基于多种群量子进化的区间二型模糊规则挖掘算法
|
摘要
利用智能优化算法挖掘模糊分类规则能够解决模糊前件参数和无关项的组合优化问题,但也存在依赖初始规则以及更新过程无指导等缺陷,导致分类精度难以保证.为此,本文以二型模糊规则分类系统为框架,采用模糊聚类得到代表性样本并启发式的产生初始规则,以量子等位基因形式对规则进行编码生成多初始种群,根据基因的优良性,以变尺度变异操作实现等位基因的指导性进化.在此基础上,利用矛盾规则重构机制,提高模糊规则分类系统的精度.将所提出算法与FH–GBML–IVFS–Amp算法和GAGRAD算法进行了分类精度对比,并在不同噪声水平下,与C4.5算法、朴素贝叶斯分类器和BP神经网络进行分类鲁棒性比较,实验结果表明所提出算法具有较好分类精度与鲁棒性.
Employing intelligent optimization algorithm to mine fuzzy classification rule, this solves a combinatorial optimization problem on fuzzy antecedent parameters and don't care variables. However, there are disadvantages such as the dependence of the initial rules and the lack of guidance in the updating process, which leads to it difficult to ensure classification accuracy. In this paper, the type–2 fuzzy rule-based classification system is employed as a framework, the fuzzy clustering is used to obtain the representative sample and the heuristic generation is used to generate initial fuzzy rules. The multiple initial populations are obtained by quantum alleles coding for each rule. Considering the superiority of genes, the variable scale mutation operation is used to guide the allele evolution in order to preserve the elitist population and individuals. And then, the contradictory rule is defined and the contradictory rule reconstruction is used to improve the accuracy of the fuzzy rules classification system. The classification accuracy of proposed algorithm is compared with both FH–GBML–IVFS–Amp and the GAGRAD algorithm, and classification robustness is compared with C4.5 algorithm,Naive Bayesian classifier and BP neural network at different class noise levels. The experimental results show that the classification accuracy and classification robustness of proposed algorithm are superior to compared algorithms.
Employing intelligent optimization algorithm to mine fuzzy classification rule, this solves a combinatorial optimization problem on fuzzy antecedent parameters and don't care variables. However, there are disadvantages such as the dependence of the initial rules and the lack of guidance in the updating process, which leads to it difficult to ensure classification accuracy. In this paper, the type–2 fuzzy rule-based classification system is employed as a framework, the fuzzy clustering is used to obtain the representative sample and the heuristic generation is used to generate initial fuzzy rules. The multiple initial populations are obtained by quantum alleles coding for each rule. Considering the superiority of genes, the variable scale mutation operation is used to guide the allele evolution in order to preserve the elitist population and individuals. And then, the contradictory rule is defined and the contradictory rule reconstruction is used to improve the accuracy of the fuzzy rules classification system. The classification accuracy of proposed algorithm is compared with both FH–GBML–IVFS–Amp and the GAGRAD algorithm, and classification robustness is compared with C4.5 algorithm,Naive Bayesian classifier and BP neural network at different class noise levels. The experimental results show that the classification accuracy and classification robustness of proposed algorithm are superior to compared algorithms.
引文
[1]PATERNAIN D,BUSTINCE H,PAGOLA M,et al.Capacities and overlap indexes with an application in fuzzy rule-based classification systems.Fuzzy Sets&Systems,2016,305(12):70-94.
[2]ELKANO M,GALAR M,SANZ J,et al.A global distributed approach to the Chi et al.fuzzy rule-based classification system for big data classification problems.IEEE International Conference on Fuzzy Systems.Naples,Italy:IEEE,2017:1-6.
[3]SCHAEFER G,NAKASHIMA T,ZAVISEK M.Analysis of breast thermograms based on statistical image features and hybrid fuzzy classification.Journal of Biological Chemistry,2008,289(16):11318-11330.
[4]GHAHAZI M A,ZARANDI M H F,HARIRCHIAN M H,et al.Fuzzy rule based expert system for diagnosis of multiple sclerosis.Norbert Wiener in the Century.Boston,US:IEEE,2014:1-5.
[5]TSANG C K,KWONG S,WANG H.Genetic-fuzzy rule mining approach and evaluation of feature selection techniques for anomaly intrusion detection.Pattern Recognition,2007,40(9):2373-2391.
[6]FERNANDEZ A,RIO S D,BAWAKID A,et al.Fuzzy rule based classification systems for big data with MapReduce:granularity analysis.Advances in Data Analysis&Classification,2017,11(4):1-20.
[7]ALDEN M E,BRYAN D M,LESSLEY B J,et al.Detection of financial statement fraud using evolutionary algorithms.Journal of E-merging Technologies in Accounting,2012,9(1):71-94.
