Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network

Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it nee...

Full description

Main Authors: Zafar, R., Kamel, N., Naufal, M., Malik, A.S., Dass, S.C., Ahmad, R.F., Abdullah, J.M., Reza, F.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.19834 /
Published: IOS Press 2017
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85030116670&doi=10.3233%2fJIN-170016&partnerID=40&md5=476b375377b777623635f500c804f856
http://eprints.utp.edu.my/19834/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.19834
recordtype eprints
spelling utp-eprints.198342018-04-22T13:06:54Z Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network Zafar, R. Kamel, N. Naufal, M. Malik, A.S. Dass, S.C. Ahmad, R.F. Abdullah, J.M. Reza, F. Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t -test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6) compared to ROI (61.88) and estimation values (64.17). © 2017 - IOS Press and the authors. All rights reserved. IOS Press 2017 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85030116670&doi=10.3233%2fJIN-170016&partnerID=40&md5=476b375377b777623635f500c804f856 Zafar, R. and Kamel, N. and Naufal, M. and Malik, A.S. and Dass, S.C. and Ahmad, R.F. and Abdullah, J.M. and Reza, F. (2017) Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network. Journal of Integrative Neuroscience, 16 (3). pp. 275-289. http://eprints.utp.edu.my/19834/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t -test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6) compared to ROI (61.88) and estimation values (64.17). © 2017 - IOS Press and the authors. All rights reserved.
format Article
author Zafar, R.
Kamel, N.
Naufal, M.
Malik, A.S.
Dass, S.C.
Ahmad, R.F.
Abdullah, J.M.
Reza, F.
spellingShingle Zafar, R.
Kamel, N.
Naufal, M.
Malik, A.S.
Dass, S.C.
Ahmad, R.F.
Abdullah, J.M.
Reza, F.
Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network
author_sort Zafar, R.
title Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network
title_short Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network
title_full Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network
title_fullStr Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network
title_full_unstemmed Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network
title_sort decoding of visual activity patterns from fmri responses using multivariate pattern analyses and convolutional neural network
publisher IOS Press
publishDate 2017
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85030116670&doi=10.3233%2fJIN-170016&partnerID=40&md5=476b375377b777623635f500c804f856
http://eprints.utp.edu.my/19834/
_version_ 1741196271565144064
score 11.62408

Similar Items