{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-4468"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-4468","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"Soccer In-Game Event Classification Using Spatio-Temporal Data","abstract":"Classifying soccer ball events, such as pass, shot, ball loss, and ball out, are crucial for advancing game analytics and tactical insights. This thesis investigates the application of machine learning to classify these ball events using player and ball spatio-temporal data, as well as additional features. We implement and compare traditional machine learning algorithms (AdaBoost, Logistic Regression, and Random Forest) with several deep learning approaches, including Feed-Forward Neural Network (FFNN), sequence-to-sequence (seq2seq) recurrent models (Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU)), and Transformer. Our experiments, evaluated on a dataset comprising of three professional soccer matches using accuracy, precision, recall, and F1-score, demonstrate that the Transformer model performs the best. It outperforms all other models by effectively capturing the complex, long-range spatio-temporal dependencies inherent in player and ball movements. This study shows the effectiveness of Transformer models for soccer event classification and provides a baseline benchmark for future research in spatio-temporal sports analytics.","abstract_html":"Classifying soccer ball events, such as pass, shot, ball loss, and ball out, are crucial for advancing game analytics and tactical insights. This thesis investigates the application of machine learning to classify these ball events using player and ball spatio-temporal data, as well as additional features. We implement and compare traditional machine learning algorithms (AdaBoost, Logistic Regression, and Random Forest) with several deep learning approaches, including Feed-Forward Neural Network (FFNN), sequence-to-sequence (seq2seq) recurrent models (Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU)), and Transformer. Our experiments, evaluated on a dataset comprising of three professional soccer matches using accuracy, precision, recall, and F1-score, demonstrate that the Transformer model performs the best. It outperforms all other models by effectively capturing the complex, long-range spatio-temporal dependencies inherent in player and ball movements. This study shows the effectiveness of Transformer models for soccer event classification and provides a baseline benchmark for future research in spatio-temporal sports analytics.","abstract_has_math":false,"creators":["Haileyesus, Million"],"institution":null,"degree_name":"M.S. Data Science","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Vasil Hnatyshin, Ph.D.","Umashanger Thayasivam, Ph.D.","Shen-Shyang Ho, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:00:05Z","subjects":["Event Classification;Machine Learning;Soccer;Spatio-Temporal Data;Sports Analytics","Computer Sciences","Physical Sciences and Mathematics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/3462","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/3462","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://rdw.rowan.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ardw.rowan.edu%3Aetd-4468","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Vasil Hnatyshin, Ph.D.","Umashanger Thayasivam, Ph.D.","Shen-Shyang Ho, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Haileyesus, Million"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-11-10T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-11-10T08:00:00Z"]},{"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. Data Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Event Classification;Machine Learning;Soccer;Spatio-Temporal Data;Sports Analytics","Computer Sciences","Physical Sciences and Mathematics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/3462"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Classifying soccer ball events, such as pass, shot, ball loss, and ball out, are crucial for advancing game analytics and tactical insights. This thesis investigates the application of machine learning to classify these ball events using player and ball spatio-temporal data, as well as additional features. We implement and compare traditional machine learning algorithms (AdaBoost, Logistic Regression, and Random Forest) with several deep learning approaches, including Feed-Forward Neural Network (FFNN), sequence-to-sequence (seq2seq) recurrent models (Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU)), and Transformer. Our experiments, evaluated on a dataset comprising of three professional soccer matches using accuracy, precision, recall, and F1-score, demonstrate that the Transformer model performs the best. It outperforms all other models by effectively capturing the complex, long-range spatio-temporal dependencies inherent in player and ball movements. This study shows the effectiveness of Transformer models for soccer event classification and provides a baseline benchmark for future research in spatio-temporal sports analytics."]},{"key":"dc:title","label":"Title","values":["Soccer In-Game Event Classification Using Spatio-Temporal Data"]}]}],"canonical_facts":{"dc:contributor":["Vasil Hnatyshin, Ph.D.","Umashanger Thayasivam, Ph.D.","Shen-Shyang Ho, Ph.D."],"dc:creator":["Haileyesus, Million"],"dc:date.available":["2025-11-10T08:00:00Z"],"dc:date.created":["2025-11-10T08:00:00Z"],"dc:description.abstract":["Classifying soccer ball events, such as pass, shot, ball loss, and ball out, are crucial for advancing game analytics and tactical insights. This thesis investigates the application of machine learning to classify these ball events using player and ball spatio-temporal data, as well as additional features. We implement and compare traditional machine learning algorithms (AdaBoost, Logistic Regression, and Random Forest) with several deep learning approaches, including Feed-Forward Neural Network (FFNN), sequence-to-sequence (seq2seq) recurrent models (Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU)), and Transformer. Our experiments, evaluated on a dataset comprising of three professional soccer matches using accuracy, precision, recall, and F1-score, demonstrate that the Transformer model performs the best. It outperforms all other models by effectively capturing the complex, long-range spatio-temporal dependencies inherent in player and ball movements. This study shows the effectiveness of Transformer models for soccer event classification and provides a baseline benchmark for future research in spatio-temporal sports analytics."],"dc:identifier":["https://rdw.rowan.edu/etd/3462"],"dc:subject":["Event Classification;Machine Learning;Soccer;Spatio-Temporal Data;Sports Analytics","Computer Sciences","Physical Sciences and Mathematics"],"dc:title":["Soccer In-Game Event Classification Using Spatio-Temporal Data"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. Data Science"]},"updated_at":"2026-11-19T09:00:05Z"}