Integrating the focusing neuron model with N-BEATS and N-HiTS

Basit Öğe Kaydı
dc.authorid0000-0003-3903-7356
dc.authorid0000-0002-8649-6013
dc.contributor.authorÖzçelik, Şuayb Talhaen_US
dc.contributor.authorTek, Faik Borayen_US
dc.date.accessioned2025-08-15T09:44:17Z
dc.date.available2025-08-15T09:44:17Z
dc.date.issued2024
dc.departmentIşık Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering and Natural Sciences, Department of Computer Engineeringen_US
dc.description.abstractThe N-BEATS (Neural Basis Expansion Analysis for Time Series) model is a robust deep learning architecture designed specifically for time series forecasting. Its foundational idea lies in the use of a generic, interpretable architecture that leverages backward and forward residual links to predict time series data effectively. N - BEATS influenced the development of N-HiTS (Neural Hierarchical Interpretable Time Series), which builds upon and extends the foundational ideas of N-BEATS. This paper introduces new integrations to enhance these models using the Focusing Neuron model in blocks of N-BEATS and N-HiTS instead of Fully Connected (Dense) Neurons. The integration aims to improve the forward and backward forecasting processes in the blocks by facilitating the learning of parametric local receptive fields. Preliminary results indicate that this new usage can significantly improve model performances on datasets that have longer sequences, providing a promising direction for future advancements in N-BEATS and N-HiTS.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationÖzçelik, Ş. T. & Tek, F. B. (2024). Integrating the focusing neuron model with N-BEATS and N-HiTS. Paper presented at the UBMK 2024 - Proceedings: 9th International Conference on Computer Science and Engineering, 422-425. doi:10.1109/UBMK63289.2024.10773495en_US
dc.identifier.doi10.1109/UBMK63289.2024.10773495
dc.identifier.endpage425
dc.identifier.isbn9798350365887
dc.identifier.scopus2-s2.0-85215526884
dc.identifier.scopusqualityN/A
dc.identifier.startpage422
dc.identifier.urihttps://hdl.handle.net/11729/6614
dc.identifier.urihttps://doi.org/10.1109/UBMK63289.2024.10773495
dc.indekslendigikaynakScopusen_US
dc.institutionauthorÖzçelik, Şuayb Talhaen_US
dc.institutionauthorid0000-0003-3903-7356
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofUBMK 2024 - Proceedings: 9th International Conference on Computer Science and Engineeringen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Öğrencien_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectFocusing neuronen_US
dc.subjectN-BEATSen_US
dc.subjectN-HiTSen_US
dc.subjectTime-seriesen_US
dc.subjectDeep learningen_US
dc.subjectLearning architecturesen_US
dc.subjectNeural base expansion analyze for time seriesen_US
dc.subjectNeural hierarchical interpretable time seriesen_US
dc.subjectNeuron modelingen_US
dc.subjectTime series forecastingen_US
dc.subjectTimes seriesen_US
dc.subjectTimes series modelsen_US
dc.subjectNeuronsen_US
dc.titleIntegrating the focusing neuron model with N-BEATS and N-HiTSen_US
dc.typeConference Objecten_US
dspace.entity.typePublicationen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Integrating_the_Focusing_Neuron_Model_with_N_BEATS_and_N_HiTS.pdf
Boyut:
360.2 KB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Öğrenci Yayınları Bildiri Koleksiyonu
Bildiri Koleksiyonu | Bilgisayar Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu