Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 강경태 | - |
dc.date.accessioned | 2019-05-09T07:20:43Z | - |
dc.date.available | 2019-05-09T07:20:43Z | - |
dc.date.issued | 2017-10 | - |
dc.identifier.citation | 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Page. 1001-1006 | en_US |
dc.identifier.isbn | 978-1-5386-1645-1 | - |
dc.identifier.isbn | 978-1-5386-1646-8 | - |
dc.identifier.uri | https://ieeexplore.ieee.org/document/8122741/ | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/103690 | - |
dc.description.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. | en_US |
dc.description.sponsorship | This work was supported in party by the IITP (Institute for Information & Communications Technology Promotion) grant funded by the Korean government (MSIT) (2014-0-00065, Resilient Cyber-Physical Systems Research) and in part by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2016R1A2A2A05005402). (Corresponding author: K. Kang; J. Hur) | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | en_US |
dc.subject | hybrid model | en_US |
dc.subject | support vector machine | en_US |
dc.subject | neural network | en_US |
dc.subject | functional magnetic resonance imaging recognition | en_US |
dc.title | Novel Hybrid CNN-SVM Model for Recognition of Functional Magnetic Resonance Images | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1109/SMC.2017.8122741 | - |
dc.relation.page | 1001-1006 | - |
dc.contributor.googleauthor | Sun, iaolong | - |
dc.contributor.googleauthor | Park, Juyoung | - |
dc.contributor.googleauthor | Kang, Kyungtae | - |
dc.contributor.googleauthor | Hur, Junbeom | - |
dc.relation.code | 20170148 | - |
dc.sector.campus | E | - |
dc.sector.daehak | COLLEGE OF COMPUTING[E] | - |
dc.sector.department | DIVISION OF COMPUTER SCIENCE | - |
dc.identifier.pid | ktkang | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.