{"id":12266,"date":"2023-05-23T13:26:11","date_gmt":"2023-05-23T10:26:11","guid":{"rendered":"https:\/\/bestessayhomework.com\/tr\/?p=12266"},"modified":"2023-05-23T13:26:11","modified_gmt":"2023-05-23T10:26:11","slug":"stokastik-modelin-sayisal-simulasyonu","status":"publish","type":"post","link":"https:\/\/bestessayhomework.com\/tr\/stokastik-modelin-sayisal-simulasyonu\/","title":{"rendered":"Stokastik Modelin Say\u0131sal Sim\u00fclasyonu"},"content":{"rendered":"

Stokastik Modelin Say\u0131sal Sim\u00fclasyonu<\/span><\/strong><\/h3>\n

Okuyucular\u0131n rahatl\u0131\u011f\u0131 i\u00e7in burada modelimizi \u00f6zetliyoruz. Yay\u0131nland\u0131ktan sonra t y\u0131l\u0131nda bir makalenin gizli at\u0131f oran\u0131 \u015f\u00f6yledir: Stokastik Modelin Say\u0131sal Sim\u00fclasyonu Okuyucular\u0131n rahatl\u0131\u011f\u0131 i\u00e7in burada modelimizi \u00f6zetliyoruz.<\/span><\/p>\n

Yay\u0131nland\u0131ktan sonra t y\u0131l\u0131nda bir makalenin gizli at\u0131f oran\u0131, burada \u03b7j, makalenin uygunluk de\u011feridir, ampirik bir parametredir ve her makale i\u00e7in benzersizdir; A \u0303(t), al\u0131nt\u0131lar i\u00e7in eskitme i\u015flevidir; P0, j makalesinin ikinci nesil bir al\u0131nt\u0131 makalesi taraf\u0131ndan dolayl\u0131 olarak al\u0131nt\u0131lanmas\u0131n\u0131n olas\u0131l\u0131k genli\u011fidir; \u03b3 eskime \u00fcss\u00fcd\u00fcr; ve nnn(t), bir birinci nesil at\u0131f makalesi ba\u015f\u0131na ikinci nesil at\u0131f makalelerinin ortalama y\u0131ll\u0131k say\u0131s\u0131d\u0131r. Makalenin at\u0131f oran\u0131 kj(t) = \u0394Kj\/\u0394t’dir; burada \u0394Kj, t y\u0131l\u0131nda al\u0131nan at\u0131f say\u0131s\u0131d\u0131r ve \u0394t = 1 y\u0131ld\u0131r.<\/span><\/p>\n

\u00dcs \u03b3 ve A \u0303(t) ve nnn(t) fonksiyonlar\u0131, ayn\u0131 y\u0131l i\u00e7inde yay\u0131nlanan bir alandaki t\u00fcm makaleler i\u00e7in ayn\u0131d\u0131r, P0(K) fonksiyonu verilir. Buradaki \u00f6zel amac\u0131m\u0131z, daha \u00f6nce de \u00a0yap\u0131ld\u0131\u011f\u0131 gibi yaln\u0131zca al\u0131nt\u0131 dinamiklerinin ortalama bile\u015fenini do\u011frulamak de\u011fildir.\u00a0<\/span><\/p>\n

Tek tek makalelerin at\u0131f dinamikleri homojen bir stokastik s\u00fcreci izliyorsa, modelle kar\u015f\u0131la\u015ft\u0131rma ka\u011f\u0131t baz\u0131nda yap\u0131labilir. Yani, \u015fematik olarak g\u00f6sterildi\u011fi gibi, her at\u0131f y\u00f6r\u00fcngesini ortalama ve dalgalanan par\u00e7alara ayr\u0131\u015ft\u0131r\u0131r ve bunlar\u0131 modelle kar\u015f\u0131la\u015ft\u0131r\u0131rd\u0131k.<\/span><\/p>\n

Bununla birlikte, bir makalenin at\u0131f dinami\u011fi, kolayca deterministik ve stokastik bile\u015fenlere ayr\u0131\u015ft\u0131r\u0131lamayan, homojen olmayan ayr\u0131k stokastik bir s\u00fcre\u00e7tir. Modelle anlaml\u0131 bir kar\u015f\u0131la\u015ft\u0131rma yapmak i\u00e7in a\u015fa\u011f\u0131daki stratejiyi benimsedik.<\/span><\/p>\n

