{"id":{"repo_id":"uno","oai_identifier":"oai:scholarworks.uno.edu:td-1837"},"canonical_url":"https://search.dev.ndltd.org/etd/uno/oai:scholarworks.uno.edu:td-1837","repository":{"repo_id":"uno","name":"University of New Orleans","base_url":"https://scholarworks.uno.edu/do/oai/"},"display":{"title":"Clustering Via Supervised Support Vector Machines","abstract":"An SVM-based clustering algorithm is introduced that clusters data with no a priori knowledge of input classes. The algorithm initializes by first running a binary SVM classifier against a data set with each vector in the set randomly labeled. Once this initialization step is complete, the SVM confidence parameters for classification on each of the training instances can be accessed. The lowest confidence data (e.g., the worst of the mislabeled data) then has its labels switched to the other class label. The SVM is then re-run on the data set (with partly re-labeled data). The repetition of the above process improves the separability until there is no misclassification. Variations on this type of clustering approach are shown.","abstract_html":"An SVM-based clustering algorithm is introduced that clusters data with no a priori knowledge of input classes. The algorithm initializes by first running a binary SVM classifier against a data set with each vector in the set randomly labeled. Once this initialization step is complete, the SVM confidence parameters for classification on each of the training instances can be accessed. The lowest confidence data (e.g., the worst of the mislabeled data) then has its labels switched to the other class label. The SVM is then re-run on the data set (with partly re-labeled data). The repetition of the above process improves the separability until there is no misclassification. Variations on this type of clustering approach are shown.","abstract_has_math":false,"creators":["Merat, Sepehr"],"institution":null,"degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Winters-Hilt, Stephen","Summa, Christopher","Zhu, Dongxiao"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2008,"date_issued":"2008-08-07T07:00:00Z","date_published":"2008-08-07T07:00:00Z","updated_at":"2026-07-24T05:28:50Z","subjects":["clustering","machine learning","pattern recognition","support vector machines","supervised learning","unsupervised learning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarworks.uno.edu/td/857","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Winters-Hilt, Stephen","Summa, Christopher","Zhu, Dongxiao"]},{"key":"dc:creator","label":"Author","values":["Merat, Sepehr"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"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":["M.S."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["clustering","machine learning","pattern recognition","support vector machines","supervised learning","unsupervised learning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarworks.uno.edu/td/857"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["An SVM-based clustering algorithm is introduced that clusters data with no a priori knowledge of input classes. The algorithm initializes by first running a binary SVM classifier against a data set with each vector in the set randomly labeled. Once this initialization step is complete, the SVM confidence parameters for classification on each of the training instances can be accessed. The lowest confidence data (e.g., the worst of the mislabeled data) then has its labels switched to the other class label. The SVM is then re-run on the data set (with partly re-labeled data). The repetition of the above process improves the separability until there is no misclassification. Variations on this type of clustering approach are shown."]},{"key":"dc:title","label":"Title","values":["Clustering Via Supervised Support Vector Machines"]}]}],"canonical_facts":{"dc:contributor":["Winters-Hilt, Stephen","Summa, Christopher","Zhu, Dongxiao"],"dc:creator":["Merat, Sepehr"],"dc:description.abstract":["An SVM-based clustering algorithm is introduced that clusters data with no a priori knowledge of input classes. The algorithm initializes by first running a binary SVM classifier against a data set with each vector in the set randomly labeled. Once this initialization step is complete, the SVM confidence parameters for classification on each of the training instances can be accessed. The lowest confidence data (e.g., the worst of the mislabeled data) then has its labels switched to the other class label. The SVM is then re-run on the data set (with partly re-labeled data). The repetition of the above process improves the separability until there is no misclassification. Variations on this type of clustering approach are shown."],"dc:identifier":["https://scholarworks.uno.edu/td/857"],"dc:subject":["clustering","machine learning","pattern recognition","support vector machines","supervised learning","unsupervised learning"],"dc:title":["Clustering Via Supervised Support Vector Machines"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."]},"updated_at":"2026-07-24T05:28:50Z"}