A research on process-dynamics mining from spatiotemporal process sequences

2017 Fiscal Year Final Research Report

• Project/Area Number: 26330253
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Shimane University
• Principal Investigator: Hirano Shoji 島根大学, 医学部, 准教授 (60333506)
• Research Collaborator: TSUMOTO Shusaku
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: データマイニング / 診療プロセス / 位置情報

Outline of Final Research Achievements

This research investigated process-dynamics mining, which facilitates knowledge discovery from spatiotemporal process sequences. Followings are main contributions. (1) Proposed a method to visualize the dynamics of outpatients in a hospital based on the clinical action records and input device locations. (2) Proposed a method to analyze the relationships between the stay time of outpatients and treatment processes they received during their hospital visits. The results suggested that a visit needs long time if treatments or examinations should be executed during the consultation, or if injections such as intravenous drips were involved in the process. (3) Proposed a temporal pattern mining method based on ranged relations. Experimental results demonstrated that the proposed method could generate frequent patterns with abstracted time ranges embedded in their temporal relations.

Free Research Field

データマイニング