[8]SHARMA P,RATNOO S.Bottom-up Pittsburgh approach for discovery of classification rules.International Conference on Contemporary Computing and Informatics.Mysore,India:IEEE,2015:31-37.
[9]GUERREROENAMORADO A,MORELL C,NOAMAN A Y,et al.An algorithm evaluation for discovering classification rules with gene expression programming.International Journal of Computational Intelligence Systems,2016,9(2):263-280.
[10]AYDOGAN E K,KARAOGLAN I,PARDALOS P M.h GA:Hybrid genetic algorithm in fuzzy rule-based classification systems for highdimensional problems.Applied Soft Computing,2012,12(2):800-806.
[11]MARIAN B,GORZALCZANY,FILIP R.A multi-objective genetic optimization for fast,fuzzy rule-based credit classification with balanced accuracy and interpretability.Applied Soft Computing,2016,40(3):206-220.
[12]DUCANGE P,LAZZERINI B,MARCELLONI F.Multi-objective genetic fuzzy classifiers for imbalanced and cost-sensitive datasets.Soft Computing,2010,14(7):713-728.
[13]ALCALAFDEZ J,ALCALA R,HERRERA F.A fuzzy association rule-based classification model for high-dimensional problems with genetic rule selection and lateral tuning.IEEE Transactions on Fuzzy Systems,2011,19(5):857-872.
[14]ZHANG Yongm,WU Xiaobei,XIANG Zhengrong,et al.Design of complex fuzzy classification system based on cooperative coevolutionary algorithm.Control Theory&Applications,2007,24(1):32-38.(张永,吴晓蓓,向峥嵘,等.复杂模糊分类系统的协同进化设计方法.控制理论与应用,2007,24(1):32-38.)
[15]ZHANG Lei,LI Renhou.Classifier design based on immune principle and fuzzy rule.Information and Control,2007,36(6):754-759.(张雷,李人厚.基于免疫原理和模糊规则的分类器设计.信息与控制,2007,36(6):754-759.)
[16]XIONG Weiqing.Classification rule mining based on binary ant colony optimization algorithm.Pattern Recognition and Artificial Intelligence,2008,21(4):500-505.(熊伟清.基于二元蚁群优化算法的分类规则挖掘.模式识别与人工智能,2008,21(4):500-505.)
[17]WU H,MENDEL J M.Classification of battlefield ground vehicles using acoustic features and fuzzy logic rule-based classifiers.IEEETransactions on Fuzzy Systems,2007,15(1):56-72.
[18]SANZ J A,FERNANDEZ A,BUSTINCE H,et al.Improving the performance of fuzzy rule-based classification systems with intervalvalued fuzzy sets and genetic amplitude tuning.Information Sciences,2010,180(19):3674-3685.
[19]MARATEB H R,GOUDARZI S.A noninvasive method for coronary artery diseases diagnosis using a clinically-interpretable fuzzy rule-based system.Journal of Research in Medical Sciences,2015,20(3):214-223.
[20]SANZ J A,BERNARDO D,HERRERA F,et al.A compact evolutionary interval-valued fuzzy rule-based classification system for the modeling and prediction of real-world financial applications with imbalanced data.IEEE Transactions on Fuzzy Systems,2014,23(4):973-990.
[21]ANTONELLI M,BERNARDO D,HAGRAS H,et al.Multiobjective evolutionary optimization of type-2 fuzzy rule-based systems for financial data classification.IEEE Transactions on Fuzzy Systems,2017,25(2):249-264.
[22]HARANDI F A,DERHAMI V.A reinforcement learning algorithm for adjusting antecedent parameters and weights of fuzzy rules in a fuzzy classifier.Journal of Intelligent&Fuzzy Systems,2016,30(4):2339-2347.
[23]FU Yaping,HUANG Min,WANG Hongfeng.Multipopulation multiobjective genetic algorithm for multiobjective permutation flow shop scheduling problem.Control Theory&Applications,2016,33(10):1281-1288.(付亚平,黄敏,王洪峰,等.面向多目标流水车间调度的多种群多目标遗传算法.控制理论与应用,2016,33(10):1281-1288.)
[24]WANG Chao,WANG Jianhui,GU Shusheng,et al.Improved incremental extreme learning machine based on multi-learning clonal selection algorithm.Control Theory&Applications,2016,33(10):368-379.(王超,王建辉,顾树生,等.基于多层学习克隆选择的改进式增量型超限学习机算法.控制理论与应用,2016,33(10):368-379.)
[25]ZHANG Yuxian,QIAN Xiaoyi,PENG Huideng.Real-coded quantum evolutionary algorithm based on allele.Chinese Journal of Scientific Instrument,2015,36(9):2129-2137.(张宇献,钱小毅,彭辉灯.基于等位基因的实数编码量子进化算法.仪器仪表学报,2015,36(9):2129-2137.)
