Impact of small-world topology on the performance of a feed-forward artificial neural network based on 2 different real-life problems

Since feed-forward artificial neural networks (FFANNs) are the most widely used models to solve real-life problems, many studies have focused on improving their learning performances by changing the network architecture and learning algorithms. On the other hand, recently, small-world network topology has been shown to meet the characteristics of real-life problems. Therefore, in this study, instead of focusing on the performance of the conventional FFANNs, we investigated how real-life problems can be solved by a FFANN with small-world topology. Therefore, we considered 2 real-life problems: estimating the thermal performance of solar air collectors and predicting the modulus of rupture values of oriented strand boards. We used the FFANN with small-world topology to solve both problems and compared the results with those of a conventional FFANN with zero rewiring. In addition, we investigated whether there was statistically significant difference between the regular FFANN and small-world FFANN model. Our results show that there exists an optimal rewiring number within the small-world topology that warrants the best performance for both problems. © TUBITAK.

Dergi Adı Turkish Journal of Electrical Engineering and Computer Sciences
Dergi Cilt Bilgisi 22
Dergi Sayısı 3
Sayfalar 708 - 718
Yayın Yılı 2014
Eser Adı
[dc.title]
Impact of small-world topology on the performance of a feed-forward artificial neural network based on 2 different real-life problems
Yazar
[dc.contributor.author]
Erkaymaz, Okan
Yazar
[dc.contributor.author]
Özer, Mahmut
Yazar
[dc.contributor.author]
Yumuşak, Nejat
Yayın Yılı
[dc.date.issued]
2014
Yayın Türü
[dc.type]
article
Özet
[dc.description.abstract]
Since feed-forward artificial neural networks (FFANNs) are the most widely used models to solve real-life problems, many studies have focused on improving their learning performances by changing the network architecture and learning algorithms. On the other hand, recently, small-world network topology has been shown to meet the characteristics of real-life problems. Therefore, in this study, instead of focusing on the performance of the conventional FFANNs, we investigated how real-life problems can be solved by a FFANN with small-world topology. Therefore, we considered 2 real-life problems: estimating the thermal performance of solar air collectors and predicting the modulus of rupture values of oriented strand boards. We used the FFANN with small-world topology to solve both problems and compared the results with those of a conventional FFANN with zero rewiring. In addition, we investigated whether there was statistically significant difference between the regular FFANN and small-world FFANN model. Our results show that there exists an optimal rewiring number within the small-world topology that warrants the best performance for both problems. © TUBITAK.
Kayıt Giriş Tarihi
[dc.date.accessioned]
2019-12-23
Açık Erişim Tarihi
[dc.date.available]
2019-12-23
Yayın Dili
[dc.language.iso]
eng
Konu Başlıkları
[dc.subject]
Feed-forward artificial neural network
Konu Başlıkları
[dc.subject]
Network topology
Konu Başlıkları
[dc.subject]
Rewiring
Konu Başlıkları
[dc.subject]
Small-world network
Künye
[dc.identifier.citation]
Erkaymaz, O., Özer, M. ve Yumuşak, N. (2014). Impact of small-world topology on the performance of a feed-forward artificial neural network based on 2 different real-life problems. Turkish Journal of Electrical Engineering and Computer Science. TÜBİTAK. doi:10.3906/elk-1202-89
Haklar
[dc.rights]
info:eu-repo/semantics/openAccess
ISSN
[dc.identifier.issn]
1300-0632
İlk Sayfa Sayısı
[dc.identifier.startpage]
708
Son Sayfa Sayısı
[dc.identifier.endpage]
718
Dergi Adı
[dc.relation.journal]
Turkish Journal of Electrical Engineering and Computer Sciences
Dergi Sayısı
[dc.identifier.issue]
3
Dergi Cilt Bilgisi
[dc.identifier.volume]
22
Tek Biçim Adres
[dc.identifier.uri]
https://dx.doi.org/10.3906/elk-1202-89
Tek Biçim Adres
[dc.identifier.uri]
https://hdl.handle.net/20.500.12628/6166
Tam Metin İndirmek için tıklayın Ön izleme
Görüntülenme Sayısı ( Şehir )
Görüntülenme Sayısı ( Ülke )
Görüntülenme Sayısı ( Zaman Dağılımı )
Görüntülenme
39
09.12.2022 tarihinden bu yana
İndirme
1
09.12.2022 tarihinden bu yana
Son Erişim Tarihi
30 Mart 2024 04:34
Google Kontrol
Tıklayınız
problems small-world topology real-life performance results learning network conventional investigated rewiring Therefore compared strand boards oriented values rupture modulus predicting collectors statistically exists TUBITAK warrants within number optimal addition regular between difference significant whether thermal
6698 sayılı Kişisel Verilerin Korunması Kanunu kapsamında yükümlülüklerimiz ve çerez politikamız hakkında bilgi sahibi olmak için alttaki bağlantıyı kullanabilirsiniz.

creativecommons
Bu site altında yer alan tüm kaynaklar Creative Commons Alıntı-GayriTicari-Türetilemez 4.0 Uluslararası Lisansı ile lisanslanmıştır.
Platforms