首页 | 本学科首页   官方微博 | 高级检索  
     

自适应梯度Boosting算法及多硝基芳香族化合物密度的主因子选择
引用本文:张海,丁毅涛,王尧,胡荣祖,高红旭,赵凤起. 自适应梯度Boosting算法及多硝基芳香族化合物密度的主因子选择[J]. 火炸药学报, 2011, 34(2): 12-16
作者姓名:张海  丁毅涛  王尧  胡荣祖  高红旭  赵凤起
作者单位:1. 西北大学数学系,陕西,西安,710069;西安交通大学信息科学与系统科学研究所,陕西,西安,710049
2. 西北大学数学系,陕西,西安,710069
3. 西安交通大学信息科学与系统科学研究所,陕西,西安,710049
4. 西安近代化学研究所,陕西,西安,710065
摘    要:
用自适应梯度Boosting算法研究了影响多硝基芳香族化合物(PNACs)密度的主因子.选择分子结构描述码作影响特征参数,采用影响多硝基芳香族化合物密度的分子结构描述码,依据相关影响程度给出了相应分子结构描述码,预测密度值与文献值的相对误差在10%以内.

关 键 词:学习算法  Boosting算法  多硝基芳香族化合物  主因子

Selecting the Main Factors Influencing the Densities of Polynitroaromatic Compounds via Adaptive Gradient Boosting Algorithm
ZHANG Hai,DING Yi-tao,WANG Yao,HU Rong-zu,GAO Hong-xu,ZHAO Feng-qi. Selecting the Main Factors Influencing the Densities of Polynitroaromatic Compounds via Adaptive Gradient Boosting Algorithm[J]. Chinese Journal of Explosives & Propellants, 2011, 34(2): 12-16
Authors:ZHANG Hai  DING Yi-tao  WANG Yao  HU Rong-zu  GAO Hong-xu  ZHAO Feng-qi
Affiliation:1.Department of Mathematics,Northwest University,Xi′an 710069,China;2.Institute for Information Science and System Science,Xi′an Jiaotong University,Xi′an 710049,China;3.Xi′an Modern Chemistry Research Institute,Xi′an 710065,China)
Abstract:
The main factors affecting the densities of polynitroaromatic compounds(PNACs) were studied by using the adaptive gradient Boosting algorithm.The molecular structure describers(MSDs) are used as the input feature parameters.The MSDs affecting the densities of PNACs are chosen and the corresponding MSDs are given according to their relative degree of influencing.The relative error between the predicted values and literature ones of the densities of PNACs is within 10%.
Keywords:learning algorithm  Boosting algorithm  PNACs  main factor  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号