Trajectory Clustering for the Classification of Eye-Tracking Users With Motor Disorders

Clemotte, Alejandro; Arregui, Harbil; Velasco, Miguel A.; Unzueta, Luis; Goenetxea, Jon; Elordi, Unai; Rocón, Eduardo; Ceres, Ramón; Bengoechea, Javier; Arizkuren, Iosu; Jauregui, Eduardo

Use this link to cite:

http://hdl.handle.net/2183/29567

Trajectory Clustering for the Classification of Eye-Tracking Users With Motor Disorders

Files

2016_Clemotte_Alejandro_Trajectory_clustering_for_the_classification_of_eye-tracking_users_with_motor_disorders.pdf (1.66 MB)

Identifiers

URI: http://hdl.handle.net/2183/29567

DOI: 10.17979/spudc.9788497498081.0150

Publication date

2016

Authors

Clemotte, Alejandro

Arregui, Harbil

Velasco, Miguel A.

Unzueta, Luis

Goenetxea, Jon

Elordi, Unai

Rocón, Eduardo

Ceres, Ramón

Bengoechea, Javier

Arizkuren, Iosu

Bibliographic citation

Clemotte, A., Arregui, H., Velasco, M.A., Unzueta, L., Goenetxea, J., Elordi, U., Rocon, E., Ceres, R., Bengoechea, J., Arizkuren, I., Jauregui, E. Trajectory clustering for the classification of eye-tracking users with motor disorders. En Actas de las XXXVII Jornadas de Automática. 7, 8 y 9 de septiembre de 2016, Madrid (pp. 150-155). DOI capítulo: https://doi.org/10.17979/spudc.9788497498081.0150 DOI libro: https://doi.org/10.17979/spudc.9788497498081

Abstract

[Abstract] This paper presents a pilot study completed in the framework of the INTERAAC project. The aim of the project is to develop a new human-computer interaction (HCI) solution based on eye-gaze estimation from webcam images for people with motor disorders such as cerebral palsy, neurodegenerative diseases, and spinal cord injury that are otherwise unable to use a keyboard or mouse. In this study, we analyzed cursor trajectories recorded during the experiment and validated that users with different diseases can be automatically classi ed in groups based on trajectory metrics. For the clustering, Ward's method was used. The metrics are based on speed and acceleration statistics from full fi ltered tracks. The results show that the participants can be grouped into two main clusters. The main contribution of this work is the evaluation of the clustering techniques applied to eye-gaze trajecto- ries for the automatic classi cation of users diseases based on a real experiment carried with the help of three clinical partners in Spain.