A wavelet deep belief network-based classifier for medical images

Khatami, Amin, Khosravi, Abbas, Lim, Chee Peng and Nahavandi, Saeid 2016, A wavelet deep belief network-based classifier for medical images, in ICONIP 2016: Proceedings of the 23rd International Conference on Neural Information Processing, Springer, Cham, Switzerland, pp. 467-474, doi: 10.1007/978-3-319-46675-0_51.

Attached Files
Name Description MIMEType Size Downloads

Title A wavelet deep belief network-based classifier for medical images
Author(s) Khatami, Amin
Khosravi, AbbasORCID iD for Khosravi, Abbas orcid.org/0000-0001-6927-0744
Lim, Chee PengORCID iD for Lim, Chee Peng orcid.org/0000-0003-4191-9083
Nahavandi, SaeidORCID iD for Nahavandi, Saeid orcid.org/0000-0002-0360-5270
Conference name Neural Information Processing. International Conference (23rd : 2016 : Kyoto, Japan)
Conference location Kyoto, Japan
Conference dates 16-21 Oct. 2016
Title of proceedings ICONIP 2016: Proceedings of the 23rd International Conference on Neural Information Processing
Publication date 2016
Series Lecture Notes in Computer Science
Start page 467
End page 474
Total pages 8
Publisher Springer
Place of publication Cham, Switzerland
Keyword(s) Science & Technology
Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Computer Science
Deep belief network
Wavelet transforms
Summary Accurately and quickly classifying high dimensional data using machine learning and data mining techniques is problematic and challenging. This paper proposes an efficient and effective technique to properly extract high level features from medical images using a deep network and precisely classify them using support vector machine. A wavelet filter is applied at the first step of the proposed method to obtain the informative coefficient matrix of each image and to reduce dimensionality of feature space. A four-layer deep belief network is also utilized to extract high level features. These features are then fed to a support vector machine to perform accurate classification. Comparative empirical results demonstrate the strength, precision, and fast-response of the proposed technique.
ISBN 9783319466743
ISSN 0302-9743
Language eng
DOI 10.1007/978-3-319-46675-0_51
Field of Research 08 Information And Computing Sciences
Socio Economic Objective 0 Not Applicable
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2016, Springer International Publishing AG
Persistent URL http://hdl.handle.net/10536/DRO/DU:30089718

Connect to link resolver
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 13 times in TR Web of Science
Scopus Citation Count Cited 14 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 431 Abstract Views, 6 File Downloads  -  Detailed Statistics
Created: Mon, 20 Mar 2017, 12:44:40 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.