東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Kavramsal Bir Hidrolojik Modele Yapa...

Kumanlioglu, Ahmet Ali,

Linked to FindBook

Google Book

Amazon

博客來

Kavramsal Bir Hidrolojik Modele Yapay Zeka Entegrasyonu = = Integration of Artificial Intelligence to a Conceptual Hydrologic Model /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Kavramsal Bir Hidrolojik Modele Yapay Zeka Entegrasyonu =/ Ahmet Ali Kumanlioglu.
Reminder of title:	Integration of Artificial Intelligence to a Conceptual Hydrologic Model /
Author:	Kumanlioglu, Ahmet Ali,
Description:	1 electronic resource (271 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-09, Section: A.
Contained By:	Dissertations Abstracts International85-09A.
Subject:	Armed forces. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30851858
ISBN:	9798381787290

Kavramsal Bir Hidrolojik Modele Yapay Zeka Entegrasyonu = = Integration of Artificial Intelligence to a Conceptual Hydrologic Model /
Kumanlioglu, Ahmet Ali,

Kavramsal Bir Hidrolojik Modele Yapay Zeka Entegrasyonu =Integration of Artificial Intelligence to a Conceptual Hydrologic Model /Ahmet Ali Kumanlioglu. - 1 electronic resource (271 pages)

Source: Dissertations Abstracts International, Volume: 85-09, Section: A.

Sunulan calismada, kavramsal bir hidrolojik modele yapay zeka tekniklerinden yapay sinir aglari ve genetik algoritmalar entegre edilerek, daha az parametreye sahip yeni bir gunluk yagis akis modeli gelistirilmistir. Calisma kapsaminda gerceklestirilen yapay zeka entegrasyonu, deterministik, ortalanmis, surekli bir parametrik model olan GR4J (Genie Rural a 4 paramatres Journalier) gunluk yagis akis modeli uzerinde gerceklestirilmistir. GR4J gunluk yagis akis modeli yapisinda biriktirme ve oteleme elemanlari bulunduran ve X1,X2, X3, ve X4, olmak uzere 4 model parametresine sahip gunluk yagis akis modelidir.Calismada kapsaminda GR4J parametrik yagis akis modeline ilk olarak yapay sinir aglarinin (YSA) entegrasyonu gerceklestirilmistir. Yapay sinir agi entegrasyonunda, GR4J modelinin parametre sayisi #ten Ve indirilmis ve model icersindeki dogrusal olmayan akim oteleme sureci yapay sinir aglari ile modellenmistir. Soz konusu bu entegrasyon ile modelin parametre sayisi onemli olcude azalirken tahmin performansi onemli olcude arttirilmistir.Calisma ayrica, GR4J-YSA entegre modeline genetik algoritmalar (GA) da entegre edilerek model parametrelerinin otomatik olarak GA sayesinde kalibre edilmesi saglanmistir. Son derece az parametreye sahip ve parametrelerini otomatik olarak kalibre edebilen GR4J-YSA-GA entegre modeli Gediz havzasinin Murat, Selendi, Deliinis, Demirci, Gordes, Medar ve Yigitler althavzalarinda uygulanarak model performanslari incelenmistir. Uygulama sonuclari, GR4J modeline YSA ve GA entegrasyonunun model performanslarini onemli olcude arttirdigi gostermistir.Sonuc olarak sunulan calismada, kavramsal hidrolojik modellere YSA ve GA gibi yapay zeka tekniklerinin entegre edilmesiyle, model parametre sayilarinin azaltilarak kalibrasyon surecinin hizlandirilabilecegi ve buna karsilik entegre modellerle model tahmin performanslarinin arttirilabilecegi gosterilmistir.

Turkish

ISBN: 9798381787290Subjects--Topical Terms:

