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

Xiaolong Sun, Juyoung Park, Kyungtae Kang, Junbeom Hur

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

3 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 languageEnglish
Title of host publication2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1001-1006
Number of pages6
ISBN (Electronic)9781538616451
DOIs
Publication statusPublished - 2017 Nov 27
Event2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 - Banff, Canada
Duration: 2017 Oct 52017 Oct 8

Publication series

Name2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
Volume2017-January

Other

Other2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
CountryCanada
CityBanff
Period17/10/517/10/8

Fingerprint

Magnetic Resonance Image
Magnetic resonance
Support vector machines
Functional Magnetic Resonance Imaging
Support Vector Machine
Neural Networks
Neural networks
Extractor
Classifiers
Classifier
Synergy
Hybrid Model
Adaptive boosting
Image recognition
Image Recognition
Random Forest
AdaBoost
Decision trees
Decision tree
Model

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

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; Hur, Junbeom.

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 proceedingConference 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). https://doi.org/10.1109/SMC.2017.8122741
Sun, Xiaolong ; Park, Juyoung ; Kang, Kyungtae ; Hur, Junbeom. / 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",
year = "2017",
month = "11",
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 - http://www.scopus.com/inward/record.url?scp=85044142751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044142751&partnerID=8YFLogxK

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.

ER -