A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification

Time series classification (TSC) is essential in various application domains to understand the system dynamics. The adoption of deep learning has advanced TSC, however its performance is sensitive to hyperparameters configuration. Manual tuning of high-dimensional hyperparameters can be labor intens...

Full description

Saved in:
Bibliographic Details
Main Authors: Ayuningtyas Hari Fristiana, Syukron Abu Ishaq Alfarozi, Adhistya Erna Permanasari, Mahardhika Pratama, Sunu Wibirama
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10795132/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850254460545138688
author Ayuningtyas Hari Fristiana
Syukron Abu Ishaq Alfarozi
Adhistya Erna Permanasari
Mahardhika Pratama
Sunu Wibirama
author_facet Ayuningtyas Hari Fristiana
Syukron Abu Ishaq Alfarozi
Adhistya Erna Permanasari
Mahardhika Pratama
Sunu Wibirama
author_sort Ayuningtyas Hari Fristiana
collection DOAJ
description Time series classification (TSC) is essential in various application domains to understand the system dynamics. The adoption of deep learning has advanced TSC, however its performance is sensitive to hyperparameters configuration. Manual tuning of high-dimensional hyperparameters can be labor intensive, leading to a preference for automatic hyperparameters optimization (HPO) methods. To the best of our knowledge, survey papers covering various studies on automatic hyperparameters optimization (HPO) of deep learning for TSC are scarce and even none. To address this gap, we present a systematic literature review to assist researchers in addressing the HPO problem for deep learning in TSC. We analyzed studies published between 2018 and June 2024. This review examines the HPO methods, hyperparameters, and tools utilized in this context based on 77 primary studies sourced from academic databases. The findings indicate that Metaheuristic algorithm and Bayesian Optimization are commonly employed approaches, with a focus on hyperparameters related to the deep learning architectures. This review provides insights that can inform the design and implementation of HPO strategies for deep learning models in time series analysis.
format Article
id doaj-art-52f7a32f5d3d4a9da698b39a50e68ef1
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-52f7a32f5d3d4a9da698b39a50e68ef12025-08-20T01:57:08ZengIEEEIEEE Access2169-35362024-01-011219116219119810.1109/ACCESS.2024.351619810795132A Survey on Hyperparameters Optimization of Deep Learning for Time Series ClassificationAyuningtyas Hari Fristiana0Syukron Abu Ishaq Alfarozi1https://orcid.org/0000-0001-8558-898XAdhistya Erna Permanasari2https://orcid.org/0000-0002-2663-4074Mahardhika Pratama3https://orcid.org/0000-0001-6531-5087Sunu Wibirama4https://orcid.org/0000-0001-9613-7017Department of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, IndonesiaDepartment of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, IndonesiaDepartment of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, IndonesiaSTEM, University of South Australia, Adelaide, SA, AustraliaDepartment of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, IndonesiaTime series classification (TSC) is essential in various application domains to understand the system dynamics. The adoption of deep learning has advanced TSC, however its performance is sensitive to hyperparameters configuration. Manual tuning of high-dimensional hyperparameters can be labor intensive, leading to a preference for automatic hyperparameters optimization (HPO) methods. To the best of our knowledge, survey papers covering various studies on automatic hyperparameters optimization (HPO) of deep learning for TSC are scarce and even none. To address this gap, we present a systematic literature review to assist researchers in addressing the HPO problem for deep learning in TSC. We analyzed studies published between 2018 and June 2024. This review examines the HPO methods, hyperparameters, and tools utilized in this context based on 77 primary studies sourced from academic databases. The findings indicate that Metaheuristic algorithm and Bayesian Optimization are commonly employed approaches, with a focus on hyperparameters related to the deep learning architectures. This review provides insights that can inform the design and implementation of HPO strategies for deep learning models in time series analysis.https://ieeexplore.ieee.org/document/10795132/Deep neural networkhyperparameters tuningevolutionary algorithmtime series analysisBayesian optimizationmultifidelity algorithm
spellingShingle Ayuningtyas Hari Fristiana
Syukron Abu Ishaq Alfarozi
Adhistya Erna Permanasari
Mahardhika Pratama
Sunu Wibirama
A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification
IEEE Access
Deep neural network
hyperparameters tuning
evolutionary algorithm
time series analysis
Bayesian optimization
multifidelity algorithm
title A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification
title_full A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification
title_fullStr A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification
title_full_unstemmed A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification
title_short A Survey on Hyperparameters Optimization of Deep Learning for Time Series Classification
title_sort survey on hyperparameters optimization of deep learning for time series classification
topic Deep neural network
hyperparameters tuning
evolutionary algorithm
time series analysis
Bayesian optimization
multifidelity algorithm
url https://ieeexplore.ieee.org/document/10795132/
work_keys_str_mv AT ayuningtyasharifristiana asurveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT syukronabuishaqalfarozi asurveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT adhistyaernapermanasari asurveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT mahardhikapratama asurveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT sunuwibirama asurveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT ayuningtyasharifristiana surveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT syukronabuishaqalfarozi surveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT adhistyaernapermanasari surveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT mahardhikapratama surveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification
AT sunuwibirama surveyonhyperparametersoptimizationofdeeplearningfortimeseriesclassification