摘要
为了对军用软件进行科学系统的过时淘汰评估,提出基于机器学习的软件过时淘汰评估模型;首先使用机器学习预处理与缩放技术处理相关的特征数据,然后基于主成分分析模型进行特征提取和降维,消除特征数据中的噪音值并选择重要的军用软件过时淘汰特征数据,使用由粒子群优化算法改进的支持向量机模型进行分类和评估建模,并使用混淆矩阵的精度评估模型,最后通过案例验证模型有效性、适用性和科学性。
To evaluate military software obsolescence scientifically and systematically,the model of software obsolescence evaluation based on machine learning is pointed.Firstly,the machine learning preprocessing and scaling techniques are used to process the related feature data,then the principal component analysis model is used to extract feature and reduce dimension,eliminate the noise value in the feature data and select important military software obsolete feature data,use particle swarm optimization algorithm to optimize support vector machine parameters and build SVM classification and evaluation model,use confusion matrix accuracy to evaluate the machine model,finally the test results showed the model is effective,applicable,and scientific.
作者
帅勇
宋太亮
郑玉杰
郑雪松
唐浩
Shuai Yong;Song Tailiang;Zheng Yujie;Zeng Xuesong;Tang Hao(Chongqing Ceprei Industrial Technology Research Institute, Chongqing401332, China;Chongqing Engineering Research Center of Electronic Information Products Reliability , Chongqing401332 China;China Defense Science & Technology Information Center100142, China)
出处
《计算机测量与控制》
2019年第5期131-135,共5页
Computer Measurement &Control
基金
武器装备预先研究基金(9140A19030314JB35275)
省部级科研项目(2016YYF0203604
MGY1704040
MGY1804040)
重庆市技术创新与应用示范重点研发项目(cstc2018jszxcyzd0634)
关键词
军用软件过时淘汰
机器学习
主成分分析
支持向量机
评估
military software obsolescence
machine learning
principe component analysis
support vector machine
evaluation