Web of Science veri taban\u0131n\u0131 kullanarak, bir alanda ayn\u0131 y\u0131l yay\u0131nlanan \u00e7ok say\u0131da makaleyi de\u011ferlendirdik ve at\u0131f dinamiklerini \u00f6l\u00e7t\u00fck. Modelimiz \u00e7er\u00e7evesinde bu setteki ka\u011f\u0131tlar sadece uygunluklar\u0131 ile farkl\u0131l\u0131k g\u00f6stermektedir.<\/span><\/p>\n

Daha sonra, ayn\u0131 say\u0131da makale ve ayn\u0131 uygunluk da\u011f\u0131l\u0131m\u0131na sahip sentetik bir set tasarlad\u0131k ve modele dayal\u0131 at\u0131f dinamiklerinin say\u0131sal sim\u00fclasyonlar\u0131n\u0131 ger\u00e7ekle\u015ftirdik. Ger\u00e7ek ve sentetik setler aras\u0131ndaki kar\u015f\u0131la\u015ft\u0131rma birka\u00e7 boyutta ger\u00e7ekle\u015ftirildi:<\/span><\/p>\n

1. K\u00fcm\u00fclatif at\u0131f da\u011f\u0131l\u0131mlar\u0131.<\/span>
\n2. Bireysel makalelerin al\u0131nt\u0131 yollar\u0131.<\/span>
\n3. At\u0131f yollar\u0131n\u0131n otokorelasyon.<\/span>
\n4. At\u0131f dinami\u011finin ortalama ve de\u011fi\u015fken bile\u015fenleri.<\/span>
\n5. At\u0131f yap\u0131lmam\u0131\u015f makale say\u0131s\u0131.<\/span><\/p>\n

At\u0131f Da\u011f\u0131l\u0131mlar\u0131<\/span><\/strong><\/h3>\n

Yay\u0131nlanan 40.195 Fizik makalesi dizisi i\u00e7in al\u0131nt\u0131 da\u011f\u0131l\u0131mlar\u0131n\u0131 g\u00f6sterir. Modelimizi kullanarak bu da\u011f\u0131l\u0131mlar\u0131 sim\u00fcle etmek i\u00e7in, her bir ka\u011f\u0131d\u0131n uygunlu\u011fu bilinmelidir. Prensip olarak, do\u011frudan al\u0131nt\u0131lar\u0131n dinamikleri izlenerek \u00f6l\u00e7\u00fclebilir. Asl\u0131nda, do\u011frudan al\u0131nt\u0131lar\u0131n k\u00fcm\u00fclatif say\u0131s\u0131n\u0131 \u00f6\u011frendi\u011fimizde, Kdir(t); ka\u011f\u0131d\u0131n uygunlu\u011fu j ifadesinden bulunabilir.<\/span><\/p>\n

Ancak, Kdir(t)’yi her ka\u011f\u0131t i\u00e7in \u00f6l\u00e7menin \u00e7ok fazla oldu\u011fu kan\u0131tlanm\u0131\u015ft\u0131r.<\/span>\u00a0j t A \u0303(\u03c4)d\u03c4 j 0 karma\u015f\u0131k, dolay\u0131s\u0131yla uygunluk da\u011f\u0131l\u0131m\u0131n\u0131 alternatif bir \u015fekilde bulduk. Stratejimizin temeli, bir makalenin yay\u0131nlanmas\u0131 ile dolayl\u0131 at\u0131flar\u0131n ba\u015flamas\u0131 aras\u0131nda bir gecikme oldu\u011fu g\u00f6zlemidir, dolay\u0131s\u0131yla bir makale taraf\u0131ndan yay\u0131nland\u0131ktan sonraki ilk 2-3 y\u0131l boyunca toplanan al\u0131nt\u0131lar \u00e7o\u011funlukla do\u011frudand\u0131r.<\/span><\/p>\n

Bu nedenle, ayn\u0131 y\u0131l i\u00e7inde yay\u0131nlanan makaleler i\u00e7in, yay\u0131nland\u0131ktan 2-3 y\u0131l sonra at\u0131f da\u011f\u0131l\u0131mlar\u0131 uygunluk da\u011f\u0131l\u0131m\u0131n\u0131 taklit eder (sabit bir fakt\u00f6r i\u00e7inde). Bu erken at\u0131f da\u011f\u0131l\u0131mlar\u0131n\u0131n log-normal’e yak\u0131n oldu\u011funu bulduk. Bunu g\u00f6z \u00f6n\u00fcnde bulundurarak, model sim\u00fclasyonunu 40.195 ka\u011f\u0131t i\u00e7in log-normal uygunluk ile \u00e7al\u0131\u015ft\u0131rd\u0131k.<\/span><\/p>\n

