請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69545
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳素雲 | |
dc.contributor.author | Chih-Han Shih | en |
dc.contributor.author | 施智涵 | zh_TW |
dc.date.accessioned | 2021-06-17T03:18:50Z | - |
dc.date.available | 2018-07-02 | |
dc.date.copyright | 2018-07-02 | |
dc.date.issued | 2017 | |
dc.date.submitted | 2018-06-27 | |
dc.identifier.citation | [1] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7):711–720, 1997.
[2] L.-F. Chen, H.-Y. M. Liao, M.-T. Ko, J.-C. Lin, and G.-J. Yu. A new lda-based face recognition system which can solve the small sample size problem. Pattern Recogni- tion, 33(10):1713–1726, 2000. [3] K. Fukunaga. Introduction to Statistical Pattern Recognition. Academic press, 2013. [4] L. Li, R. D. Cook, and C.-L. Tsai. Partial inverse regression. Biometrika, pages 615–625, 2007. [5] J. Ye and T. Xiong. Computational and theoretical analysis of null space and orthogo- nal linear discriminant analysis. Journal of Machine Learning Research, 7(Jul):1183– 1204, 2006. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69545 | - |
dc.description.abstract | Fisher線性判別分析常用於處理分類問題,然而在高維度低樣本數的框架下,類別內的樣本共變異矩陣常常是非滿秩矩陣,導致傳統的Fisher線性判別分析無法實行。在過去文獻中有許多方法處理這個難題,像是主成份分析-線性判別分析、零空間-線性判別分析、特徵值稀疏性-線性判別分析、脊-線性判別分析。在這篇論文中,我們針對不同的方法所求出的分類方向的估計進行穩定性分析。 | zh_TW |
dc.description.abstract | Fisher linear discriminant analysis (LDA) is commonly used in classification problems. However, in high dimension low sample size (HDLSS) scenarios, the within-class sample covariance matrix is often singular, which leads to the failure of LDA. Several discriminant methods were developed in literature to deal with this difficulty, such as PCA-LDA, Null-space LDA, Eigen-sparsity based LDA and Ridge LDA. In this thesis, we analyze the stability for various regularized estimators of discriminant direction derived from different methods. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T03:18:50Z (GMT). No. of bitstreams: 1 ntu-106-R04246007-1.pdf: 646431 bytes, checksum: 148da9e493ab5bf5c243dda6d8e11e05 (MD5) Previous issue date: 2017 | en |
dc.description.tableofcontents | 口試委員會審定書 iii
誌謝 v 摘要 vii Abstract ix 1 Introduction 1 2 Literature review 3 2.1 PCA-LDA.................................. 4 2.2 Null-spaceLDA............................... 5 2.3 Ridge LDA ................................. 5 2.4 Eigen-sparsity based LDA ......................... 6 3 Main results: stability analysis 7 4 Discussion 17 4.1 Unbiasedness condition of discriminant direction . . . . . . . . . . . . . 17 4.2 Stability analysis .............................. 18 4.3 Stability analysis under spike model assumption . . . . . . . . . . . . . . 21 4.4 Futurework................................. 24 5 appendix 25 5.1 Derivatives of eigenvalues and eigenvectors . . . . . . . . . . . . . . . . 25 5.2 Asymptotic normality of sample covariance matrix . . . . . . . . . . . . 25 5.3 Kronecker product and commutation matrix . . . . . . . . . . . . . . . . 25 Bibliography . . . . . . . . . . . . . . . . 27 | |
dc.language.iso | en | |
dc.title | 正規化線性判別分析之穩定性分析 | zh_TW |
dc.title | Stability Analysis of Regularized Linear Discriminant Analysis | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 陳宏 | |
dc.contributor.oralexamcommittee | 陳定立,洪弘 | |
dc.subject.keyword | 線性判別分析,非滿秩,主成份分析,特徵值稀疏性,穩定性分析, | zh_TW |
dc.subject.keyword | Linear discriminant analysis,HDLSS,PCA,Eigen-sparsity,Ridge LDA, | en |
dc.relation.page | 27 | |
dc.identifier.doi | 10.6342/NTU201801133 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2018-06-28 | |
dc.contributor.author-college | 理學院 | zh_TW |
dc.contributor.author-dept | 應用數學科學研究所 | zh_TW |
顯示於系所單位: | 應用數學科學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-106-1.pdf 目前未授權公開取用 | 631.28 kB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。