RapidMiner大數據挖掘應用與案例分析

Big Data Mining Application with RapidMiner and Case Studies

連柏鈞(PO-CHUN LIEN)

指導教授 ： 洪士程

朝陽科技大學/資訊學院/資訊工程系/碩士(2018年)

摘要

近年來由於計算機技術和資訊產業的快速發展，促使了相關的數據量也產 生了極大的增長。然而面對這些龐大且雜亂的多維數據集，我們無法快速 且有效的找到我們所需要的資訊。因此我們必須要使用數據挖掘技術以從 數據集中去提取我們所需要的資料，並且進行分析與處理。在本篇論文中， 我們將介紹一個新的大數據挖掘分析軟體 Rapidminer，並且與其他舊有的 數據挖掘分析軟體來做一個功能性的比較。透過四個案例研究，包括線性 回歸、類神經網路、決策樹和支持向量機，說明應用 Rapidminer 進行大數 據挖掘分析的運作流程，並介紹 Rapidminer 的操作介面跟分析方法。本篇 論文採用 Rapidminer 的原因，主要是因為它擁有非常便捷的圖形化介面， 而且使用者在操作上不需要再額外去學習其它的程式語法，只需要透過選 取元件以及設定參數的方式就可以完成。而且在分析結果的顯示上也非常 的多樣化，可以讓使用者自行選擇要觀看哪一種圖形顯示分析的結果。

關鍵字

Rapidminer ； 大數據挖掘 ； 線性回歸 ； 類神經網路 ； 決策樹 ； 支持向量機

並列摘要

In recent years, the rapid development of computer technology and information industry has led to a significant increase in the amount of data. However, regarding these large and messy multidimensional data sets, we cannot quickly and effectively find the information that we need. Therefore, we have to use the data mining techniques to concentrate on extracting the information that we need from the data. In this thesis, we will introduce a relatively new data mining software, Rapidminer. We compare the Rapidminer with other data mining software via comparative analysis of a functional operating procedures. Through the application of four case studies including linear regression, neural networks, decision trees, and support vector machines to illustrate the operations of Rapidminer. There are two reasons to use Rapidminer in this thesis. The first one is that it has a very convenient graphical interface. The second one is that user does not need to learn other programming syntax, just need to select components and setting parameters. The display of analysis results is also diversification, which allowing users to choose the functional map to view the results.

並列關鍵字

Rapidminer ； Big data mining ； Linear regression ； Neural networks ； Decision trees ； Support vector machines

參考文獻

參考文獻

[1] I-Hsuan Ethan Chiang, W. Keener Hughen, " Do oil futures prices predict stock returns?," Journal of Banking & Finance, June 2017, vol. 79, pp. 129-141.

[2] Peter Braun, Alfredo Cuzzocrea , Carson K. Leung, Adam G.M. Pazdor, Kimberly Tran, "Knowledge Discovery from Social Graph Data," Procedia Computer Science, 2016, vol. 96, pp. 682-691.

[3] T. Denoeux, "A neural network classifier based on Dempster-Shafer theory," IEEE Transactions on System,Man and Cybernetics, vol. 30, pp. 131-150, March 2000.

[4] G. P. Zhang, "Neural Networks for Classification: A Survey," IEEE Transactions on System,Man and Cybernetics, vol. 30, pp. 451-462, Nov. 2000.