政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/146306

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/146306

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | 全文笔数/总笔数 : 114205/145239 (79%)
造访人次 : 52610487 在线人数 : 759

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

搜寻范围

查询小技巧：

您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果

若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据

进阶搜寻

主页 ‧ 登入 ‧ 上传 ‧ 说明 ‧ 关于政大典藏 ‧ 管理

到手机版

政大機構典藏 > 商學院 > 統計學系 > 學位論文 > Item 140.119/146306

请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/146306

题名:	基於K-Means和因素森林的特徵選取法 Feature Selection Using Factor-Forest and K-Means
作者:	陳劭晏 Chen, Shao-Yan
贡献者:	周珮婷張育瑋 Elizabeth Chou Yu-Wei Chang 陳劭晏 Chen, Shao-Yan
关键词:	特徵選取維度縮減集群分析 Feature selection Dimension reduction Clustering Factor-Forest-K-Means
日期:	2023
上传时间:	2023-08-02 13:04:02 (UTC+8)
摘要:	在資料分析的流程中，特徵選取是至關重要的步驟，可以用來從龐大而複雜的資料中篩選出重要的特徵。近年來，許多研究顯示K-Means 演算法不僅能用於進行特徵選取，更可以提升機器學習模型性能，它能夠找出使模型表現有所提升的變數子集。此外，Goretzko & Bühner (2020) 提出了一種名為因素森林 (Factor Forest) 的方法，可用於確定資料中潛在因子的適當數量。在本研究中，我們將提出一種全新的特徵選擇方法，Factor-Forest-K-Means（FFKM），該方法採用 Factor-Forest 作為指標，並透過 K-Means 來篩選變數。它不僅能夠將資料的維度減少約 90%，還能維持模型的準確率。FFKM 具備簡單易使用的特性，並且在本研究中的實驗中整體表現優於其他指標方法和模型，並在其選出的特徵子集上擁有最佳的準確度保留率 (accuracy retention)、降維幅度百分比 (reduction percentage) 和變數準確度保留比例 (Accuracy Retention per Variables)。實驗結果顯示，FFKM 是一種良好的維度縮減方法，能夠在大幅度降低維度的情況下，提升機器學習模型的性能。 Feature selection is a critical step in data analysis to identify important variables from a large number of complex data. Many recent studies have demonstrated that K-Means can be utilized to find a subset of variables that enhances the performance of machine learning models. Another method, Factor Forest (Goretzko & Bühner, 2020), has also been proposed to determine the appropriate number of latent factors in data. In this research, we introduce a new feature selection method using K-Means clustering, called Factor-Forest-K-Means (FFKM), which not only reduces the dimensionality by approximately 90%, but also preserves the predictive accuracy of the original model. The FFKM method is easy to implement and outperforms other index methods and models tested in this study, with the highest accuracy retention, reduction percentage and accuracy retention per variable selected among all methods in different settings. Our results show that FFKM is a promising feature reduction method and can enhance machine learning models’ performance.
參考文獻:	Braeken, J., & Van Assen, M. A. (2017). An empirical kaiser criterion. Psychological methods, 22(3), 450. Breiman, L. (2001). Random forests. Machine learning, 45, 5–32. Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785–794). Gini, C. (1921). Measurement of inequality of incomes. The economic journal, 31(121),124–125. Goretzko, D., & Bühner, M. (2020). One model to rule them all? using machine learning algorithms to determine the number of factors in exploratory factor analysis. Psychological Methods, 25(6), 776. Goretzko, D., & Bühner, M. (2022). Factor retention using machine learning with ordinal data. Applied Psychological Measurement, 46(5), 406–421. Hartigan, J. (1975). Clustering algorithms. Wiley. Retrieved from https://books.google.com.tw/books?id=cDnvAAAAMAAJ Horn, J. L. (1965). A rationale and test for the number of factors in factor analysis. Psychometrika, 30, 179–185. Kaiser, H. F. (1960). The application of electronic computers to factor analysis. Educational and psychological measurement, 20(1), 141–151. Khaleel, S. (2011). Feature selection using k-means clustering for data mining. Liaw, A., & Wiener, M. (2002). Classification and regression by randomforest. R News, 2(3), 18-22. Retrieved from https://CRAN.R-project.org/doc/Rnews/ Lloyd, S. (1957). Least square quantization in pcm. bell telephone laboratories paper. published in journal much later: Lloyd, sp: Least squares quantization in pcm. IEEE Trans. Inform. Theor.(1957/1982), 18(11). MacQueen, J. (1967). Classification and analysis of multivariate observations. In 5th berkeley symp. math. statist. probability (pp. 281–297). Parida, K., Mandal, S., Das, S., & Tripathy, A. (2011). Feature extraction using k-means clustering: An approach implementation. Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20, 53–65. Ruscio, J., & Roche, B. (2012). Determining the number of factors to retain in an exploratory factor analysis using comparison data of known factorial structure. Psychological assessment, 24(2), 282. Tang, X., Dong, M., Bi, S., Pei, M., Cao, D., Xie, C., & Chi, S. (2017). Feature selection algorithm based on k-means clustering. In 2017 ieee 7th annual international conference on cyber technology in automation, control, and intelligent systems (cyber) (pp. 1522–1527). Thomas, J., Coors, S., & Bischl, B. (2018). Automatic gradient boosting. arXiv preprint arXiv:1807.03873. Thorndike, R. (1953). Who belongs in the family? Psychometrika, 18(4), 267–276.
描述:	碩士國立政治大學統計學系 110354012
資料來源:	http://thesis.lib.nccu.edu.tw/record/#G0110354012
数据类型:	thesis
显示于类别:	[統計學系] 學位論文

文件中的档案:

档案	描述	大小	格式	浏览次数
401201.pdf		450Kb	Adobe PDF2	0	检视/开启

在政大典藏中所有的数据项都受到原著作权保护.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - 回馈