Proactive Data Mining for Detecting Anomalies in Derivational Development

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K00101
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Software
• Research Institution: Wakayama University
• Principal Investigator: OHIRA MASAO 和歌山大学, システム工学部, 准教授 (70379600)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 派生開発 / プロアクティブマイニング / High Impact Defects / 異常検知 / オープンソースソフトウェア

Outline of Final Research Achievements

The goal of this study is to construct a proactive mining method so that software maintainers can detect high impact defects (so called "anomalies" in this study) as soon as possible in software maintenance activities where large changes to existing software are required. We built a environment to monitor software changes which may induce high impact defects and construct a a proactive mining method to predict the possibility of being diagnosed with high impact defects in the future.

Free Research Field

ソフトウェア工学