{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-10055"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-10055","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Comparative Study of Clustering Techniques on Eye-Tracking in Dynamic 3D Virtual Environments","abstract":"Eye-tracking has been used for decades to understand how and why an individual focuses on particular objects, areas, and elements of space. A vast body of knowledge exists on how eye-tracking is measured. However, historically, eye-tracking has been predominately studied using 2D environments, with limited work in 3D environments. The purpose of this study is to identify which methods most accurately represent the areas that have captured the participant’s visual attention within a 3D dynamic environment. This will be completed by evaluating different clustering methods of fixations using a customized virtual reality tool that collects eye-tracking data. There exist several different clustering techniques that could result in varying representations of fixation phenomenon. Thus, selecting the most appropriate clustering algorithm for different eye-tracking datasets is vital. This leads us to the problem of interest. We expect that traditional methods of clustering may fall short in this new scenario. This thesis will conduct a comparative analysis of several clustering methods. These include DBSCAN, OPTICS, BIRCH, Affinity Propagation, and Mean Shift. These methods range greatly in complexity and provide emphasis on different aspects of the data to ensure we find the most appropriate method(s). To test the appropriateness of each method, we will create four scenarios, each with a known number of distinct targets. Each scenario will be increasingly complex, ranging from static to dynamic. We task participants to look at the targets when they appear and for as long as they appear. Eye-tracking data on those targets will then be used as input for the clustering methods. The accuracy of each method will be measured by how well it represents the correct number and location of the known targets. An adequate number of participants will be used to produce the necessary data.","abstract_html":"Eye-tracking has been used for decades to understand how and why an individual focuses on particular objects, areas, and elements of space. A vast body of knowledge exists on how eye-tracking is measured. However, historically, eye-tracking has been predominately studied using 2D environments, with limited work in 3D environments. The purpose of this study is to identify which methods most accurately represent the areas that have captured the participant’s visual attention within a 3D dynamic environment. This will be completed by evaluating different clustering methods of fixations using a customized virtual reality tool that collects eye-tracking data. There exist several different clustering techniques that could result in varying representations of fixation phenomenon. Thus, selecting the most appropriate clustering algorithm for different eye-tracking datasets is vital. This leads us to the problem of interest. We expect that traditional methods of clustering may fall short in this new scenario. This thesis will conduct a comparative analysis of several clustering methods. These include DBSCAN, OPTICS, BIRCH, Affinity Propagation, and Mean Shift. These methods range greatly in complexity and provide emphasis on different aspects of the data to ensure we find the most appropriate method(s). To test the appropriateness of each method, we will create four scenarios, each with a known number of distinct targets. Each scenario will be increasingly complex, ranging from static to dynamic. We task participants to look at the targets when they appear and for as long as they appear. Eye-tracking data on those targets will then be used as input for the clustering methods. The accuracy of each method will be measured by how well it represents the correct number and location of the known targets. An adequate number of participants will be used to produce the necessary data.","abstract_has_math":false,"creators":["Johnson, Scott"],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Soukaina Filali Boubrahim","Isaac Cho","Brent Chamberlain"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:58:14Z","subjects":["Comparative Analysis","Eye‐tracking","Clustering","Virtual Reality","3D Virtual Environments","Fixation","Saccade","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/90e3-683b"],"render_values":[{"text":"https://doi.org/10.26076/90e3-683b","href":"https://doi.org/10.26076/90e3-683b","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/8885","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/8885","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-10055","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Soukaina Filali Boubrahim","Isaac Cho","Brent Chamberlain"]},{"key":"dc:creator","label":"Author","values":["Johnson, Scott"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2023-08-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Comparative Analysis","Eye‐tracking","Clustering","Virtual Reality","3D Virtual Environments","Fixation","Saccade","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/8885"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/90e3-683b"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Eye-tracking has been used for decades to understand how and why an individual focuses on particular objects, areas, and elements of space. A vast body of knowledge exists on how eye-tracking is measured. However, historically, eye-tracking has been predominately studied using 2D environments, with limited work in 3D environments. The purpose of this study is to identify which methods most accurately represent the areas that have captured the participant’s visual attention within a 3D dynamic environment. This will be completed by evaluating different clustering methods of fixations using a customized virtual reality tool that collects eye-tracking data. There exist several different clustering techniques that could result in varying representations of fixation phenomenon. Thus, selecting the most appropriate clustering algorithm for different eye-tracking datasets is vital. This leads us to the problem of interest. We expect that traditional methods of clustering may fall short in this new scenario. This thesis will conduct a comparative analysis of several clustering methods. These include DBSCAN, OPTICS, BIRCH, Affinity Propagation, and Mean Shift. These methods range greatly in complexity and provide emphasis on different aspects of the data to ensure we find the most appropriate method(s). To test the appropriateness of each method, we will create four scenarios, each with a known number of distinct targets. Each scenario will be increasingly complex, ranging from static to dynamic. We task participants to look at the targets when they appear and for as long as they appear. Eye-tracking data on those targets will then be used as input for the clustering methods. The accuracy of each method will be measured by how well it represents the correct number and location of the known targets. An adequate number of participants will be used to produce the necessary data."]},{"key":"dc:title","label":"Title","values":["Comparative Study of Clustering Techniques on Eye-Tracking in Dynamic 3D Virtual Environments"]}]}],"canonical_facts":{"dc:contributor":["Soukaina Filali Boubrahim","Isaac Cho","Brent Chamberlain"],"dc:creator":["Johnson, Scott"],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2023-08-01T07:00:00Z"],"dc:description.abstract":["Eye-tracking has been used for decades to understand how and why an individual focuses on particular objects, areas, and elements of space. A vast body of knowledge exists on how eye-tracking is measured. However, historically, eye-tracking has been predominately studied using 2D environments, with limited work in 3D environments. The purpose of this study is to identify which methods most accurately represent the areas that have captured the participant’s visual attention within a 3D dynamic environment. This will be completed by evaluating different clustering methods of fixations using a customized virtual reality tool that collects eye-tracking data. There exist several different clustering techniques that could result in varying representations of fixation phenomenon. Thus, selecting the most appropriate clustering algorithm for different eye-tracking datasets is vital. This leads us to the problem of interest. We expect that traditional methods of clustering may fall short in this new scenario. This thesis will conduct a comparative analysis of several clustering methods. These include DBSCAN, OPTICS, BIRCH, Affinity Propagation, and Mean Shift. These methods range greatly in complexity and provide emphasis on different aspects of the data to ensure we find the most appropriate method(s). To test the appropriateness of each method, we will create four scenarios, each with a known number of distinct targets. Each scenario will be increasingly complex, ranging from static to dynamic. We task participants to look at the targets when they appear and for as long as they appear. Eye-tracking data on those targets will then be used as input for the clustering methods. The accuracy of each method will be measured by how well it represents the correct number and location of the known targets. An adequate number of participants will be used to produce the necessary data."],"dc:identifier":["https://digitalcommons.usu.edu/etd/8885"],"dc:identifier.doi":["https://doi.org/10.26076/90e3-683b"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["Comparative Analysis","Eye‐tracking","Clustering","Virtual Reality","3D Virtual Environments","Fixation","Saccade","Computer Sciences"],"dc:title":["Comparative Study of Clustering Techniques on Eye-Tracking in Dynamic 3D Virtual Environments"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:58:14Z"}