摘要
传统的舰船系统交叉覆盖数据分类方法存在着分类性能差的缺陷,为此提出基于机器学习的舰船系统交叉覆盖数据分类方法研究。采用随机森林算法对交叉覆盖数据的不相关特征属性进行剔除,得到有价值的交叉覆盖数据集合,利用领域粗糙集算法对有价值交叉覆盖数据集合的特征进行提取,以特征集合为依据,采用机器学习算法实现了舰船系统交叉覆盖数据的分类。通过实验得到,提出的舰船系统交叉覆盖数据分类方法的分类精度比传统方法高出30%,迭代次数比传统方法少了9次,说明提出的舰船系统交叉覆盖数据分类方法具备更好的分类性能。
Traditional classification methods for cross-cover data of warship systems have the disadvantage of poor classification performance. For this reason, a method for classification of cross-cover data of warship systems based on machine learning is proposed. Random forest algorithm is used to eliminate the irrelevant feature attributes of cross-cover data,and valuable cross-cover data sets are obtained. Domain rough set algorithm is used to extract the features of valuable crosscover data sets. Based on the feature sets, machine learning algorithm is used to realize the classification of cross-cover data of warship system. The experimental results show that the classification accuracy of the proposed method is 30% higher than that of the traditional method, and the number of iterations is 9 times less than that of the traditional method. This shows that the proposed method has better classification performance.
引文
[1]徐东,陶欧,林兆洲,等.基于机器学习方法中草药电子鼻智能鉴别分类器的优化[J].中华中医药学刊, 2017, 23(9):117–119.
[2]楚博策,文义红,陈金勇.基于多特征融合的SAR图像舰船自学习检测算法[J].无线电工程, 2018, 42(2):92–95.
[3]王军,黄杰飞,程勇.基于大数据处理的农业气象灾害分类模型[J].计算机仿真, 2017, 34(5):353–356.
[4]许学添,邹同浩.网络数据库中隐蔽数据快速挖掘方法研究[J].电子设计工程, 2016, 24(24):15–18.