[26]DOMBI J,GERA Z.Rule based fuzzy classification using squashing functions.Journal of Intelligent&Fuzzy Systems,2008,19(1):3-8.
[27]BACHE K,LICHMAN M.UCI machine learning repository.Irvine,University of California,2007.URL.
[28]LIU Wangshu,CHEN Xiang,GU Qing,et al.A Noise tolerable feature selection framework for software defect prediction.Chinese Journal of Computers,2016,39(33):1-16.(刘望舒,陈翔,顾庆,等.一种面向软件缺陷预测的可容忍噪声的特征选择框架.计算机学报,2016,39(33):1-16.)
[29]GARCIA S,FERNANDEZ A,LUENGO J,et al.Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining:experimental analysis of power.Information Sciences,2010,180(10):2044-2064.
[30]I S G,HERRERA F.An extension on statistical comparisons of classifiers over multiple data sets for all pairwise comparisons.Journal of Machine Learning Research,2008,9(12):2677-2694.
[31]MANTAS C J,ABELLAN J,CASTELLANO J G.Analysis of Credal-C4.5 for classification in noisy domains.Expert Systems with Applications,2016,61(11):314-326.
[32]BEREND D,KONTOROVICH A.A finite sample analysis of the Naive Bayes classifier.Journal of Machine Learning Research,2015,16(1):1519-1545.
[33]ZHAO Yanwei,REN Shedong,CHEN Weigang,et al.Extension classifier construction based on improved BP neural network.Computer Integrated Manufacturing Systems,2015,21(10):2807-2815.(赵燕伟,任设东,陈尉刚,等.基于改进BP神经网络的可拓分类器构建.计算机集成制造系统,2015,21(10):2807-2815.)
[2]ELKANO M,GALAR M,SANZ J,et al.A global distributed approach to the Chi et al.fuzzy rule-based classification system for big data classification problems.IEEE International Conference on Fuzzy Systems.Naples,Italy:IEEE,2017:1-6.
[3]SCHAEFER G,NAKASHIMA T,ZAVISEK M.Analysis of breast thermograms based on statistical image features and hybrid fuzzy classification.Journal of Biological Chemistry,2008,289(16):11318-11330.
[4]GHAHAZI M A,ZARANDI M H F,HARIRCHIAN M H,et al.Fuzzy rule based expert system for diagnosis of multiple sclerosis.Norbert Wiener in the Century.Boston,US:IEEE,2014:1-5.
[5]TSANG C K,KWONG S,WANG H.Genetic-fuzzy rule mining approach and evaluation of feature selection techniques for anomaly intrusion detection.Pattern Recognition,2007,40(9):2373-2391.
[6]FERNANDEZ A,RIO S D,BAWAKID A,et al.Fuzzy rule based classification systems for big data with MapReduce:granularity analysis.Advances in Data Analysis&Classification,2017,11(4):1-20.
[7]ALDEN M E,BRYAN D M,LESSLEY B J,et al.Detection of financial statement fraud using evolutionary algorithms.Journal of E-merging Technologies in Accounting,2012,9(1):71-94.
[8]SHARMA P,RATNOO S.Bottom-up Pittsburgh approach for discovery of classification rules.International Conference on Contemporary Computing and Informatics.Mysore,India:IEEE,2015:31-37.
[9]GUERREROENAMORADO A,MORELL C,NOAMAN A Y,et al.An algorithm evaluation for discovering classification rules with gene expression programming.International Journal of Computational Intelligence Systems,2016,9(2):263-280.
[10]AYDOGAN E K,KARAOGLAN I,PARDALOS P M.h GA:Hybrid genetic algorithm in fuzzy rule-based classification systems for highdimensional problems.Applied Soft Computing,2012,12(2):800-806.
[11]MARIAN B,GORZALCZANY,FILIP R.A multi-objective genetic optimization for fast,fuzzy rule-based credit classification with balanced accuracy and interpretability.Applied Soft Computing,2016,40(3):206-220.
[12]DUCANGE P,LAZZERINI B,MARCELLONI F.Multi-objective genetic fuzzy classifiers for imbalanced and cost-sensitive datasets.Soft Computing,2010,14(7):713-728.
[13]ALCALAFDEZ J,ALCALA R,HERRERA F.A fuzzy association rule-based classification model for high-dimensional problems with genetic rule selection and lateral tuning.IEEE Transactions on Fuzzy Systems,2011,19(5):857-872.
[14]ZHANG Yongm,WU Xiaobei,XIANG Zhengrong,et al.Design of complex fuzzy classification system based on cooperative coevolutionary algorithm.Control Theory&Applications,2007,24(1):32-38.(张永,吴晓蓓,向峥嵘,等.复杂模糊分类系统的协同进化设计方法.控制理论与应用,2007,24(1):32-38.)
