Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics

Makkie, M; Huang, H; Zhao, Y; Vasilakos, AV; Liu, T

Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics

Makkie, M Huang, H Zhao, Y Vasilakos, AV

Liu, T

Permalink

Publication Type:: Journal Article
Citation:: Neurocomputing, 2019, 325 pp. 20 - 30
Issue Date:: 2019-01-24

Closed Access

	Filename	Description	Size
	1-s2.0-S0925231218311470-main.pdf	Published Version	3.27 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Makkie, M	en_US
dc.contributor.author	Huang, H	en_US
dc.contributor.author	Zhao, Y	en_US
dc.contributor.author	Vasilakos, AV https://orcid.org/0000-0003-1902-9877	en_US
dc.contributor.author	Liu, T	en_US
dc.date.accessioned	2020-03-26T03:21:38Z
dc.date.available	2020-03-26T03:21:38Z
dc.date.issued	2019-01-24	en_US
dc.identifier.citation	Neurocomputing, 2019, 325 pp. 20 - 30	en_US
dc.identifier.issn	0925-2312	en_US
dc.identifier.uri	http://hdl.handle.net/10453/139547
dc.description.abstract	© 2018 Elsevier B.V. In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks. However, due to the sheer size of tfMRI data, its intrinsic complex structure, and lack of ground truth of underlying neural activities, modeling tfMRI data is hard and challenging. Previously proposed data modeling methods including Independent Component Analysis (ICA) and Sparse Dictionary Learning only provided shallow models based on blind source separation under the strong assumption that original fMRI signals could be linearly decomposed into time series components with corresponding spatial maps. Given the Convolutional Neural Network (CNN) successes in learning hierarchical abstractions from low-level data such as tfMRI time series, in this work we propose a novel scalable distributed deep CNN autoencoder model and apply it for fMRI big data analysis. This model aims to both learn the complex hierarchical structures of the tfMRI big data and to leverage the processing power of multiple GPUs in a distributed fashion. To deploy such a model, we have created an enhanced processing pipeline on the top of Apache Spark and Tensorflow, leveraging from a large cluster of GPU nodes over cloud. Experimental results from applying the model on the Human Connectome Project (HCP) data show that the proposed model is efficient and scalable toward tfMRI big data modeling and analytics, thus enabling data-driven extraction of hierarchical neuroscientific information from massive fMRI big data.	en_US
dc.relation.ispartof	Neurocomputing	en_US
dc.relation.isbasedon	10.1016/j.neucom.2018.09.066	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics	en_US
dc.type	Journal Article
utslib.citation.volume	325	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	en_US
utslib.for	17 Psychology and Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.publication-status	Published	en_US
pubs.volume	325	en_US

Abstract:

© 2018 Elsevier B.V. In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks. However, due to the sheer size of tfMRI data, its intrinsic complex structure, and lack of ground truth of underlying neural activities, modeling tfMRI data is hard and challenging. Previously proposed data modeling methods including Independent Component Analysis (ICA) and Sparse Dictionary Learning only provided shallow models based on blind source separation under the strong assumption that original fMRI signals could be linearly decomposed into time series components with corresponding spatial maps. Given the Convolutional Neural Network (CNN) successes in learning hierarchical abstractions from low-level data such as tfMRI time series, in this work we propose a novel scalable distributed deep CNN autoencoder model and apply it for fMRI big data analysis. This model aims to both learn the complex hierarchical structures of the tfMRI big data and to leverage the processing power of multiple GPUs in a distributed fashion. To deploy such a model, we have created an enhanced processing pipeline on the top of Apache Spark and Tensorflow, leveraging from a large cluster of GPU nodes over cloud. Experimental results from applying the model on the Human Connectome Project (HCP) data show that the proposed model is efficient and scalable toward tfMRI big data modeling and analytics, thus enabling data-driven extraction of hierarchical neuroscientific information from massive fMRI big data.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/139547