A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet

<p dir="ltr">In this paper, we present a novel method for advancing time series forecasting by representing discretized time series data through de Bruijn Graphs (dBGs). This method harnesses the capability of dBGs to encapsulate and project future states from historical sequences, t...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Mert Onur Cakiroglu (22927777) (author)
مؤلفون آخرون: Hasan Kurban (13144983) (author), Elham Buxton (22927780) (author), Mehmet Dalkilic (13144986) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513531513143296
author Mert Onur Cakiroglu (22927777)
author2 Hasan Kurban (13144983)
Elham Buxton (22927780)
Mehmet Dalkilic (13144986)
author2_role author
author
author
author_facet Mert Onur Cakiroglu (22927777)
Hasan Kurban (13144983)
Elham Buxton (22927780)
Mehmet Dalkilic (13144986)
author_role author
dc.creator.none.fl_str_mv Mert Onur Cakiroglu (22927777)
Hasan Kurban (13144983)
Elham Buxton (22927780)
Mehmet Dalkilic (13144986)
dc.date.none.fl_str_mv 2025-07-18T12:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2025.3588507
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Novel_Discrete_Time_Series_Representation_With_De_Bruijn_Graphs_for_Enhanced_Forecasting_Using_TimesNet/30971014
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Time series analysis
De Bruijn graph
TimesNet
graph embeddings
Forecasting
Feature extraction
Predictive models
Data models
Transformers
Encoding
Computational modeling
Accuracy
Training
dc.title.none.fl_str_mv A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">In this paper, we present a novel method for advancing time series forecasting by representing discretized time series data through de Bruijn Graphs (dBGs). This method harnesses the capability of dBGs to encapsulate and project future states from historical sequences, thus enhancing predictive analytics in time series. Our approach is multi-faceted, involving: 1) encoding time series data as a dBG; 2) the application of graph representation learning, specifically struct2vec, to distill salient features from dBG constructed from time series and 3) the seamless integration of these extracted features into the state of the art TimesNet model to bolster short-term forecasting accuracy. Empirical evaluations conducted on the M4 datasets illustrate that our approach not only maintains the intrinsic dynamics of the time series but also achieves notable improvements in forecasting performance across diverse datasets. All the code developed for this study can be found at: <a href="https://github.com/KurbanIntelligenceLab/dBGTime-Series-Library" target="_blank">https://github.com/KurbanIntelligenceLab/dBGTime-Series-Library</a></p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3588507" target="_blank">https://dx.doi.org/10.1109/access.2025.3588507</a></p>
eu_rights_str_mv openAccess
id Manara2_6a9f8a7f0f88b9dc190f2d6e5af099fc
identifier_str_mv 10.1109/access.2025.3588507
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30971014
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNetMert Onur Cakiroglu (22927777)Hasan Kurban (13144983)Elham Buxton (22927780)Mehmet Dalkilic (13144986)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningTime series analysisDe Bruijn graphTimesNetgraph embeddingsForecastingFeature extractionPredictive modelsData modelsTransformersEncodingComputational modelingAccuracyTraining<p dir="ltr">In this paper, we present a novel method for advancing time series forecasting by representing discretized time series data through de Bruijn Graphs (dBGs). This method harnesses the capability of dBGs to encapsulate and project future states from historical sequences, thus enhancing predictive analytics in time series. Our approach is multi-faceted, involving: 1) encoding time series data as a dBG; 2) the application of graph representation learning, specifically struct2vec, to distill salient features from dBG constructed from time series and 3) the seamless integration of these extracted features into the state of the art TimesNet model to bolster short-term forecasting accuracy. Empirical evaluations conducted on the M4 datasets illustrate that our approach not only maintains the intrinsic dynamics of the time series but also achieves notable improvements in forecasting performance across diverse datasets. All the code developed for this study can be found at: <a href="https://github.com/KurbanIntelligenceLab/dBGTime-Series-Library" target="_blank">https://github.com/KurbanIntelligenceLab/dBGTime-Series-Library</a></p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3588507" target="_blank">https://dx.doi.org/10.1109/access.2025.3588507</a></p>2025-07-18T12:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3588507https://figshare.com/articles/journal_contribution/A_Novel_Discrete_Time_Series_Representation_With_De_Bruijn_Graphs_for_Enhanced_Forecasting_Using_TimesNet/30971014CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/309710142025-07-18T12:00:00Z
spellingShingle A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
Mert Onur Cakiroglu (22927777)
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Time series analysis
De Bruijn graph
TimesNet
graph embeddings
Forecasting
Feature extraction
Predictive models
Data models
Transformers
Encoding
Computational modeling
Accuracy
Training
status_str publishedVersion
title A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
title_full A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
title_fullStr A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
title_full_unstemmed A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
title_short A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
title_sort A Novel Discrete Time Series Representation With De Bruijn Graphs for Enhanced Forecasting Using TimesNet
topic Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Time series analysis
De Bruijn graph
TimesNet
graph embeddings
Forecasting
Feature extraction
Predictive models
Data models
Transformers
Encoding
Computational modeling
Accuracy
Training