3562018
Armed forces.

Kavramsal Bir Hidrolojik Modele Yapay Zeka Entegrasyonu = = Integration of Artificial Intelligence to a Conceptual Hydrologic Model /
LDR:05378nmm a22003853i 4500 001 2437330
005 20251119142756.5
006 m o d
007 cr|nu||||||||
008 261011s2011 miu||||||m |||||||eng d
020 $a 9798381787290
035 $a (MiAaPQD)AAI30851858
035 $a (MiAaPQD)DokuzEylul468e1e81495341e486f9c73bc5890848
035 $a AAI30851858
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Kumanlioglu, Ahmet Ali, $e author. $3 3828269
245 1 0 $a Kavramsal Bir Hidrolojik Modele Yapay Zeka Entegrasyonu = $b Integration of Artificial Intelligence to a Conceptual Hydrologic Model / $c Ahmet Ali Kumanlioglu.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2011
300 $a 1 electronic resource (271 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-09, Section: A.
500 $a Advisors: Fistikoglu, Okan Committee members: Ozkul, Sevunc; Senol, Yavuz.
502 $b Ph.D. $c Dokuz Eylul Universitesi (Turkey) $d 2011.
520 $a Sunulan calismada, kavramsal bir hidrolojik modele yapay zeka tekniklerinden yapay sinir aglari ve genetik algoritmalar entegre edilerek, daha az parametreye sahip yeni bir gunluk yagis akis modeli gelistirilmistir. Calisma kapsaminda gerceklestirilen yapay zeka entegrasyonu, deterministik, ortalanmis, surekli bir parametrik model olan GR4J (Genie Rural a 4 paramatres Journalier) gunluk yagis akis modeli uzerinde gerceklestirilmistir. GR4J gunluk yagis akis modeli yapisinda biriktirme ve oteleme elemanlari bulunduran ve X1,X2, X3, ve X4, olmak uzere 4 model parametresine sahip gunluk yagis akis modelidir.Calismada kapsaminda GR4J parametrik yagis akis modeline ilk olarak yapay sinir aglarinin (YSA) entegrasyonu gerceklestirilmistir. Yapay sinir agi entegrasyonunda, GR4J modelinin parametre sayisi #ten Ve indirilmis ve model icersindeki dogrusal olmayan akim oteleme sureci yapay sinir aglari ile modellenmistir. Soz konusu bu entegrasyon ile modelin parametre sayisi onemli olcude azalirken tahmin performansi onemli olcude arttirilmistir.Calisma ayrica, GR4J-YSA entegre modeline genetik algoritmalar (GA) da entegre edilerek model parametrelerinin otomatik olarak GA sayesinde kalibre edilmesi saglanmistir. Son derece az parametreye sahip ve parametrelerini otomatik olarak kalibre edebilen GR4J-YSA-GA entegre modeli Gediz havzasinin Murat, Selendi, Deliinis, Demirci, Gordes, Medar ve Yigitler althavzalarinda uygulanarak model performanslari incelenmistir. Uygulama sonuclari, GR4J modeline YSA ve GA entegrasyonunun model performanslarini onemli olcude arttirdigi gostermistir.Sonuc olarak sunulan calismada, kavramsal hidrolojik modellere YSA ve GA gibi yapay zeka tekniklerinin entegre edilmesiyle, model parametre sayilarinin azaltilarak kalibrasyon surecinin hizlandirilabilecegi ve buna karsilik entegre modellerle model tahmin performanslarinin arttirilabilecegi gosterilmistir.
520 $a In the presented study, a new daily rainfall flow model with fewer parameters was developed by integrating artificial neural networks and genetic algorithms from artificial intelligence techniques into a conceptual hydrological model. The artificial intelligence integration within the scope of the study was carried out on the GR4J (Genie Rural a 4 paramatres Journalier) daily rainfall flow model, which is a deterministic, centered, continuous parametric model. GR4J daily rainfall flow model includes accumulation and translation elements in its structure and includes X1,X2, X3, and X4It is a daily rainfall flow model with 4 model parameters: sub>,.In the scope of the study, first the integration of artificial neural networks (ANN) was carried out into the GR4J parametric rainfall flow model. In the artificial neural network integration, the number of parameters of the GR4J model was reduced from # to Ve and the nonlinear current translation process in the model was modeled with artificial neural networks. With this integration, the number of parameters of the model was significantly reduced, while the prediction performance was significantly increased.The study also integrated genetic algorithms (GA) into the GR4J-ANN integrated model, ensuring that the model parameters were automatically calibrated thanks to GA. The GR4J-ANN-GA integrated model, which has very few parameters and can automatically calibrate its parameters, was applied to the Murat, Selendi, Deliinis, Demirci, Gordes, Medar and Yigitler sub-basins of the Gediz basin and the model performances were examined. Application results have shown that the integration of ANN and GA into the GR4J model significantly increases model performances.As a result, in the presented study, by integrating artificial intelligence techniques such as ANN and GA into conceptual hydrological models, the calibration process can be accelerated by reducing the number of model parameters and this On the other hand, it has been shown that model prediction performances can be increased with integrated models.
546 $a Turkish
590 $a School code: 5972
650 4 $a Armed forces. $3 3562018
650 4 $a Military studies. $3 2197382
690 $a 0800
690 $a 0750
710 2 $a Dokuz Eylul Universitesi (Turkey). $e degree granting institution. $3 3818706
720 1 $a Fistikoglu, Okan $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-09A.
790 $a 5972
791 $a Ph.D.
792 $a 2011
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30851858