基于迁移学习的跨公司航天软件缺陷预测

哈清华; 陈媛; 刘逻

doi:10.3788/OPE.20192702.0469

您当前的位置：

首页 >

文章列表页 >

基于迁移学习的跨公司航天软件缺陷预测

信息科学 | 更新时间：2020-08-13

- 基于迁移学习的跨公司航天软件缺陷预测
- Approach to cross-company spacecraft software defect prediction based on transfer learning
- 光学精密工程 2019年27卷第2期页码：469-478
- 作者机构：
  
  1.吉林大学计算机科学与技术学院，吉林长春 130012
  2.中国科学院长春光学精密机械与物理研究所，吉林长春 130033
  3.吉林大学符号计算与知识工程教育部重点实验室，吉林长春 130012
- 作者简介：
  
  [ "哈清华(1983-), 男, 吉林长春人, 回族, 助理研究员, 博士研究生, 2007年于哈尔滨工业大学获得硕士学位, 主要从事软件测试方面的研究。E-mail:haqinghuaha@hotmail.com" ]
- 基金信息：
  
  国家自然科学基金(61502198);国家自然科学基金(61572226);国家自然科学基金(61472161)
- DOI：10.3788/OPE.20192702.0469
  中图分类号： TB853.29
- 收稿日期：2018-06-27，
  
  录用日期：2018-9-6，
  
  纸质出版日期：2019-02-15
- 稿件说明：
移动端阅览
哈清华, 陈媛, 刘逻. 基于迁移学习的跨公司航天软件缺陷预测[J]. 光学精密工程, 2019,27(2):469-478.

Qing-hua HA, Yuan CHEN, Luo LIU. Approach to cross-company spacecraft software defect prediction based on transfer learning[J]. Optics and precision engineering, 2019, 27(2): 469-478.
哈清华, 陈媛, 刘逻. 基于迁移学习的跨公司航天软件缺陷预测[J]. 光学精密工程, 2019,27(2):469-478. DOI： 10.3788/OPE.20192702.0469.

Qing-hua HA, Yuan CHEN, Luo LIU. Approach to cross-company spacecraft software defect prediction based on transfer learning[J]. Optics and precision engineering, 2019, 27(2): 469-478. DOI： 10.3788/OPE.20192702.0469.

摘要

为提高航天软件测试的效率和质量，针对同公司航天软件数量少、研制周期长的特点，提出了一种跨公司航天软件缺陷预测方法。从航天软件背景信息复杂、规模大、功能独立等特征出发，提出基于静态分类缺陷预测的模型构建思想。引入迁移学习方法，利用最近邻分类器和数据引力模型，对训练数据的分布特征进行修正，提高训练数据与目标数据的相似性；为提高模型的泛化能力以适应目标数据的多样性，提出在训练数据中加入少量目标数据用于模型训练。将该方法在实际工程中进行应用，实验结果表明，与已有软件缺陷预测方法相比，该方法在保持较低误报率(不高于0.3)的情况下可有效提高召回率(接近0.6)，整体可信度得到有效增强(G-measure超过0.6)，方法稳定度高，泛化能力较强；本方法在实际工程中对测试规模影响可控，测试效率得到提高。

Abstract

In order to improve the efficiency and quality of aerospace software testing

an approach to cross-company aerospace software defect prediction was proposed

especially for the scarcity of within-company software and the long cycle of development. Considering the complexity

large scale

and independent functions of aerospace software

the idea of building a defect prediction model based on static classification was proposed. In this paper

the transfer learning method was introduced. Using the nearest neighbor classifier and data gravity model

the distribution characteristics of training data were corrected to improve the similarity between training data and target data. In order to improve the generalization ability of the model to adapt to the diversity of target data

a small amount of target data was added to the training data for model training. The approach was applied to the test for aerospace software testing. The results of application show that

compared with existing software defect prediction methods

the proposed method can effectively improve the recall rate (close to 0.6) with a low false alarm rate (not higher than 0.3). The overall credibility is effectively enhanced (G-measure is over 0.6)

and the method has high stability and strong generalization ability. This method can control the test scale in practical projects and improve testing efficiency.

