摘要: 本贴列出实验室在粒计算, 特别是属性约简方向的一些工作. 主要目的是保存 bib 方便以后引用.
1. SCI 期刊论文
1.1 名词性属性值划分与离散化
1.1.1 名词型属性值划分, 是属性约简的泛化. 本文将它转换成一系列的属性约简问题, 并证明了其最优子结构性质. 贪心选择性质可能不成立.
这也是我发表的第一篇 SCI 期刊论文.
@ARTICLE{MinLiuFang2008Partition,
author = {Fan Min and Qi-He Liu and Chun-Lan Fang},
title = {Rough sets approach to symbolic value partition},
journal = {International Journal of Approximate Reasoning},
year = {2008},
volume = {49},
number = {3},
pages = {689--700},
doi = {10.1016/j.ijar.2008.07.002}
}
1.1.2 温柳英基于 MinLiuFang2008Partition 继续做了一些工作.
@ARTICLE{WenMin2015Granular,
author = {Liu-Ying Wen and Fan Min},
title = {A granular computing approach to symbolic value partitioning},
journal = {Fundamenta Informaticae},
year = {2015},
volume = {142},
number = {1-4},
pages = {337--371},
doi = {10.3233/FI-2015-1297}
}
1.1.3 名词型数据划分在多标签中的应用.
@ARTICLE{WenMin2015Granular,
author = {Liu-Ying Wen and Chao-Guang Luo and Wei-Zhi Wu and Fan Min},
title = {Multi-label symbolic value partitioning through random walks},
journal = {Neurocomputing},
year = {2020},
volume = {387},
pages = {195--209},
doi = {10.1016/j.neucom.2020.01.046}
}
1.1.4 离散化.
@ARTICLE{WenMinWang2017Two,
author = {Liu-Ying Wen and Fan Min and Shi-Yuan Wang},
title = {A two-stage discretization algorithm based on information entropy},
journal = {Applied Intelligence},
year = {2017},
volume = {47},
pages = {1169--1185},
doi = {10.1007/s10489-017-0941-0}
}
1.2 代价敏感属性约简
1.2.1 考虑公共代价和序列因素, 建立一个代价敏感决策系统的体系, 包括 6 个基本模型. 这篇论文没有涉及任何算法, 但为后面的工作打下了数据模型的基础.
这也是我第一篇被引过百的论文.
@ARTICLE{MinLiu2009AHierarchical,
author = {Fan Min and Qi-He Liu},
title = {A hierarchical model for test-cost-sensitive decision systems},
journal = {Information Sciences},
year = {2009},
volume = {179},
issue = {14},
pages = {2442--2452},
doi = {10.1016/j.ins.2009.03.007}
}
1.2.2 首次将测试代价引入属性约简问题.
这篇论文至今被引用 300 余次. 刚 online 的时候, 连续三个月下载量排名该刊第一, 这也是我没想到的, 甚至以为网站出 bug.
@ARTICLE{MinHeQianZhu2011Test,
author = {Fan Min and Hua-Ping He and Yu-Hua Qian and William Zhu},
title = {Test-cost-sensitive attribute reduction},
journal = {Information Sciences},
year = {2011},
volume = {181},
issue = {22},
pages = {4928--4942},
doi = {10.1016/j.ins.2011.07.010}
}
1.2.3 考虑了带误差范围的数值型数据的属性约简. 误差越小的仪器, 测试代价越大. 将处理数据从名词型扩展到数值型, 更有实际意义.
@ARTICLE{MinZhu2012Range,
author = {Fan Min and William Zhu},
title = {Attribute reduction of data with error ranges and test costs},
journal = {Information Sciences},
year = {2012},
volume = {211},
pages = {48--67},
doi = {10.1016/j.ins.2012.04.031}
}
1.2.4 将代价属性约简归结为一个约束满足问题. 可以由它衍生出不同的新的具体问题.
这也是我在代价敏感属性约简问题上的最后一篇重要论文.
@ARTICLE{MinHuZhu2014Constraint,
author = {Fan Min and Qing-Hua Hu and William Zhu},
title = {Feature selection with test cost constraint},
journal = {International Journal of Approaximate Reasoning},
year = {2014},
volume = {55},
number = {1},
pages = {167--179},
doi = {10.1016/j.ijar.2013.04.003}
}
1.2.5 在 MinZhu2012Range 的基础上, 考虑了测量误差.
赵红的第一篇 SCI 论文.
@ARTICLE{ZhaoMinZhu2013Cost,
author = {Hong Zhao and Fan Min and William Zhu},
title = {Cost-sensitive feature selection of numeric data with measurement errors},
journal = {Journal of Applied Mathematics},
year = {2013},
volume = {2013},
pages = {1--13},
doi = {10.1155/2013/754698}
}
1.2.6 在 ZhaoMinZhu2013Cost 的基础上, 考虑了正态分布的测量误差.
