Accelerating Hyperparameter Tuning in Machine Learning for Alzheimer's Disease With High Performance Computing

Simple item page
dc.creatorZhang, Fan
dc.creatorPetersen, Melissa E.
dc.creatorJohnson, Leigh A.
dc.creatorHall, James R.
dc.creatorO'Bryant, Sid E.
dc.creator.orcid0000-0003-0582-5266 (O'Bryant, Sid E.)
dc.creator.orcid0000-0001-7769-8417 (Johnson, Leigh A.)
dc.creator.orcid0000-0002-3920-5877 (Petersen, Melissa E.)
dc.date.accessioned2022-07-07T13:54:27Z
dc.date.available2022-07-07T13:54:27Z
dc.date.issued2021-12-08
dc.description.abstractDriven by massive datasets that comprise biomarkers from both blood and magnetic resonance imaging (MRI), the need for advanced learning algorithms and accelerator architectures, such as GPUs and FPGAs has increased. Machine learning (ML) methods have delivered remarkable prediction for the early diagnosis of Alzheimer's disease (AD). Although ML has improved accuracy of AD prediction, the requirement for the complexity of algorithms in ML increases, for example, hyperparameters tuning, which in turn, increases its computational complexity. Thus, accelerating high performance ML for AD is an important research challenge facing these fields. This work reports a multicore high performance support vector machine (SVM) hyperparameter tuning workflow with 100 times repeated 5-fold cross-validation for speeding up ML for AD. For demonstration and evaluation purposes, the high performance hyperparameter tuning model was applied to public MRI data for AD and included demographic factors such as age, sex and education. Results showed that computational efficiency increased by 96%, which helped to shed light on future diagnostic AD biomarker applications. The high performance hyperparameter tuning model can also be applied to other ML algorithms such as random forest, logistic regression, xgboost, etc.
dc.description.sponsorshipResearch reported in this publication was supported by the National Institute on Aging of the National Institutes of Health under Award Number R01AG058537, R01AG054073, R01AG058533, and 3R01AG058533-02S1. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
dc.identifier.citationZhang, F., Petersen, M., Johnson, L., Hall, J., & O'Bryant, S. E. (2021). Accelerating Hyperparameter Tuning in Machine Learning for Alzheimer's Disease With High Performance Computing. Frontiers in artificial intelligence, 4, 798962. https://doi.org/10.3389/frai.2021.798962
dc.identifier.issn2624-8212
dc.identifier.urihttps://hdl.handle.net/20.500.12503/31545
dc.identifier.volume4
dc.publisherFrontiers Media S.A.
dc.relation.urihttps://doi.org/10.3389/frai.2021.798962
dc.rights.holderCopyright © 2021 Zhang, Petersen, Johnson, Hall and O'Bryant
dc.rights.licenseAttribution 4.0 International (CC BY 4.0)
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.sourceFrontiers in Artificial Intelligence
dc.subjectAlzheimer's disease
dc.subjecthigh performance computing
dc.subjecthyperparameter tuning
dc.subjectmachine learning
dc.subjectsupport vector machine
dc.subject.meshAlzheimer Disease
dc.titleAccelerating Hyperparameter Tuning in Machine Learning for Alzheimer's Disease With High Performance Computing
dc.typeArticle
dc.type.materialtext

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
10.3389_frai.2021.798962.pdf
Size:
1.66 MB
Format:
Adobe Portable Document Format
Description:
full text article
Download

Collections

Publications -- Sid E. O'Bryant
Publications -- Fan Zhang
Publications -- James R. Hall
Publications -- Leigh A. Johnson
Publications -- Melissa E. Petersen