No Cover Image

Journal article 468 views 72 downloads

Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis

Xiaobo Liu, Scott Yang Orcid Logo, Zhengxian Liu

NeuroSci, Volume: 2, Issue: 4, Pages: 427 - 442

Swansea University Author: Scott Yang Orcid Logo

  • 59033.pdf

    PDF | Version of Record

    © 2021 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license

    Download (2.48MB)

Check full text

DOI (Published version): 10.3390/neurosci2040032

Abstract

Objectives: Functional connectivity triggered by naturalistic stimuli (e.g., movie clips), coupled with machine learning techniques provide great insight in exploring brain functions such as fluid intelligence. However, functional connectivity is multi-layered while traditional machine learning is b...

Full description

Published in: NeuroSci
ISSN: 2673-4087
Published: MDPI AG 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa59033
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-12-20T21:34:16Z
last_indexed 2022-01-08T04:27:59Z
id cronfa59033
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-01-07T15:34:18.7344772</datestamp><bib-version>v2</bib-version><id>59033</id><entry>2021-12-20</entry><title>Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis</title><swanseaauthors><author><sid>81dc663ca0e68c60908d35b1d2ec3a9b</sid><ORCID>0000-0002-6618-7483</ORCID><firstname>Scott</firstname><surname>Yang</surname><name>Scott Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-12-20</date><deptcode>SCS</deptcode><abstract>Objectives: Functional connectivity triggered by naturalistic stimuli (e.g., movie clips), coupled with machine learning techniques provide great insight in exploring brain functions such as fluid intelligence. However, functional connectivity is multi-layered while traditional machine learning is based on individual model, which is not only limited in performance, but also fails to extract multi-dimensional and multi-layered information from the brain network. Methods: In this study, inspired by multi-layer brain network structure, we propose a new method, namely weighted ensemble model and network analysis, which combines machine learning and graph theory for improved fluid intelligence prediction. Firstly, functional connectivity analysis and graphical theory were jointly employed. The functional connectivity and graphical indices computed using the preprocessed fMRI data were then all fed into an auto-encoder parallelly for automatic feature extraction to predict the fluid intelligence. In order to improve the performance, tree regression and ridge regression models were stacked and fused automatically with weighted values. Finally, layers of auto-encoder were visualized to better illustrate the connectome patterns, followed by the evaluation of the performance to justify the mechanism of brain functions. Results: Our proposed method achieved the best performance with a 3.85 mean absolute deviation, 0.66 correlation coefficient and 0.42 R-squared coefficient; this model outperformed other state-of-the-art methods. It is also worth noting that the optimization of the biological pattern extraction was automated though the auto-encoder algorithm. Conclusion: The proposed method outperforms the state-of-the-art reports, also is able to effectively capture the biological patterns of functional connectivity during a naturalistic movie state for potential clinical explorations.</abstract><type>Journal Article</type><journal>NeuroSci</journal><volume>2</volume><journalNumber>4</journalNumber><paginationStart>427</paginationStart><paginationEnd>442</paginationEnd><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2673-4087</issnElectronic><keywords>functional magnetic resonance imaging; functional connectivity; weighted ensemble model and network analysis; fluid intelligence</keywords><publishedDay>17</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-12-17</publishedDate><doi>10.3390/neurosci2040032</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>China Scholarship Council and the National Social Science Foundation of China (BEA200115)</funders><lastEdited>2022-01-07T15:34:18.7344772</lastEdited><Created>2021-12-20T21:33:04.5043629</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Xiaobo</firstname><surname>Liu</surname><order>1</order></author><author><firstname>Scott</firstname><surname>Yang</surname><orcid>0000-0002-6618-7483</orcid><order>2</order></author><author><firstname>Zhengxian</firstname><surname>Liu</surname><order>3</order></author></authors><documents><document><filename>59033__22077__9f24626f9a594ff9a1925f98c36b4c7c.pdf</filename><originalFilename>59033.pdf</originalFilename><uploaded>2022-01-07T15:32:36.4441619</uploaded><type>Output</type><contentLength>2602695</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2021 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-01-07T15:34:18.7344772 v2 59033 2021-12-20 Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis 81dc663ca0e68c60908d35b1d2ec3a9b 0000-0002-6618-7483 Scott Yang Scott Yang true false 2021-12-20 SCS Objectives: Functional connectivity triggered by naturalistic stimuli (e.g., movie clips), coupled with machine learning techniques provide great insight in exploring brain functions such as fluid intelligence. However, functional connectivity is multi-layered while traditional machine learning is based on individual model, which is