@ARTICLE{ZhaoMinZhu2013Test,
author = {Hong Zhao and Fan Min and William Zhu},
title = {Test-cost-sensitive attribute reduction of data with normal distribution measurement errors},
journal = {Mathematical Problems in Engineering},
year = {2013},
volume = {2013},
pages = {1--12},
doi = {10.1155/2013/946070}
}
1.2.7 使用蚁群算法做 MinHeQianZhu2011Test 提出的代价敏感属性约简.
@ARTICLE{XuZhaoMin2013AntColony,
author = {Zi-Long Xu and Hong Zhao and Fan Min and William Zhu},
title = {Ant colony optimization with three stages for independent test cost attribute reduction},
journal = {Mathematical Problems in Engineering},
year = {2013},
volume = {2013},
pages = {1--12},
doi = {10.1155/2013/510167}
}
1.2.8 考虑时间代价敏感约简. 时间具有重叠性, 即等待某项检测结果的时候, 可以做其它检测.
@ARTICLE{CaiZhuDing2014Artificial,
author = {Jin-Ling Cai and William Zhu and Hai-Jun Ding and Fan Min},
title = {An improved artificial bee colony algorithm for minimal time cost reduction},
journal = {International Journal of Machine Learning \& Cybernetics},
year = {2014},
volume = {5},
issue = {5},
pages = {743--752},
doi = {10.1007/s13042-013-0219-8}
}
1.2.9 在 MinZhu2012Range 的基础上, 考虑多目标优化.
方宇的第一篇 SCI.
@ARTICLE{FangLiuMin2016MultiObjective,
author = {Yu Fang and Zhong-Hui Liu and Fan Min},
title = {Multi-objective cost-sensitive attribute reduction on data with error ranges},
journal = {International Journal of Machine Learning and Cybernetics},
year = {2016},
volume = {7},
issue = {5},
pages = {783--793},
doi = {10.1007/s13042-014-0296-3}
}
1.2.10 使用 PSO 仿生算法来做.
@ARTICLE{FangLiuMin2016PSO,
author = {Yu Fang and Zhong-Hui Liu and Fan Min},
title = {{A PSO} algorithm for multi-objective cost-sensitive attribute reduction on numeric data with error ranges},
journal = {Soft Computing},
year = {2016},
volume = {21},
pages = {7173--7189},
doi = {10.1007/s00500-016-2260-5}
}
1.2.10 与决策粗糙集结合.
@ARTICLE{LiaoZhuMin2014CostSensitive,
author = {Shu-Jiao Liao and Qing-Xin Zhu and Fan Min},
title = {Cost-sensitive attribute reduction in decision-theoretic rough set models},
journal = {Mathematical Problems in Engineering},
year = {2014},
volume = {2014},
pages = {1--14},
doi = {10.1155/2014/875918}
}
1.2.11 使用蚁群算法.
@ARTICLE{MinZhu2012Range,
author = {Fan Min and Zhi-heng Zhang and Ji Dong},
title = {Ant colony optimization with partial-complete searching for attribute reduction},
journal = {Journal of Computational Science},
year = {2017},
pages = {170--182},
doi = {10.1016/j.jocs.2017.05.007}
}
1.2.12 近似约简.
@ARTICLE{FangMin2019Cost,
author = {Yu Fang and Fan Min},
title = {Cost-sensitive approximate attribute reduction with three-way decisions},
journal = {International Journal of Approximate Reasoning},
year = {2019},
volume = {104},
pages = {148--165},
doi = {10.1016/j.ijar.2018.11.003}
}
1.2.13 快速约简.
@ARTICLE{FanCao2022Rapid,
author = {Yu Fang and Xue-Mei Cao and Xin Wang and Fan Min},
title = {Three-way sampling for rapid attribute reduction},
journal = {Information Sciences},
year = {2022},
volume = {609},
pages = {26--45},
doi = {10.1016/j.ins.2022.07.063}
}
1.3 粒关联规则
1.3.1 为粒关联规则进行数据离散化.
这种名气小, 经营不善的期刊, 特别拖.可惜这个方向最原创的论文被 Information Sciences 拒了, 所以我没再沿着它做.
@ARTICLE{HeMinZhu2014Comparison,
author = {Xu He and Fan Min and William Zhu},
title = {Comparison of discretization approaches for granular association rule mining},
journal = {Canadian Journal of Electrical and Computer Engineering},
year = {2014},
volume = {37},
number = {3},
pages = {157--167},
doi = {}
}
1.3.2 基于带参粗糙集的粒关联规则.
这篇论文是基于投 Information Sciences 那篇之后投的. 它都中了, 后者还处于审稿阶段.
@ARTICLE{HeMinZhu2013Parametric,
author = {Xu He and Fan Min and William Zhu},
title = {Parametric rough sets with application to granular association rule mining},
journal = {Mathematical Problems in Engineering},
year = {2013},
volume = {2013},
pages = {1--13},
doi = {10.1155/2013/461363}
}
1.4 粗糙拟阵与覆盖粗糙集
1.4.1 王石平粗糙拟阵的论文, 我只是参与了讨论.
