Show simple item record

dc.contributor.advisorAlpaydın, Ahmet İbrahim Ethem
dc.contributor.advisorErtüzün, Aysın Baytan
dc.contributor.authorDimililer, Nazife
dc.date.accessioned2020-12-04T11:50:15Z
dc.date.available2020-12-04T11:50:15Z
dc.date.submitted1995
dc.date.issued2018-08-06
dc.identifier.urihttps://acikbilim.yok.gov.tr/handle/20.500.12812/81163
dc.description.abstractTam olarak çözülmemiş bir problem olan deprem tahmin problemini yapay nöron ağîanna uyguladık. Manyitüt ve iki deprem arasındaki zamandan oluşan verilerin bir zaman serisini meydana getirdikleri ve bu serinin deprem sırası hakkında tüm gerekli bilgiyi içerdiğim kabul ederek, daha önce çeşitli zaman serilerini tahmin etmede ve modellemede kullanılan bazı nöron ağlarını çalıştırdık. Tezde deprem tahmin etme amacıyla kullanılan algoritmaların en başarılılarından olan Canada-Nevada algorithması kısaca açıklanıyor ve bu algoritmanın başarılı olurken, tezde uygulanlann başarısız olmasının nedenleri tartışılıyor. Aynca nöron algorithmalanyîa birlikte Box Jenkins yöntemi de uygulanıyor.
dc.description.abstractEarthquake Prediction is a mainly unsolved problem. A îarge number of different approaches have been tried and only a small number of attempts were fruitfuî. A few of these are explained briefly in this thesis. Öne of the most succesfui earthquake prediction sytems in use today is the Canada-Nevada, CN, algorithm. it is discussed and contrasted to the neural networks impiemented in the project. For this project the earthquake prediction problem is treated as a time series prediction problem and neural networks that have been used for ordinary time series prediction with some success have been applied to the problem. The data used was treated as a two dimensionaî time series with two variables; the magnitude of the present earthquake, and the time elapsed since the previous earthquake. The neural network architectures impiemented were the multilayer perceptron network with sigmoidal activation îunction, NADINE, and a multilayer network with chaotic activation îunction. Theresults were not succesfui because of the complex nature of input data and the earthquake generation process.en_US
dc.languageEnglish
dc.language.isoen
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightsAttribution 4.0 United Statestr_TR
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectBilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontroltr_TR
dc.subjectComputer Engineering and Computer Science and Controlen_US
dc.titleEarthquake predicition using neural networks
dc.typemasterThesis
dc.date.updated2018-08-06
dc.contributor.departmentBilgisayar Mühendisliği Anabilim Dalı
dc.subject.ytmEarthquake
dc.subject.ytmArtificial neural networks
dc.identifier.yokid47518
dc.publisher.instituteFen Bilimleri Enstitüsü
dc.publisher.universityBOĞAZİÇİ ÜNİVERSİTESİ
dc.identifier.thesisid47518
dc.description.pages102
dc.publisher.disciplineDiğer


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/openAccess
Except where otherwise noted, this item's license is described as info:eu-repo/semantics/openAccess