A New Algorithm for Classification Based on Multi-classifiers Learning
Quality and quantity are the two key factors to influence the accuracy of classification. In order to improve the classification accuracy, in this paper, we propose a new algorithm, called CMCM (Classification based on Multiple Classifier Models), which consists of two classification models. In Model1, we mainly focus on the improvement of quality, thus the best attribute value from both the items and their complements in the training set is selected as the first item of a classification rule. While in Model2, quantity is taken into consideration, so it constructs two candidate sets and uses the one-versus-many strategy to generate several rules at one time. The experiment results show that: (1) Model1 can extract sufficient high quality rules and achieve high classification accuracy. (2) Model2 can extract sufficient information and achieve high classification accuracy. (3) CMCM can achieve higher classification accuracy compare with traditional classification.
KeywordsData mining Classification Ensemble learning Classification rule
This work is supported by Natural Science Funds of China (Nos. 61701213), Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry, the Program for Excellent Talents of Fujian Province, the Special Research Fund for Higher Education of Fujian (No. JK2015027), and the Research Fund for Educational Department of Fujian Province (No. JA15300).
- 2.Veloso, A., Meira Jr., W., Zaki, M.J.: Lazy associative classification. In: ICDM 2006, pp. 645–654 (2006)Google Scholar
- 4.Brin, S., Motwani, R., Silverstein, C.: Beyond market: generalizing association rules to correlations. In: SIGMOD 1997, pp. 265–276 (1997)Google Scholar
- 5.Liu, B., Hsu, W., Ma, Y.: Integrating classification and association rule mining. In: KDD 1998, pp. 80–86 (1998)Google Scholar
- 10.Li, W., Han, J., Pei, J.: CMAR: accurate and efficient classification based on multiple class-association rules. In: ICDM 2001, pp. 369–376 (2001)Google Scholar
- 11.Zheng, Y., Huang, Z., He, T.: Classification based on both attribute value weight and tuple weight under the cloud computing. Math. Prob. Eng. 2013(2013), 1–7 (2013)Google Scholar
- 12.Zhou, Z.H.: Ensemble Methods: Foundations and Algorithms, p. 2012. CRC, Boca Raton (2012)Google Scholar