• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of Metrics Based on Complex Network Indicators to Predict Quality Changes in Derivative System Development

Research Project

Project/Area Number 17KT0122
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section特設分野
Research Field Intensification of Artifact Systems
Research InstitutionYokohama National University

Principal Investigator

HAMAGAMI TOMOKI  横浜国立大学, 大学院工学研究院, 教授 (30334204)

Project Period (FY) 2017-07-18 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2017: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Keywordsソフトウェア品質管理 / 複雑ネットワーク / 機械学習 / ニューラルネットワーク / 知能システム / ソフトウェア / ネットワーク指標 / メトリクス / 予測 / ソフトウェアメトリクス / ソフトウェア工学 / 品質評価
Outline of Final Research Achievements

In order to maintain the quality of software systems with long lifecycles, we have developed complex network metrics to evaluate the relationship between quality and structural changes caused by derivative development and continuous integration. Then, we contribute to autonomous software development by using machine learning prediction methods. First, we analyzed the software structure using the metrics and measured the index values of the complex network in the software before and after the modification. Next, we performed bug prediction by machine learning using these metrics and confirmed its effectiveness. In addition, we realized an extended BBNN technique for a fast design using an evolutionary method with metrics as the adaptive degree in FPGA implementation with block neural networks.

Academic Significance and Societal Importance of the Research Achievements

近年のソフトウェア開発においては,新規開発に比べ既存のソフトウェアを改変する派生開発の比重が増している。特に組み込みソフトウェアのように,ライフサイクルが比較的長く,機能追加のための改変が頻繁に行われる開発形態では,改変時の品質管理が重要な課題となる。かかるソフトウェアの発展において、将来的な品質を予測し問題が起きる前に対処することは重要な課題である。本研究では、複雑ネットワーク指標を用いたメトリクスによって改変後の品質に与える影響が予測できることを示すとともに、FPGAと機械学習を用いた実験により発展的ソフトウェアの品質評価と継続的インテグレーションの方法を明らかにした。

Report

(5 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (14 results)

All 2020 2019 2018 2017

All Journal Article (1 results) (of which Peer Reviewed: 1 results) Presentation (12 results) (of which Int'l Joint Research: 4 results) Book (1 results)

  • [Journal Article] Block-Based Neural Network Optimization with Manageable Problem Space2020

    • Author(s)
      Lee Kundo、Hamagami Tomoki
    • Journal Title

      IEEJ Transactions on Electronics, Information and Systems

      Volume: 140 Issue: 1 Pages: 68-74

    • DOI

      10.1541/ieejeiss.140.68

    • NAID

      130007779188

    • ISSN
      0385-4221, 1348-8155
    • Year and Date
      2020-01-01
    • Related Report
      2020 Annual Research Report 2019 Research-status Report
    • Peer Reviewed
  • [Presentation] Structured Feature Derivation for Transfer Learning on Credit Scoring2020

    • Author(s)
      Koichii Iwai, Masanori Akiyoshi, Tomoki Hamagami
    • Organizer
      2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] An Improved Auto-encoder Based on 2-Level Prioritized Experience Replay for High Dimension Skewed Data2019

    • Author(s)
      Li Xin、Hamagami Tomoki
    • Organizer
      Intelligent and Evolutionary Systems 2019, Springer
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Block-Based Neural Network High Speed Optimization2019

    • Author(s)
      Lee Kundo、Hamagami Tomoki
    • Organizer
      Intelligent and Evolutionary Systems 2019, Springer
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] クレジットスコアリングモデルにおけるクラスタリングを用いた転移学習アルゴリズム2019

    • Author(s)
      岩井康一,濱上知樹
    • Organizer
      第29回インテリジェント・システム・シンポジウム
    • Related Report
      2019 Research-status Report
  • [Presentation] LSTMを用いた多次元時系列データからの事象予測2018

    • Author(s)
      島田 直哉, 濱上 知樹
    • Organizer
      電気学会 システム研究会 ST-18-110
    • Related Report
      2018 Research-status Report
  • [Presentation] Prioritized Sampling Method for Autoencoder to Reduce Loss Rate for Skewed Data2018

    • Author(s)
      Li Xin,Hamagami Tomoki
    • Organizer
      電気学会 システム研究会 ST-18-076
    • Related Report
      2018 Research-status Report
  • [Presentation] GHSOM改良によるクラスタリング精度向上及び構造分類の実現2018

    • Author(s)
      史虹波, 徐浩源, 濱上知樹
    • Organizer
      電気学会 システム研究会 ST-18-114
    • Related Report
      2018 Research-status Report
  • [Presentation] 教師なしランダムフォレストを用いた多変量時系列データの類型化2018

    • Author(s)
      岡崎雅也, 濱上知樹
    • Organizer
      電気学会 システム研究会 ST-18-115
    • Related Report
      2018 Research-status Report
  • [Presentation] Performance oriented Block-Based Neural Network Model by parallelized neighbor's communication2018

    • Author(s)
      Kundo Lee, Tomoki Hamagami
    • Organizer
      IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2018 )
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] Theoretical adaptation of multiple rule-generation in XCS2018

    • Author(s)
      Masaya Nakata, Will Browne, Tomoki Hamagami
    • Organizer
      GECCO '18 Proceedings of the Genetic and Evolutionary Computation Conference
    • Related Report
      2018 Research-status Report
  • [Presentation] 機械学習による水処理施設の運転制御2018

    • Author(s)
      濱上知樹
    • Organizer
      電気学会システム研究会 ST-18-020
    • Related Report
      2017 Research-status Report
  • [Presentation] 機械学習によるソフトウェア品質メトリクスの研究2017

    • Author(s)
      濱上知樹
    • Organizer
      電気学会システム研究会 ST-18-010
    • Related Report
      2017 Research-status Report
  • [Book] 機械学習・人工知能 業務活用の手引き~導入の判断・具体的応用とその運用設計事例集~第3章 機械学習とそのアルゴリズム2017

    • Author(s)
      濱上知樹
    • Total Pages
      337
    • Publisher
      情報機構
    • ISBN
      9784865021424
    • Related Report
      2017 Research-status Report

URL: 

Published: 2017-07-21   Modified: 2022-12-28  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi