen; Alessandro Gulberti; Monika Pötter-Nerger; Frank Ückert

doi:10.3390/s24092688

Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms

Standard

Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms. / Gundler, Christopher; Temmen, Matthias; Gulberti, Alessandro ; Pötter-Nerger, Monika ; Ückert, Frank.

in: SENSORS-BASEL, Jahrgang 24, Nr. 9, 24.04.2024, S. 2688.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung

Harvard

Gundler, C, Temmen, M, Gulberti, A , Pötter-Nerger, M & Ückert, F 2024, 'Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms', SENSORS-BASEL, Jg. 24, Nr. 9, S. 2688. https://doi.org/10.3390/s24092688

APA

Gundler, C., Temmen, M., Gulberti, A., Pötter-Nerger, M., & Ückert, F. (2024). Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms. SENSORS-BASEL, 24(9), 2688. https://doi.org/10.3390/s24092688

Vancouver

Gundler C, Temmen M, Gulberti A , Pötter-Nerger M , Ückert F. Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms. SENSORS-BASEL. 2024 Apr 24;24(9):2688. https://doi.org/10.3390/s24092688

Bibtex

@article{8fa7c42b662b422abcce58db1c91c74b,

title = "Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms",

abstract = "High-quality eye-tracking data are crucial in behavioral sciences and medicine. Even with a solid understanding of the literature, selecting the most suitable algorithm for a specific research project poses a challenge. Empowering applied researchers to choose the best-fitting detector for their research needs is the primary contribution of this paper. We developed a framework to systematically assess and compare the effectiveness of 13 state-of-the-art algorithms through a unified application interface. Hence, we more than double the number of algorithms that are currently usable within a single software package and allow researchers to identify the best-suited algorithm for a given scientific setup. Our framework validation on retrospective data underscores its suitability for algorithm selection. Through a detailed and reproducible step-by-step workflow, we hope to contribute towards significantly improved data quality in scientific experiments.",

keywords = "Algorithms, Humans, Eye-Tracking Technology, Software, Data Accuracy, Eye Movements/physiology, Reproducibility of Results",

author = "Christopher Gundler and Matthias Temmen and Alessandro Gulberti and Monika P{\"o}tter-Nerger and Frank {\"U}ckert",

year = "2024",

month = apr,

day = "24",

doi = "10.3390/s24092688",

language = "English",

volume = "24",

pages = "2688",

journal = "SENSORS-BASEL",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "9",

}

RIS

TY - JOUR

T1 - Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms

AU - Gundler, Christopher

AU - Temmen, Matthias

AU - Gulberti, Alessandro

AU - Pötter-Nerger, Monika

AU - Ückert, Frank

PY - 2024/4/24

Y1 - 2024/4/24

N2 - High-quality eye-tracking data are crucial in behavioral sciences and medicine. Even with a solid understanding of the literature, selecting the most suitable algorithm for a specific research project poses a challenge. Empowering applied researchers to choose the best-fitting detector for their research needs is the primary contribution of this paper. We developed a framework to systematically assess and compare the effectiveness of 13 state-of-the-art algorithms through a unified application interface. Hence, we more than double the number of algorithms that are currently usable within a single software package and allow researchers to identify the best-suited algorithm for a given scientific setup. Our framework validation on retrospective data underscores its suitability for algorithm selection. Through a detailed and reproducible step-by-step workflow, we hope to contribute towards significantly improved data quality in scientific experiments.

AB - High-quality eye-tracking data are crucial in behavioral sciences and medicine. Even with a solid understanding of the literature, selecting the most suitable algorithm for a specific research project poses a challenge. Empowering applied researchers to choose the best-fitting detector for their research needs is the primary contribution of this paper. We developed a framework to systematically assess and compare the effectiveness of 13 state-of-the-art algorithms through a unified application interface. Hence, we more than double the number of algorithms that are currently usable within a single software package and allow researchers to identify the best-suited algorithm for a given scientific setup. Our framework validation on retrospective data underscores its suitability for algorithm selection. Through a detailed and reproducible step-by-step workflow, we hope to contribute towards significantly improved data quality in scientific experiments.

KW - Algorithms

KW - Humans

KW - Eye-Tracking Technology

KW - Software

KW - Data Accuracy

KW - Eye Movements/physiology

KW - Reproducibility of Results

U2 - 10.3390/s24092688

DO - 10.3390/s24092688

M3 - SCORING: Journal article

C2 - 38732794

VL - 24

SP - 2688

JO - SENSORS-BASEL

JF - SENSORS-BASEL

SN - 1424-8220

IS - 9

ER -