運用混合式進化演算法於法則探勘之回應模型

Using a hybrid meta-evolutionary rule mining approach as a response model

曹惠鈴(Huei-Ling Tsao)

國立虎尾科技大學/管理學院/資訊管理研究所/碩士(2007年)

https://doi.org/10.6827/NFU.2007.00014

摘要

資料探勘乃經常被用來發掘資料庫中新知識的方法及工具。本研究提出一混合式進化演算法在分類問題上去評量數值樣本並同時萃取包含預測變數，相對應的不等式及門檻值之分類法則，來建立最高預測準確率之決策模型。傳統的統計模型及統計相關技術如邏輯迴歸及複迴歸常被拿來使用，但現實生活的問題經常是高度非線性，很難使用統計方法去發展出一套包含所有獨立變數模型。近年來具非線性及複雜度之機器學習方法如：類神經網路及支援向量機已經被證明比傳統的統計方法更具可靠，儘管文獻中顯示出類神經網路及支援向量機的好處，但大多數的障礙在於建立及所使用的分類法則難以被理解。本研究和文獻中各種方法及商業軟體比較結果，實驗數據顯示此法則探勘分類方法是較能增加預測的準確度以及模型更具簡明性，本研究所提方法所萃取的分類法則可以建立類似專家系統之預測或分類問題的模型。

並列摘要

Data mining usually means the methodologies and tools for the efficient new knowledge discovery from databases. Based on the data mining techniques, a response model can be built as a decision model for prediction or classification of a domain problem potential like expert systems. In this paper, a hybrid meta-evolutionary rule mining based approach to assess nu-merical data pattern in the classification problem is proposed for extracting the decision rules including the predictors, the corresponding inequality and parameter values simultaneously so as to building a decision-making model with maximum prediction accuracy. Conventional statistical methods and statistical related techniques include logistic regression and multi-normal regressions were used. As the real world problems are highly nonlinear in na-ture, they are hard to develop a comprehensive model taking into account all the independent variables using the these statistical approaches. Recently, nonlinear and complex machine learning approaches such as neural networks (NNs) and support vector machines (SVMs) have been demonstrated to be with more reliable than the conventional statistical approaches. Although the usefulness of using NNs/SVMs has been reported in literatures, the most obsta-cles is in the building and using the model in which the classification rules are hard to be re-alized. We compared our results against the other methods in literature, and we show ex-perimentally that the proposed rule extraction approach is promising for improving prediction accuracy and enhancing the modeling simplicity. In particular, the extracting rules by using the proposed approach can be developed as a computer model for prediction or classification problem like expert systems.

參考文獻

[1] Inmon, W. H., "The data warehouse and data mining", Communications of the ACM,39(11), pp. 49-50, 1996.

[2] Mitra, S., Pal, S. K., and Mitra, P., "Data mining in soft computing framework: a survey",

IEEE Transactions on Neural Networks, 13(1), pp. 3-14, 2002.

time prediction with a data-mining approach", Semiconductor Manufacturing,

IEEE Transactions on, 19(2), pp. 252-258, 2006.