Spatial and Anatomical Regularization Based on Multiple Kernel Learning for Neuroimaging Classification
Summary :
Recently, a high dimensional classification framework has been proposed to introduce spatial and anatomical priors in classical single kernel support vector machine optimization scheme, wherein the sequential minimal optimization (SMO) training algorithm is adopted, for brain image analysis. However, to satisfy the optimization conditions required in the single kernel case, it is unreasonably assumed that the spatial regularization parameter is equal to the anatomical one. In this letter, this approach is improved by combining SMO algorithm with multiple kernel learning to avoid that assumption and optimally estimate two parameters. The improvement is comparably demonstrated by experimental results on classification of Alzheimer patients and elderly controls.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.4 pp.1272-1274
- Publication Date
- 2016/04/01
- Publicized
- 2016/01/13
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2015EDL8163
- Type of Manuscript
- LETTER
- Category
- Biological Engineering
Authors
YingJiang WU
Guizhou University,Guangdong Medical University
BenYong LIU
Guizhou University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
YingJiang WU, BenYong LIU, "Spatial and Anatomical Regularization Based on Multiple Kernel Learning for Neuroimaging Classification" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 4, pp. 1272-1274, April 2016, doi: 10.1587/transinf.2015EDL8163.
Abstract: Recently, a high dimensional classification framework has been proposed to introduce spatial and anatomical priors in classical single kernel support vector machine optimization scheme, wherein the sequential minimal optimization (SMO) training algorithm is adopted, for brain image analysis. However, to satisfy the optimization conditions required in the single kernel case, it is unreasonably assumed that the spatial regularization parameter is equal to the anatomical one. In this letter, this approach is improved by combining SMO algorithm with multiple kernel learning to avoid that assumption and optimally estimate two parameters. The improvement is comparably demonstrated by experimental results on classification of Alzheimer patients and elderly controls.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8163/_p
Copy
@ARTICLE{e99-d_4_1272,
author={YingJiang WU, BenYong LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Spatial and Anatomical Regularization Based on Multiple Kernel Learning for Neuroimaging Classification},
year={2016},
volume={E99-D},
number={4},
pages={1272-1274},
abstract={Recently, a high dimensional classification framework has been proposed to introduce spatial and anatomical priors in classical single kernel support vector machine optimization scheme, wherein the sequential minimal optimization (SMO) training algorithm is adopted, for brain image analysis. However, to satisfy the optimization conditions required in the single kernel case, it is unreasonably assumed that the spatial regularization parameter is equal to the anatomical one. In this letter, this approach is improved by combining SMO algorithm with multiple kernel learning to avoid that assumption and optimally estimate two parameters. The improvement is comparably demonstrated by experimental results on classification of Alzheimer patients and elderly controls.},
keywords={},
doi={10.1587/transinf.2015EDL8163},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Spatial and Anatomical Regularization Based on Multiple Kernel Learning for Neuroimaging Classification
T2 - IEICE TRANSACTIONS on Information
SP - 1272
EP - 1274
AU - YingJiang WU
AU - BenYong LIU
PY - 2016
DO - 10.1587/transinf.2015EDL8163
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2016
AB - Recently, a high dimensional classification framework has been proposed to introduce spatial and anatomical priors in classical single kernel support vector machine optimization scheme, wherein the sequential minimal optimization (SMO) training algorithm is adopted, for brain image analysis. However, to satisfy the optimization conditions required in the single kernel case, it is unreasonably assumed that the spatial regularization parameter is equal to the anatomical one. In this letter, this approach is improved by combining SMO algorithm with multiple kernel learning to avoid that assumption and optimally estimate two parameters. The improvement is comparably demonstrated by experimental results on classification of Alzheimer patients and elderly controls.
ER -
English
