Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/3843
Title: | Temporal pattern based classification of independent components in resting state fMRI | Authors: | Đuričić , Jasna Lončar-Turukalo, Tatjana Dabic D. Koprivšek, Katarina Lučić, Miloš Šveljo, Olivera |
Issue Date: | 27-Dec-2016 | Journal: | 2016 13th Symposium on Neural Networks and Applications, NEUREL 2016 | Abstract: | © 2016 IEEE. The analysis of the resting state fMRI is hampered by the confounding presence of the artefacts Independent component analysis (ICA) presents a data-driven approach, ideally, separating noise and independent components (IC) of interest. The automatic identification of meaningful ICs in the resting state fMRI is done using three classification algorithms: multi-layer perceptron (MLP), support vector machines (SVM), and random forest (RF) based only on temporal IC patterns. The algorithms' performance was evaluated using manually labeled resting state fMRI data of 13 subjects. The achieved accuracy on group level is 91%, 85, 77% and 89,83% for MLP, SVM and RF, respectively. MLP performed the best on the reduced feature set, providing the best recall of 89% for the meaningful class and the best individual accuracy of 96%. | URI: | https://open.uns.ac.rs/handle/123456789/3843 | ISBN: | 9781509015306 | DOI: | 10.1109/NEUREL.2016.7800101 |
Appears in Collections: | FTN Publikacije/Publications |
Show full item record
SCOPUSTM
Citations
1
checked on May 10, 2024
Page view(s)
22
Last Week
2
2
Last month
8
8
checked on May 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.