Nonnegative Compression for Semi-Nonnegative Independent Component Analysis

被引：3

作者：

Wang, Lu ^{[1
,2
,4
]}

Kachenoura, Amar ^{[1
,2
,4
]}

Albera, Laurent ^{[1
,2
,4
,5
]}

Karfoul, Ahmad ^{[6
]}

Shu, Hua Zhong ^{[3
,4
]}

Senhadji, Lotti ^{[1
,2
,4
]}

机构：

[1] INSERM, UMR 1099, F-35000 Rennes, France

[2] Univ Rennes 1, LTSl, F-35000 Rennes, France

[3] Southeast Univ, LIST, Nanjing 210096, Jiangsu, Peoples R China

[4] Ctr Rech Informat Biomed Sinofranrcais CRIBs, Rennes, France

[5] Ctr Inria Rennes Bretagne Atlantique, INRIA, F-35042 Rennes, France

[6] AL Baath Univ, Mech & Elect Engn, Homs, Syria

来源：

2014 IEEE 8TH SENSOR ARRAY AND MULTICHANNEL SIGNAL PROCESSING WORKSHOP (SAM) | 2014年

关键词：

D O I：

10.1109/SAM.2014.6882343

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In many Independent Component Analysis (ICA) problems the mixing matrix is nonnegative while the sources are unconstrained, giving rise to what we call hereafter the Semi-Nonnegative ICA (SN-ICA) problems. Exploiting the nonnegativity property can improve the ICA result. Besides, in some practical applications, the dimension of the observation space must be reduced. However, the classical dimension compression procedure, such as prewhitening, breaks the nonnegativity property of the compressed mixing matrix. In this paper, we introduce a new nonnegative compression method, which guarantees the nonnegativity of the compressed mixing matrix. Simulation results show its fast convergence property. An illustration of Blind Source Separation (BSS) of Magnetic Resonance Spectroscopy (MRS) data confirms the validity of the proposed method.

引用

页码：81 / 84

页数：4

共 50 条

[1] Semi-nonnegative Independent Component Analysis: The (3,4)-SENICAexp Method
Coloigner, Julie
Albera, Laurent
Karfoul, Ahmad
Kachenoura, Amar
Comon, Pierre
Senhadji, Lotfi
LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION, 2010, 6365 : 612 - +
[2] Semi-nonnegative joint diagonalization by congruence and semi-nonnegative ICA
Coloigner, Julie
Albera, Laurent
Kachenoura, Amar
Noury, Fanny
Senhadji, Lotfi
SIGNAL PROCESSING, 2014, 105 : 185 - 197
[3] Convex and Semi-Nonnegative Matrix Factorizations
Ding, Chris
Li, Tao
Jordan, Michael I.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (01) : 45 - 55
[4] Tight Semi-nonnegative Matrix Factorization
David W. Dreisigmeyer
Pattern Recognition and Image Analysis, 2020, 30 : 632 - 637
[5] Tight Semi-nonnegative Matrix Factorization
Dreisigmeyer, David W.
PATTERN RECOGNITION AND IMAGE ANALYSIS, 2020, 30 (04) : 632 - 637
[6] Conditions for nonnegative independent component analysis
Plumbley, M
IEEE SIGNAL PROCESSING LETTERS, 2002, 9 (06) : 177 - 180
[7] Algorithms for nonnegative independent component analysis
Plumbley, MD
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (03): : 534 - 543
[8] EXACT AND HEURISTIC ALGORITHMS FOR SEMI-NONNEGATIVE MATRIX FACTORIZATION
Gillis, Nicolas
Kumar, Abhishek
SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2015, 36 (04) : 1404 - 1424
[9] EFFICIENT INITIALIZATION FOR NONNEGATIVE MATRIX FACTORIZATION BASED ON NONNEGATIVE INDEPENDENT COMPONENT ANALYSIS
Kitamura, Daichi
Ono, Nobutaka
2016 IEEE INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), 2016,
[10] Distribution Preserving Deep Semi-Nonnegative Matrix Factorization
Tan, Zhuolin
Qin, Anyong
Sun, Yongqing
Tang, Yuan Yan
2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2021, : 1081 - 1086

← 1 2 3 4 5 →