The purpose of this research is to study the performance of kNN (k Nearest Neighbor) classification approach to determine patients’ mortality rate using ICU (Intensive Care Unit) medical records. The ICU data contains medical records collected during the patients’ first 48 hours stay at the ICU. The challenge of this research is the processing of ICU multivariate and high dimensional time-series data collected at irregular time periods. To handle the ICU irregular multivariate time-series three different methods were developed: Capture Statistics, Detect Changes, and Aggregate Segments. We examine the effectiveness of each method on kNN classification. In addition, this paper addresses imbalanced class distributions and their effect on kNN performance.
","abstract_html":"<p>The purpose of this research is to study the performance of kNN (k Nearest Neighbor) classification approach to determine patients’ mortality rate using ICU (Intensive Care Unit) medical records. The ICU data contains medical records collected during the patients’ first 48 hours stay at the ICU. The challenge of this research is the processing of ICU multivariate and high dimensional time-series data collected at irregular time periods. To handle the ICU irregular multivariate time-series three different methods were developed: Capture Statistics, Detect Changes, and Aggregate Segments. We examine the effectiveness of each method on kNN classification. In addition, this paper addresses imbalanced class distributions and their effect on kNN performance.</p>","abstract_has_math":false,"creators":["Djulovic, Admir"],"institution":null,"degree_name":"Master of Science (MS) in Computer Science","degree_level":"Thesis: EWU Only","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Dr. Dan Li","Dr. Carol Taylor","Dr. Robin O'Quinn"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-01T08:00:00Z","date_published":"2014-01-01T08:00:00Z","updated_at":"2026-07-24T02:12:26Z","subjects":["Computer Sciences"],"languages":[],"rights":["Access perpetually restricted to EWU users with an active EWU NetID"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://dc.ewu.edu/theses/262","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Dan Li","Dr. Carol Taylor","Dr. Robin O'Quinn"]},{"key":"dc:creator","label":"Author","values":["Djulovic, Admir"]}]},{"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: EWU Only"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS) in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Access perpetually restricted to EWU users with an active EWU NetID"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://dc.ewu.edu/theses/262"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The purpose of this research is to study the performance of kNN (k Nearest Neighbor) classification approach to determine patients’ mortality rate using ICU (Intensive Care Unit) medical records. The ICU data contains medical records collected during the patients’ first 48 hours stay at the ICU. The challenge of this research is the processing of ICU multivariate and high dimensional time-series data collected at irregular time periods. To handle the ICU irregular multivariate time-series three different methods were developed: Capture Statistics, Detect Changes, and Aggregate Segments. We examine the effectiveness of each method on kNN classification. In addition, this paper addresses imbalanced class distributions and their effect on kNN performance.
"]},{"key":"dc:title","label":"Title","values":["A study of kNN using ICU multivariate time series data"]}]}],"canonical_facts":{"dc:contributor":["Dr. Dan Li","Dr. Carol Taylor","Dr. Robin O'Quinn"],"dc:creator":["Djulovic, Admir"],"dc:description.abstract":["The purpose of this research is to study the performance of kNN (k Nearest Neighbor) classification approach to determine patients’ mortality rate using ICU (Intensive Care Unit) medical records. The ICU data contains medical records collected during the patients’ first 48 hours stay at the ICU. The challenge of this research is the processing of ICU multivariate and high dimensional time-series data collected at irregular time periods. To handle the ICU irregular multivariate time-series three different methods were developed: Capture Statistics, Detect Changes, and Aggregate Segments. We examine the effectiveness of each method on kNN classification. In addition, this paper addresses imbalanced class distributions and their effect on kNN performance.
"],"dc:identifier":["https://dc.ewu.edu/theses/262"],"dc:rights":["Access perpetually restricted to EWU users with an active EWU NetID"],"dc:subject":["Computer Sciences"],"dc:title":["A study of kNN using ICU multivariate time series data"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis: EWU Only"],"thesis:degree_name":["Master of Science (MS) in Computer Science"]},"updated_at":"2026-07-24T02:12:26Z"}