Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images

Xiaolong Sun; Juyoung Park; Kyungtae Kang; Junbeom Hur

doi:10.1109/SMC.2017.8122741

Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images

Xiaolong Sun
, Juyoung Park
, Kyungtae Kang^*
, Junbeom Hur

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

31 Citations (Scopus)

Abstract

This paper proposes a novel hybrid model that integrates the synergy of two superior classifiers for functional magnetic resonance imaging (fMRI) recognition, namely, convolutional neural networks (CNNs) and support vector machines (SVMs), both of which have proven results in the field of image recognition. In the proposed model, the CNN functions as a trainable feature extractor and the SVM functions as a recognizer. This hybrid model extracts features from raw images and generates predictions for fMRI recognition. We conducted experiments on Haxby's 2001 fMRI dataset. Comparisons with Haxby's study using the same database indicated that the proposed fusion achieved superior recognition accuracy of 99.5% compared to the Haxby's approach. Further, when the CNN was used as a feature extractor, the SVM classifier was demonstrated to be the best combining counterpart, providing the best synergy effect in terms of accuracy. This is compared with other classifiers based on learning algorithms such as decision tree, neural network, K-nearest neighbor, random forest, and AdaBoost.

Original language	English
Title of host publication	2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1001-1006
Number of pages	6
ISBN (Electronic)	9781538616451
DOIs	https://doi.org/10.1109/SMC.2017.8122741
Publication status	Published - 2017 Nov 27
Event	2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 - Banff, Canada Duration: 2017 Oct 5 → 2017 Oct 8

Publication series

Name	2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
Volume	2017-January

Other

Other	2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
Country/Territory	Canada
City	Banff
Period	17/10/5 → 17/10/8

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

Functional magnetic resonance imaging recognition
Hybrid model
Neural network
Support vector machine

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Human-Computer Interaction
Control and Optimization

Access to Document

10.1109/SMC.2017.8122741

Cite this

Sun, X., Park, J., Kang, K., & Hur, J. (2017). Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images. In 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 (pp. 1001-1006). (2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2017.8122741

Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images. / Sun, Xiaolong; Park, Juyoung; Kang, Kyungtae et al.
2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1001-1006 (2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sun, X, Park, J, Kang, K & Hur, J 2017, Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images. in 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 1001-1006, 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, Banff, Canada, 17/10/5. https://doi.org/10.1109/SMC.2017.8122741

Sun X, Park J, Kang K, Hur J. Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images. In 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1001-1006. (2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017). doi: 10.1109/SMC.2017.8122741

Sun, Xiaolong ; Park, Juyoung ; Kang, Kyungtae et al. / Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images. 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1001-1006 (2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017).

@inproceedings{06af01ac81744e7490d3e21646a156e2,

title = "Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images",

abstract = "This paper proposes a novel hybrid model that integrates the synergy of two superior classifiers for functional magnetic resonance imaging (fMRI) recognition, namely, convolutional neural networks (CNNs) and support vector machines (SVMs), both of which have proven results in the field of image recognition. In the proposed model, the CNN functions as a trainable feature extractor and the SVM functions as a recognizer. This hybrid model extracts features from raw images and generates predictions for fMRI recognition. We conducted experiments on Haxby's 2001 fMRI dataset. Comparisons with Haxby's study using the same database indicated that the proposed fusion achieved superior recognition accuracy of 99.5\% compared to the Haxby's approach. Further, when the CNN was used as a feature extractor, the SVM classifier was demonstrated to be the best combining counterpart, providing the best synergy effect in terms of accuracy. This is compared with other classifiers based on learning algorithms such as decision tree, neural network, K-nearest neighbor, random forest, and AdaBoost.",

keywords = "Functional magnetic resonance imaging recognition, Hybrid model, Neural network, Support vector machine",

author = "Xiaolong Sun and Juyoung Park and Kyungtae Kang and Junbeom Hur",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 ; Conference date: 05-10-2017 Through 08-10-2017",

year = "2017",

month = nov,

day = "27",

doi = "10.1109/SMC.2017.8122741",

language = "English",

series = "2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1001--1006",

booktitle = "2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017",

}

TY - GEN

T1 - Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images

AU - Sun, Xiaolong

AU - Park, Juyoung

AU - Kang, Kyungtae

AU - Hur, Junbeom

PY - 2017/11/27

Y1 - 2017/11/27

N2 - This paper proposes a novel hybrid model that integrates the synergy of two superior classifiers for functional magnetic resonance imaging (fMRI) recognition, namely, convolutional neural networks (CNNs) and support vector machines (SVMs), both of which have proven results in the field of image recognition. In the proposed model, the CNN functions as a trainable feature extractor and the SVM functions as a recognizer. This hybrid model extracts features from raw images and generates predictions for fMRI recognition. We conducted experiments on Haxby's 2001 fMRI dataset. Comparisons with Haxby's study using the same database indicated that the proposed fusion achieved superior recognition accuracy of 99.5% compared to the Haxby's approach. Further, when the CNN was used as a feature extractor, the SVM classifier was demonstrated to be the best combining counterpart, providing the best synergy effect in terms of accuracy. This is compared with other classifiers based on learning algorithms such as decision tree, neural network, K-nearest neighbor, random forest, and AdaBoost.

AB - This paper proposes a novel hybrid model that integrates the synergy of two superior classifiers for functional magnetic resonance imaging (fMRI) recognition, namely, convolutional neural networks (CNNs) and support vector machines (SVMs), both of which have proven results in the field of image recognition. In the proposed model, the CNN functions as a trainable feature extractor and the SVM functions as a recognizer. This hybrid model extracts features from raw images and generates predictions for fMRI recognition. We conducted experiments on Haxby's 2001 fMRI dataset. Comparisons with Haxby's study using the same database indicated that the proposed fusion achieved superior recognition accuracy of 99.5% compared to the Haxby's approach. Further, when the CNN was used as a feature extractor, the SVM classifier was demonstrated to be the best combining counterpart, providing the best synergy effect in terms of accuracy. This is compared with other classifiers based on learning algorithms such as decision tree, neural network, K-nearest neighbor, random forest, and AdaBoost.

KW - Functional magnetic resonance imaging recognition

KW - Hybrid model

KW - Neural network

KW - Support vector machine

UR - https://www.scopus.com/pages/publications/85044142751

U2 - 10.1109/SMC.2017.8122741

DO - 10.1109/SMC.2017.8122741

M3 - Conference contribution

AN - SCOPUS:85044142751

T3 - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017

SP - 1001

EP - 1006

BT - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017

Y2 - 5 October 2017 through 8 October 2017

ER -

Novel hybrid CNN-SVM model for recognition of functional magnetic resonance images

Abstract

Publication series

Other

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this