由最大同类球提取模糊分类规则

徐明亮; 王士同

doi:10.11999/JEIT160779

由最大同类球提取模糊分类规则

doi: 10.11999/JEIT160779

徐明亮¹,
王士同²

2.
(江南大学数字媒体学院无锡 214122) ②(无锡环境科学与工程研究中心无锡 214063)

基金项目:

国家自然科学基金(61170122, 61202311, 61272210)，江苏省自然科学基金(BK2012552)，江苏省青蓝工程资助项目(2014)

计量
- 文章访问数: 998
- HTML全文浏览量: 89
- PDF下载量: 315
- 被引次数: 0
出版历程
- 收稿日期: 2016-07-22
- 修回日期: 2017-01-09
- 刊出日期: 2017-05-19

Extracting Fuzzy Rules from the Maximum Ball Containing the Homogeneous Data

XU Mingliang¹,
WANG Shitong²

2.
(The School of Digital Media, Jiangnan University, Wuxi 214122, China)

Funds:

The National Natural Science Foundation of China (61170122, 61202311, 61272210), The Natural Science Foundation of Jiangsu Province (BK2012552), The Qing Lan Project of Jiangsu Province (2014)

摘要

摘要: 为提高模糊分类规则的有效性和可解释性，该文提出一种基于最大同类球的模糊规则提取方法。首先，每个样本根据与最近异类之间的距离确定一个最大同类球。然后根据各个同类球中样本之间的包含关系和独有性对同类球进行约简。再根据约简后的同类球建立MA分类器的模糊规则前件。MA(Mamdani-Assilan)二分类器的模糊规则后件参数学习以加权分类错误平方最小化为目标函数，采用共轭梯度法求解后件参数。KEEL标准数据集中的12个10折交叉验数据集的对比分类实验验证了该方法的有效性。
- 模糊规则 /
- 分类 /
- 约简 /
- Mamdani-Assilan (MA) /
- 同类
Abstract: In order to improve the interpretability and effectiveness of the fuzzy classifier rules, this paper presents a new method to extract the fuzzy rules based on the maximum ball only containing the homogeneous data. At first, every sample constructs a maximum ball in the light of the shortest distance to heterogeneous samples. Then those balls are reduced according to the relation of inclusion and the unique among the samples that the ball encloses. Then the fuzzy rules are constructed with the reserved balls. The parameters learning of the antecedent part of the classifier are based on the minimization of the weight misclassification quadratic error and resolved with the conjugate gradient algorithm. The experiments on 12 benchmark datasets with 10 folds are performed to demonstrate the validity of the classifier.
- Fuzzy rule /
- Classifier /
- Reduction /
- Mamdani-Assilan (MA) /
- Homogeneous data

HTML全文

参考文献(18)

HARANDI F A and DERHAMI V. A reinforcement learning algorithm for adjusting antecedent parameters and weights of fuzzy rules in a fuzzy classifier[J]. Journal of Intelligent Fuzzy Systems, 2016, 30(4): 2339-2347. doi: 10.3233/IFS- 152004.

JAMALABADI H, NASROLLAHI H, ALIZADEH S, et al. Competitive interaction reasoning: A bio-inspired reasoning method for fuzzy rule based classification systems[J]. Information Sciences, 2016, 352: 35-47. doi: 10.1016/ j.ins.2016.02.052.

CINTRA M E, CAMARGO H A, and MONARD M C. Genetic generation of fuzzy systems with rule extraction using formal concept analysis[J]. Information Sciences, 2016, 349: 199-215. doi: 10.1016/j.ins.2016.02.026

POURPANAHA F, LIM C P, and MOHAMAD SALEHA J. A hybrid model of fuzzy ARTMAP and genetic algorithm for data classification and rule extraction[J]. Expert Systems With Applications, 2016, 49: 74-85. doi: 10.1016/j.eswa. 2015.11.009.

李继东, 张学杰. 基于遗传算法的多维模糊分类器构造的研究[J]. 软件学报, 2005, 16(5): 779-785.

LI J D and ZHANG X J. Research on the construction of fuzzy classifier system for multidimensional pattern classification using genetic algorithms[J]. Journal of Software, 2005, 16(5): 779-785.

RUDZINSKI F. A multi-objective genetic optimization of interpretability-oriented fuzzy rule-based classifiers[J]. Applied Soft Computing, 2016, 38: 118-133. doi: 10.1016/ j.asoc.2015.09.038.

MARIAN B G and RUDZINSKI F. A multi-objective genetic optimization for fast, fuzzy rule-based credit classification with balanced accuracy and interpretability[J]. Applied Soft Computing, 2016, 40: 206-220. doi: 10.1016/j.asoc.2015. 11.037.

SHANGHOOSHABAD A M and ABADEH M S. Robust, interpretable and high quality fuzzy rule discovery using krill herd algorithm[J]. Journal of Intelligent and Fuzzy Systems, 2016, 30(3): 1601-1612. doi: 10.3233/IFS-151867

GARCA-GALN S, PARDO P R, and MUNOZ EXPSITO J E. Rules discovery in fuzzy classifier systems with PSO for scheduling in grid computational infrastructures[J]. Applied Soft Computing, 2015, 29: 424-435. doi: 10.1016/j.asoc.2014.11.064.

WU Jue, YANG Lei, LI Tianrui, et al. Rule-based fuzzy classifier based on quantum ant optimization algorithm[J]. Journal of Intelligent Fuzzy Systems, 2015, 29 (6): 2365-2371. doi: 10.3233/IFS-151935.

MAHDIZADEH M and EFTEKHARI M. Generating fuzzy rule base classifier for highly imbalanced datasets using a hybrid of evolutionary algorithms and subtractive clustering[J]. Journal of Intelligent and Fuzzy Systems, 2014, 27(6): 3033-3046. doi: 10.3233/IFS-141261.

邢宗义, 张永, 侯远龙, 等. 基于模糊聚类和遗传方法的具备解释性和精确性的模糊分类系统设计[J]. 电子学报, 2006, 34(1): 83-88.

XING Zongyi, ZHANG Yong, HOU Yuanlong, et al. Design of interpretable and precise fuzzy classification system based on fuzzy clustering and genetic algorithm[J]. Acta Electronica Sinica, 2006, 34(1): 83-88.

王莉, 周献中, 李华雄. 基于决策粗糙集的模糊分类模型[J]. 信息与控制, 2014, 43(1): 24-29. doi: 10.3724/SP.J.1219.2014. 00024.

WANG Li, ZHOU Xianzhong, and LI Huaxiong. Fuzzy classification model based on decision-theoretic rough set[J]. Information and Control, 2014, 43(1): 24-29. doi: 10. 3724 /SP.J.1219.2014.00024.

JACK M L. Fuzzy (c + p)-means clustering and its application to a fuzzy rule-based classifier: Towards good generalization and good interpretability[J]. IEEE Transactions on Fuzzy Systems, 2015, 23(4): 802-812. doi: 10.1109/TFUZZ.2014.2327995

LESKI J M. Iteratively reweighted least squares classifier and is - and -regularized kernel versions[J]. Bulletin of the Polish Academy of Sciences: Technical Sciences, 2010, 58(1): 171-182. doi: 10.2478/v10175-010-0018-2.

施引文献

资源附件(0)

访问统计