not only limited in performance, but also fails to extract multi-dimensional and multi-layered information from the brain network. Methods: In this study, inspired by multi-layer brain network structure, we propose a new method, namely weighted ensemble model and network analysis, which combines machine learning and graph theory for improved fluid intelligence prediction. Firstly, functional connectivity analysis and graphical theory were jointly employed. The functional connectivity and graphical indices computed using the preprocessed fMRI data were then all fed into an auto-encoder parallelly for automatic feature extraction to predict the fluid intelligence. In order to improve the performance, tree regression and ridge regression models were stacked and fused automatically with weighted values. Finally, layers of auto-encoder were visualized to better illustrate the connectome patterns, followed by the evaluation of the performance to justify the mechanism of brain functions. Results: Our proposed method achieved the best performance with a 3.85 mean absolute deviation, 0.66 correlation coefficient and 0.42 R-squared coefficient; this model outperformed other state-of-the-art methods. It is also worth noting that the optimization of the biological pattern extraction was automated though the auto-encoder algorithm. Conclusion: The proposed method outperforms the state-of-the-art reports, also is able to effectively capture the biological patterns of functional connectivity during a naturalistic movie state for potential clinical explorations. Journal Article NeuroSci 2 4 427 442 MDPI AG 2673-4087 functional magnetic resonance imaging; functional connectivity; weighted ensemble model and network analysis; fluid intelligence 17 12 2021 2021-12-17 10.3390/neurosci2040032 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University Not Required China Scholarship Council and the National Social Science Foundation of China (BEA200115) 2022-01-07T15:34:18.7344772 2021-12-20T21:33:04.5043629 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Xiaobo Liu 1 Scott Yang 0000-0002-6618-7483 2 Zhengxian Liu 3 59033__22077__9f24626f9a594ff9a1925f98c36b4c7c.pdf 59033.pdf 2022-01-07T15:32:36.4441619 Output 2602695 application/pdf Version of Record true © 2021 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license true eng https://creativecommons.org/licenses/by/4.0/
title Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
spellingShingle Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
Scott Yang
title_short Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
title_full Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
title_fullStr Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
title_full_unstemmed Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
title_sort Predicting Fluid Intelligence via Naturalistic Functional Connectivity Using Weighted Ensemble Model and Network Analysis
author_id_str_mv 81dc663ca0e68c60908d35b1d2ec3a9b
author_id_fullname_str_mv 81dc663ca0e68c60908d35b1d2ec3a9b_***_Scott Yang
author Scott Yang
author2 Xiaobo Liu
Scott Yang
Zhengxian Liu
format Journal article
container_title NeuroSci
container_volume 2
container_issue 4
container_start_page 427
publishDate 2021
institution Swansea University
issn 2673-4087
doi_str_mv 10.3390/neurosci2040032
publisher MDPI AG
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description Objectives: Functional connectivity triggered by naturalistic stimuli (e.g., movie clips), coupled with machine learning techniques provide great insight in exploring brain functions such as fluid intelligence. However, functional connectivity is multi-layered while traditional machine learning is based on individual model, which is not only limited in performance, but also fails to extract multi-dimensional and multi-layered information from the brain network. Methods: In this study, inspired by multi-layer brain network structure, we propose a new method, namely weighted ensemble model and network analysis, which combines machine learning and graph theory for improved fluid intelligence prediction. Firstly, functional connectivity analysis and graphical theory were jointly employed. The functional connectivity and graphical indices computed using the preprocessed fMRI data were then all fed into an auto-encoder parallelly for automatic feature extraction to predict the fluid intelligence. In order to improve the performance, tree regression and ridge regression models were stacked and fused automatically with weighted values. Finally, layers of auto-encoder were visualized to better illustrate the connectome patterns, followed by the evaluation of the performance to justify the mechanism of brain functions. Results: Our proposed method achieved the best performance with a 3.85 mean absolute deviation, 0.66 correlation coefficient and 0.42 R-squared coefficient; this model outperformed other state-of-the-art methods. It is also worth noting that the optimization of the biological pattern extraction was automated though the auto-encoder algorithm. Conclusion: The proposed method outperforms the state-of-the-art reports, also is able to effectively capture the biological patterns of functional connectivity during a naturalistic movie state for potential clinical explorations.
published_date 2021-12-17T04:16:01Z
_version_ 1763754074735378432
score 11.013371

Similar Items