Amac\u0131m\u0131z t = 2 i\u00e7in \u00f6l\u00e7\u00fclen at\u0131f da\u011f\u0131l\u0131m\u0131na en uygun olan\u0131 elde etmekti. Sim\u00fclasyonun di\u011fer parametreleri a\u015fa\u011f\u0131daki gibiydi. Dolayl\u0131 referanslar ve al\u0131nt\u0131lar \u00f6l\u00e7\u00fcmlerimizde oldu\u011fu gibi \u03b3 = 1,2 yr-1 kulland\u0131k.<\/span><\/p>\n

nnn (t ) ve m(t ) ba\u011f\u0131ml\u0131l\u0131klar\u0131n\u0131n ayn\u0131 oldu\u011funu, yani nnn (t ) = m(t ) oldu\u011funu varsayd\u0131k; burada s = 1.2, ikinci nesil al\u0131nt\u0131 makalesini \u00f6nc\u00fcl\u00fcne ba\u011flayan iki sekmeli yollar\u0131n ortalama s say\u0131s\u0131d\u0131r. . \u015eekil 5.2, \u00f6l\u00e7\u00fclen ve sim\u00fcle edilmi\u015f at\u0131f da\u011f\u0131l\u0131mlar\u0131 aras\u0131nda m\u00fckemmel bir uyum oldu\u011funu g\u00f6stermektedir.<\/span><\/p>\n

\n

Monte Carlo sim\u00fclasyonu Ders Notlar\u0131<\/span>
\nMonte Carlo Sim\u00fclasyonu<\/a> \u00f6rnekleri<\/span>
\nSastry sim\u00fclasyon modeli<\/span>
\nMonte Carlo Sim\u00fclasyonu \u00f6rnek soru<\/span>
\nMonte Carlo sim\u00fclasyonu uygulama ad\u0131mlar\u0131<\/span>
\nMonte Carlo sim\u00fclasyonu nedir<\/span>
\nMonte Carlo Sim\u00fclasyonu Excel \u00f6rnek<\/span>
\nMonte Carlo Sim\u00fclasyonu Python<\/span><\/p>\n

\n

At\u0131f Y\u00f6r\u00fcngeleri<\/span><\/strong><\/h3>\n

Model, at\u0131f da\u011f\u0131l\u0131mlar\u0131n\u0131 m\u00fckemmel bir \u015fekilde yakalasa da, farkl\u0131 at\u0131f y\u00f6r\u00fcngeleri ayn\u0131 at\u0131f da\u011f\u0131l\u0131mlar\u0131 setini verebilece\u011finden, bu t\u00fcr do\u011frulama hala yetersizdir. Modelimizi daha fazla do\u011frulamak i\u00e7in \u00f6l\u00e7\u00fclen ve sim\u00fcle edilen al\u0131nt\u0131 y\u00f6r\u00fcngelerini kar\u015f\u0131la\u015ft\u0131rd\u0131k. Makalelerin al\u0131nt\u0131 dinamiklerinin, ge\u00e7mi\u015f dalgalanmalar\u0131 g\u00fc\u00e7lendiren, kendi kendini heyecanland\u0131ran bir Hawkes s\u00fcrecini takip etti\u011fine dikkat edilmelidir.<\/span><\/p>\n

Bu nedenle, ayn\u0131 ba\u015flang\u0131\u00e7 ko\u015fullar\u0131 i\u00e7in bile, sim\u00fcle edilmi\u015f at\u0131f y\u00f6r\u00fcngelerinin da\u011f\u0131l\u0131m\u0131 o kadar geni\u015ftir ki, \u00f6l\u00e7\u00fclen ve sim\u00fcle edilen y\u00f6r\u00fcngelerin ka\u011f\u0131t baz\u0131nda kar\u015f\u0131la\u015ft\u0131r\u0131lmas\u0131 anlams\u0131zd\u0131r. Bu nedenle, benzer makale gruplar\u0131 i\u00e7in al\u0131nt\u0131 y\u00f6r\u00fcngelerini kar\u015f\u0131la\u015ft\u0131rd\u0131k.<\/span><\/p>\n

