Evaluating learning algorithms to support human rule evaluation based on objective rule evaluation indices

被引：0
作者：
Abe, H. [1 ]
Tsumoto, S. [1 ]
Ohsaki, M. [2 ]
Yamaguchi, T. [3 ]
机构：
[1] Dept. of Medical Informatics, Shimane University, School of Medicine, Izumo Shimane, 6938501
[2] Faculty of Engineering, Doshisha University, Kyo-Tanabe Kyoto, 6100321
[3] Faculty of Science and Technology, Keio University, Kohoku-ku Yokohama Kanagawa, 2238522
来源：
Data Science Journal | 2007年 / 6卷 / SUPPL.期
关键词：
Data mining; Objective rule evaluation index; Post-processing; Rule evaluation support;
D O I：
10.2481/dsj.6.S285
中图分类号：
学科分类号：
摘要：
In this paper, we present an evaluation of learning algorithms of a novel rule evaluation support method for post-processing of mined results with rule evaluation models based on objective indices. Post-processing of mined results is one of the key processes in a data mining process. However, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset with noise. To reduce the costs in such rule evaluation task, we have developed a rule evaluation support method with rule evaluation models that learn from a dataset. This dataset comprises objective indices for mined classification rules and evaluation by a human expert for each rule. To evaluate performances of learning algorithms for constructing the rule evaluation models, we have done a case study on the meningitis data mining as an actual problem. Furthermore, we have also evaluated our method with ten rule sets obtained from ten UCI datasets. With regard to these results, we show the availability of our rule evaluation support method for human experts.
引用
收藏
页码：S285 / S296
页数：11
相关论文
共 21 条
  • [1] Ali K., Manganaris S., Srikant R., Partial Classification Using Association Rules, Proc. of Int. Conf. on Knowledge Discovery and Data Mining KDD-1997, pp. 115-118, (1997)
  • [2] Brin S., Motwani R., Ullman J., Tsur S., Dynamic itemset counting and implication rules for market basket data, Proc. of ACM SIGMOD Int. Conf. on Management of Data, pp. 255-264, (1997)
  • [3] Frank E., Wang Y., Inglis S., Holmes G., Witten I.H., Using model trees for classification, Machine Learning, 32, 1, pp. 63-76, (1998)
  • [4] Frank E., Witten I.H., Generating accurate rule sets without global optimization, Proc. of the Fifteenth International Conference on Machine Learning, pp. 144-151, (1998)
  • [5] Gago P., Bento C., A Metric for Selection of the Most Promising Rules, Proc. of Euro. Conf. on the Principles of Data Mining and Knowledge Discovery PKDD-1998, pp. 19-27, (1998)
  • [6] Goodman L.A., Kruskal W.H., Measures of association for cross classifications, Springer Series in Statistics, 1, (1979)
  • [7] Gray B., Orlowska M.E., CCAIIA: Clustering Categorical Attributes into Interesting Association Rules, Proc. of Pacific-Asia Conf. on Knowledge Discovery and Data Mining PAKDD-1998, pp. 132-143, (1998)
  • [8] Hamilton H.J., Shan N., Ziarko W., Machine Learning of Credible Classifications, Proc. of Australian Conf. on Artificial Intelligence AI-1997, pp. 330-339, (1997)
  • [9] Hatazawa H., Negishi N., Suyama A., Tsumoto S., Yamaguchi T., Knowledge Discovery Support from a Meningoencephalitis Database Using an Automatic Composition Tool for Inductive Applications, Proc. of KDD Challenge 2000 in conjunction with PAKDD2000, pp. 28-33, (2000)
  • [10] Hettich S., Blake C.L., Merz C.J., UCI Repository of machine learning databases, (1998)
123