Intelligent data mining systems by generalized multiple kernel machines on graph based subspace

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Mining high-dimensional business data is a challenging problem. This paper proposes a novel approach to address the problems including (1) the curse of dimensionality and (2) the meaningfulness of the similarity measure in the high dimension space. The solution of this study is to build a generalized multiple kernel machine (GMKM) on a low-dimensional subspace. The representative subspace is created by the locally consistent matrix factorization (an improved variation of non-negative matrix factorization). The strengths of our system are two-fold: (1) GMKM takes products of kernels-corresponding to a tensor product of feature spaces. This leads to a richer and much higher dimensional feature representation, which is powerful in identifying relevant features and their apposite kernel representation. (2) Locally consistent matrix factorization finds a compact low-dimensional representation for data, which uncovers underlying information and simultaneously respects the intrinsic geometric structure of data manifold. Our system robustly outperforms traditional multiple kernel machines, and dimensionality reduction methods.

Original languageEnglish
Title of host publicationProceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages120-125
Number of pages6
ISBN (Electronic)9781467373364
DOIs
Publication statusPublished - 2015 Sep 23
Event7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and the 7th IEEE International Conference on Robotics, Automation and Mechatronics, RAM 2015 - Siem Reap, Cambodia
Duration: 2015 Jul 152015 Jul 17

Publication series

NameProceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015

Other

Other7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and the 7th IEEE International Conference on Robotics, Automation and Mechatronics, RAM 2015
CountryCambodia
CitySiem Reap
Period15-07-1515-07-17

Fingerprint

Factorization
Data mining
Tensors
Industry

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Huang, S-C., & Wu, T-K. (2015). Intelligent data mining systems by generalized multiple kernel machines on graph based subspace. In Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015 (pp. 120-125). [7274559] (Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCIS.2015.7274559
Huang, Shian-Chang ; Wu, Tung-Kuang. / Intelligent data mining systems by generalized multiple kernel machines on graph based subspace. Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 120-125 (Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015).
@inproceedings{dadca72f29a54b4f88255ebc336a6fab,
title = "Intelligent data mining systems by generalized multiple kernel machines on graph based subspace",
abstract = "Mining high-dimensional business data is a challenging problem. This paper proposes a novel approach to address the problems including (1) the curse of dimensionality and (2) the meaningfulness of the similarity measure in the high dimension space. The solution of this study is to build a generalized multiple kernel machine (GMKM) on a low-dimensional subspace. The representative subspace is created by the locally consistent matrix factorization (an improved variation of non-negative matrix factorization). The strengths of our system are two-fold: (1) GMKM takes products of kernels-corresponding to a tensor product of feature spaces. This leads to a richer and much higher dimensional feature representation, which is powerful in identifying relevant features and their apposite kernel representation. (2) Locally consistent matrix factorization finds a compact low-dimensional representation for data, which uncovers underlying information and simultaneously respects the intrinsic geometric structure of data manifold. Our system robustly outperforms traditional multiple kernel machines, and dimensionality reduction methods.",
author = "Shian-Chang Huang and Tung-Kuang Wu",
year = "2015",
month = "9",
day = "23",
doi = "10.1109/ICCIS.2015.7274559",
language = "English",
series = "Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "120--125",
booktitle = "Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015",
address = "United States",

}

Huang, S-C & Wu, T-K 2015, Intelligent data mining systems by generalized multiple kernel machines on graph based subspace. in Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015., 7274559, Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015, Institute of Electrical and Electronics Engineers Inc., pp. 120-125, 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and the 7th IEEE International Conference on Robotics, Automation and Mechatronics, RAM 2015, Siem Reap, Cambodia, 15-07-15. https://doi.org/10.1109/ICCIS.2015.7274559

Intelligent data mining systems by generalized multiple kernel machines on graph based subspace. / Huang, Shian-Chang; Wu, Tung-Kuang.

Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 120-125 7274559 (Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Intelligent data mining systems by generalized multiple kernel machines on graph based subspace

AU - Huang, Shian-Chang

AU - Wu, Tung-Kuang

PY - 2015/9/23

Y1 - 2015/9/23

N2 - Mining high-dimensional business data is a challenging problem. This paper proposes a novel approach to address the problems including (1) the curse of dimensionality and (2) the meaningfulness of the similarity measure in the high dimension space. The solution of this study is to build a generalized multiple kernel machine (GMKM) on a low-dimensional subspace. The representative subspace is created by the locally consistent matrix factorization (an improved variation of non-negative matrix factorization). The strengths of our system are two-fold: (1) GMKM takes products of kernels-corresponding to a tensor product of feature spaces. This leads to a richer and much higher dimensional feature representation, which is powerful in identifying relevant features and their apposite kernel representation. (2) Locally consistent matrix factorization finds a compact low-dimensional representation for data, which uncovers underlying information and simultaneously respects the intrinsic geometric structure of data manifold. Our system robustly outperforms traditional multiple kernel machines, and dimensionality reduction methods.

AB - Mining high-dimensional business data is a challenging problem. This paper proposes a novel approach to address the problems including (1) the curse of dimensionality and (2) the meaningfulness of the similarity measure in the high dimension space. The solution of this study is to build a generalized multiple kernel machine (GMKM) on a low-dimensional subspace. The representative subspace is created by the locally consistent matrix factorization (an improved variation of non-negative matrix factorization). The strengths of our system are two-fold: (1) GMKM takes products of kernels-corresponding to a tensor product of feature spaces. This leads to a richer and much higher dimensional feature representation, which is powerful in identifying relevant features and their apposite kernel representation. (2) Locally consistent matrix factorization finds a compact low-dimensional representation for data, which uncovers underlying information and simultaneously respects the intrinsic geometric structure of data manifold. Our system robustly outperforms traditional multiple kernel machines, and dimensionality reduction methods.

UR - http://www.scopus.com/inward/record.url?scp=84960877801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960877801&partnerID=8YFLogxK

U2 - 10.1109/ICCIS.2015.7274559

DO - 10.1109/ICCIS.2015.7274559

M3 - Conference contribution

T3 - Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015

SP - 120

EP - 125

BT - Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Huang S-C, Wu T-K. Intelligent data mining systems by generalized multiple kernel machines on graph based subspace. In Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 120-125. 7274559. (Proceedings of the 2015 7th IEEE International Conference on Cybernetics and Intelligent Systems, CIS 2015 and Robotics, Automation and Mechatronics, RAM 2015). https://doi.org/10.1109/ICCIS.2015.7274559