[15]ZHANG Lei,LI Renhou.Classifier design based on immune principle and fuzzy rule.Information and Control,2007,36(6):754-759.(张雷,李人厚.基于免疫原理和模糊规则的分类器设计.信息与控制,2007,36(6):754-759.)
[16]XIONG Weiqing.Classification rule mining based on binary ant colony optimization algorithm.Pattern Recognition and Artificial Intelligence,2008,21(4):500-505.(熊伟清.基于二元蚁群优化算法的分类规则挖掘.模式识别与人工智能,2008,21(4):500-505.)
[17]WU H,MENDEL J M.Classification of battlefield ground vehicles using acoustic features and fuzzy logic rule-based classifiers.IEEETransactions on Fuzzy Systems,2007,15(1):56-72.
[18]SANZ J A,FERNANDEZ A,BUSTINCE H,et al.Improving the performance of fuzzy rule-based classification systems with intervalvalued fuzzy sets and genetic amplitude tuning.Information Sciences,2010,180(19):3674-3685.
[19]MARATEB H R,GOUDARZI S.A noninvasive method for coronary artery diseases diagnosis using a clinically-interpretable fuzzy rule-based system.Journal of Research in Medical Sciences,2015,20(3):214-223.
[20]SANZ J A,BERNARDO D,HERRERA F,et al.A compact evolutionary interval-valued fuzzy rule-based classification system for the modeling and prediction of real-world financial applications with imbalanced data.IEEE Transactions on Fuzzy Systems,2014,23(4):973-990.
[21]ANTONELLI M,BERNARDO D,HAGRAS H,et al.Multiobjective evolutionary optimization of type-2 fuzzy rule-based systems for financial data classification.IEEE Transactions on Fuzzy Systems,2017,25(2):249-264.
[22]HARANDI F A,DERHAMI V.A reinforcement learning algorithm for adjusting antecedent parameters and weights of fuzzy rules in a fuzzy classifier.Journal of Intelligent&Fuzzy Systems,2016,30(4):2339-2347.
[23]FU Yaping,HUANG Min,WANG Hongfeng.Multipopulation multiobjective genetic algorithm for multiobjective permutation flow shop scheduling problem.Control Theory&Applications,2016,33(10):1281-1288.(付亚平,黄敏,王洪峰,等.面向多目标流水车间调度的多种群多目标遗传算法.控制理论与应用,2016,33(10):1281-1288.)
[24]WANG Chao,WANG Jianhui,GU Shusheng,et al.Improved incremental extreme learning machine based on multi-learning clonal selection algorithm.Control Theory&Applications,2016,33(10):368-379.(王超,王建辉,顾树生,等.基于多层学习克隆选择的改进式增量型超限学习机算法.控制理论与应用,2016,33(10):368-379.)
[25]ZHANG Yuxian,QIAN Xiaoyi,PENG Huideng.Real-coded quantum evolutionary algorithm based on allele.Chinese Journal of Scientific Instrument,2015,36(9):2129-2137.(张宇献,钱小毅,彭辉灯.基于等位基因的实数编码量子进化算法.仪器仪表学报,2015,36(9):2129-2137.)
[26]DOMBI J,GERA Z.Rule based fuzzy classification using squashing functions.Journal of Intelligent&Fuzzy Systems,2008,19(1):3-8.
[27]BACHE K,LICHMAN M.UCI machine learning repository.Irvine,University of California,2007.URL
[28]LIU Wangshu,CHEN Xiang,GU Qing,et al.A Noise tolerable feature selection framework for software defect prediction.Chinese Journal of Computers,2016,39(33):1-16.(刘望舒,陈翔,顾庆,等.一种面向软件缺陷预测的可容忍噪声的特征选择框架.计算机学报,2016,39(33):1-16.)
[29]GARCIA S,FERNANDEZ A,LUENGO J,et al.Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining:experimental analysis of power.Information Sciences,2010,180(10):2044-2064.
[30]I S G,HERRERA F.An extension on statistical comparisons of classifiers over multiple data sets for all pairwise comparisons.Journal of Machine Learning Research,2008,9(12):2677-2694.
[31]MANTAS C J,ABELLAN J,CASTELLANO J G.Analysis of Credal-C4.5 for classification in noisy domains.Expert Systems with Applications,2016,61(11):314-326.
[32]BEREND D,KONTOROVICH A.A finite sample analysis of the Naive Bayes classifier.Journal of Machine Learning Research,2015,16(1):1519-1545.
[33]ZHAO Yanwei,REN Shedong,CHEN Weigang,et al.Extension classifier construction based on improved BP neural network.Computer Integrated Manufacturing Systems,2015,21(10):2807-2815.(赵燕伟,任设东,陈尉刚,等.基于改进BP神经网络的可拓分类器构建.计算机集成制造系统,2015,21(10):2807-2815.)