Uzun zaman s\u0131n\u0131r\u0131nda ayn\u0131 say\u0131da al\u0131nt\u0131 toplayan makale gruplar\u0131 i\u00e7in al\u0131nt\u0131 y\u00f6r\u00fcngelerini g\u00f6sterin. Her set i\u00e7in ortalama al\u0131rsak, \u00f6l\u00e7\u00fclen ve sim\u00fcle edilmi\u015f ortalama at\u0131f y\u00f6r\u00fcngeleri iyi bir uyum i\u00e7indedir.<\/span><\/p>\n

Dolayl\u0131 al\u0131nt\u0131lar\u0131n olas\u0131l\u0131\u011f\u0131 i\u00e7in ampirik fonksiyon, P0(K)e\u2212\u03b3(t\u2212\u03c4), sadece modelin benzer makalelerin ortalama al\u0131nt\u0131 dinamiklerine uymas\u0131 gereklili\u011finden kuruldu\u011fu i\u00e7in bu beklenmedik bir durum de\u011fildir. Farkl\u0131 y\u00f6r\u00fcnge k\u00fcmeleri ayn\u0131 ortalama y\u00f6r\u00fcngeye sahip olabilir, bu nedenle bireysel makalelerin \u00f6l\u00e7\u00fclen ve sim\u00fcle edilmi\u015f al\u0131nt\u0131 y\u00f6r\u00fcngelerinin \u015fekillerinin kar\u015f\u0131la\u015ft\u0131r\u0131lmas\u0131, ortalaman\u0131n \u00f6tesinde ayr\u0131 bir hikaye anlat\u0131r.<\/span><\/p>\n

D\u00fc\u015f\u00fck ve orta derecede al\u0131nt\u0131 yap\u0131lan makaleler i\u00e7in, \u00f6l\u00e7\u00fclen ve sim\u00fcle edilen y\u00f6r\u00fcngelerin \u00e7ok benzer oldu\u011funu g\u00f6sterir – a\u015fa\u011f\u0131 yukar\u0131 ayn\u0131 boyut ve s\u00fcreye sahip dalgalanmalar sergilerler. Y\u00fcksek oranda at\u0131f yap\u0131lan makaleler i\u00e7in her iki y\u00f6r\u00fcnge setinin de p\u00fcr\u00fczs\u00fcz oldu\u011funu, ancak \u00f6l\u00e7\u00fclen y\u00f6r\u00fcngelerin yay\u0131lmas\u0131n\u0131n sim\u00fcle edilmi\u015f olanlardan daha fazla oldu\u011funu g\u00f6sterir.<\/span><\/p>\n

Sim\u00fclasyon, al\u0131nt\u0131 y\u00f6r\u00fcngelerinde \u00f6nemli bir da\u011f\u0131l\u0131m sa\u011flasa da, “uyuyan g\u00fczel” veya “kayan y\u0131ld\u0131z” gibi a\u015f\u0131r\u0131 durumlar\u0131 iyi bir \u015fekilde yeniden \u00fcretmez. Bu \u00f6d\u00fcllendirici \u00e7\u00fcnk\u00fc bilimin \u00f6ng\u00f6r\u00fclemezli\u011fi onu e\u011flenceli k\u0131lan en \u00f6nemli fakt\u00f6rlerden biridir. (Asl\u0131nda, model “uyuyan g\u00fczelleri” yeniden \u00fcretir, ancak bunlar \u00e7ok nadirdir, oysa ger\u00e7ekte \u00e7ok daha s\u0131kt\u0131rlar.)<\/span><\/p>\n

\u00c7o\u011fu makale i\u00e7in model, al\u0131nt\u0131 yollar\u0131n\u0131n \u015feklini ve d\u00fczg\u00fcnl\u00fc\u011f\u00fcn\u00fc do\u011fru bir \u015fekilde tahmin eder.\u00a0Bununla birlikte, model, al\u0131nt\u0131 kariyerinin ba\u015flang\u0131c\u0131nda olduk\u00e7a pop\u00fcler olan ancak k\u0131sa s\u00fcre sonra ilgisinin kayboldu\u011fu gibi a\u015f\u0131r\u0131 durumlar iyi kar\u015f\u0131lanmaz.<\/span><\/p>\n

\n\n
<\/div>\n\n<\/div>\n \n