关键词

Keywords

references

王俊杰, 沈湘衡, 张波, 等.环境参数与状态参数融合的测试用例集约简方法[J].光学精密工程, 2009, 17(7):1678-1685.

WANG J J, SHEN X H, ZHANG B, et al ..Optimal test suite generation methods based on fusion of environment and state parameters [J]. Opt. Precision Eng ., 2009, 17(7): 1678-1685.(in Chinese)

苗悦, 王峰.敏捷成像卫星"逐级择优"在轨任务实时规划[J].光学精密工程, 2018, 26(1):150-160.

MIAO Y, WANG F. Optimize-by-priority on-orbit task real-time planning for agile imaging satellite [J]. Opt. Precision Eng. , 2018, 26(1): 150-160.(in chinese)

MCCABE T J. A complexity measure [J]. IEEE Transactions on Software Engineering , 1976, SE-2(4): 308-320.

CHIDAMBER S R, KEMERER C. A metrics suite for object oriented design[J]. IEEE Transactions on Software Engineering , 1994, 20(6): 476-493.

陈翔, 王莉萍, 顾庆, 等.跨项目软件缺陷预测方法研究综述[J].软件学报, 2018, 41(1):254-274.

CHEN X, WANG L P, GU Q, et al .. A survey on cross-project software defect prediction methods [J]. Journal of Software , 2018, 41(1): 254-274.(in Chinese)

TURHAN B, MENZIES T, Bener A B, et al .. On the relative value of cross-company and within-company data for defect prediction [J]. Empirical Software Engineering , 2009, 14(5): 540-578..

ZIMMERMANN T, NAGAPPAN N, GALL H, et al .. Cross-project defect prediction: a large scale experiment on data vs. domain vs. process [C]. Proc. Joint Meeting of the European Software Engineering Conference and the ACM Sigsoft Symposium on the Foundations of Software Engineering ., 2009: 91-100.

LIU D, LIANG D. Three-way decisions in ordered decision system [J]. Knowledge-Based Systems , 2017, 137(12):182-195.

Ma Y, Luo G, Zeng X, et al .. Transfer learning for cross-company software defect prediction [J]. Information & Software Technology , 2012, 54(3):248-256.

ZHANG, FENG, MOCKUS, et al .. Towards building a universal defect prediction model [J]. Empirical Software Engineering , 2016, 21(5):2107-2145.

KAMEI Y, FUKUSHIMA T, MCINTOSH S, et al .. Studying just-in-time defect prediction using cross-project models [J]. Empirical Software Engineering , 2016, 21(5):2072-2106.

ZHANG F, ZHENG Q, ZOU Y, et al .. Cross-project defect prediction using a connectivity-based unsupervised classifier [C]. Ieee/acm, International Conference on Software Engineering. IEEE , 2017: 309-320.

KHOSHGOGTAAR T M, CUKIC B, SELIYA N. An empirical assessment on program module-order models [J]. Quality Technology & Quantitative Management , 2007, 4(2):171-190.

ZIMMERMANN T, PREMRAJ R, ZELLER A. Predicting defects for eclipse [C]. International Workshop on Predictor MODELS in Software Engineering, 2007. Promise'07: ICSE Workshops. IEEE , 2007: 9.

PENG L, YANG B, CHEN Y, et al .. Data gravitation based classification [J]. Information Sciences An International Journal , 2009, 179(6):809-819.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种跨公司航天软件缺陷预测方法

基于ACGAN和迁移学习的骨显像分类方法

融合注意力的ConvNeXt视网膜病变自动分级

基于标签预留Softmax算法的机器视觉检测鉴别语义分割迁移学习技术

融合多尺度图像的密集神经网络肺部肿瘤识别算法