@ARTICLE{WangZhuZhu2012Matroidal,
author = {Shi-Ping Wang and Qing-Xin Zhu and William Zhu and Fan Min},
title = {Matroidal structure of rough sets and its characterization to attribute reduction},
journal = {Knowledge-Based Systems},
year = {2012},
volume = {36},
pages = {155--161},
doi = {10.1016/j.ins.2012.07.030}
}
1.4.2 王石平在覆盖粗糙集方面的工作
@ARTICLE{WangZhuZhu2013Quantitative,
author = {Shi-Ping Wang and Qing-Xin Zhu and William Zhu and Fan Min},
title = {Quantitative analysis for covering-based rough set through the upper approximation number},
journal = {Information Sciences},
year = {2013},
volume = {220},
number = {20},
pages = {483--491},
doi = {10.1016/j.ins.2012.07.030}
}
1.4.3 王石平在粗糙拟阵方向的工作
@ARTICLE{WangZhuMin2013Matroidal,
author = {Shi-Ping Wang and William Zhu and Qing-Xin Zhu and Fan Min},
title = {Four matroidal structures of covering and their relationships with rough sets},
journal = {International Journal of Approximate Reasoning},
year = {2013},
volume = {54},
issue = {9},
pages = {1361--1372},
doi = {10.1016/j.ijar.2013.07.001}
}
1.4.4 王石平在布尔矩阵分解方面的工作
@ARTICLE{WangZhuZhu2014CharacteristicMatrix,
author = {Shi-Ping Wang and William Zhu and Qing-Xin Zhu and Fan Min},
title = {Characteristic matrix of covering and its application to {B}oolean matrix decomposition},
journal = {Information Sciences},
year = {2014},
volume = {263},
pages = {186--197},
doi = {10.1016/j.ins.2013.10.018}
}
1.4.5 王石平在覆盖粗糙集方面的工作.
@ARTICLE{WangZhuMin2013EquivalentCharacterizations,
author = {Shi-Ping Wang and Qing-Xin Zhu and William Zhu and Fan Min},
title = {Equivalent characterizations of some graph problems by covering-based rough sets},
journal = {Journal of Applied Mathematics},
year = {2013},
volume = {2013},
pages = {1--7},
doi = {10.1155/2013/519173}
}
1.4.6 汤建国在粗糙拟阵方面的工作.
这个期刊在数学方面不错.
@ARTICLE{TangShe2013Matroid,
author = {Jian-Guo Tang and Kun She and Fan Min and William Zhu},
title = {A matroidal approach to rough set theory},
journal = {Theoretical Computer Science},
year = {2013},
volume = {471},
pages = {1--11},
doi = {10.1016/j.tcs.2012.10.060}
}
1.5 基于邻域粗糙集的分类器
1.5.1 基于邻域粗糙集的分类.
张本文访问 Smale 一年的成果.
@ARTICLE{ZhangMin2015Representative,
author = {Ben-Wen Zhang and Fan Min and Davide Ciucci},
title = {Representative-based classification through covering-based neighborhood rough sets},
journal = {Applied Intelligence},
year = {2015},
volume = {43},
issue = {4},
pages = {840--854},
doi = {10.1007/s10489-015-0687-5}
}
1.5.2 基于 ZhangMin2015Representative 的工作, 几种相似度比较.
@ARTICLE{LiuZhangCiucciMin2018similarity,
author = {Fu-Lun Liu and Ben-Wen Zhang and Davide Ciucci and Fan Min},
title = {A comparison study of similarity measures for covering-based neighborhood classifiers},
journal = {Information Sciences},
year = {2018},
volume = {448--449},
pages = {1--17}
}
2. 国际会议论文
2.1 球形邻域粗糙集用于属性约简.
@INPROCEEDINGS{FangCao2022PAKDD,
author = {Yu Fang and Xue-Mei Cao and Xin Wang and Fan Min},
title = {Hypersphere neighborhood {R}ough {S}et for rapid attribute reduction},
booktitle = {PAKDD},
year = {2022},
pages = {161--173},
doi = {10.1007/978-3-031-05936-0_13}
}
3. 核心及其它期刊论文
3.1 Semi-greedy 的思想可以用于多数启发式算法. 想到这个 idea 的时候很兴奋, 以为是 一个非常原创的 big idea. 但发现它在某些领域已经被提出来了. 不过这也不影响我们广泛地使用它.
本来以为 Granular Computing 会冲 SCI 的, 否则也不把这篇论文投上面了.
@ARTICLE{MinZhu2012Range,
author = {Fan Min and Juan Xu},
title = {Semi-greedy heuristics for feature selection with test cost constraints},
journal = {Granular Computing},
year = {2016},
volume = {1},
issue = {3},
pages = {199--211},
doi = {10.1007/s41066-016-0017-2}
}
有时间再补充