Software Reliability Assessment via Multi-dimension Wavelet Analysis

2016 Fiscal Year Final Research Report

• Project/Area Number: 26730039
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Software
• Research Institution: Tokyo Metropolitan University
• Principal Investigator: XIAO XIAO 首都大学東京, システムデザイン研究科, 助教 (30707477)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: ソフトウェア信頼性 / 非同次ポアソン過程 / ノンパラメトリック推定 / ウェーブレット解析 / 分散安定化変換 / 雑音除去 / バイアス補正 / 適合性評価

Outline of Final Research Achievements

In this research, we develop a wavelet analysis-based software reliability assessment method, keeping in mind the purpose of supporting decision makings in the software development project management. As a statistical inference technique, we focus on wavelet shrinkage estimation, and develop a theoretical framework to perform the statistical estimation with higher accuracy and lower computation cost. We develop a simplified statistical analysis tool to implement the wavelet-based estimation algorithm, and investigate the performance and applicability of the proposal though numerical experiments using real software fault data.

Free Research Field

ソフトウェア信頼性工学