Abstract
Bu çalışmada,
nüfus artış tahminini yapmak üzere yapay zekanın bir alt disiplini olan genetik
algoritmalardan yararlanılarak .NET ortamında C# programlama dili kullanılarak
görsel ara yüze sahip bir yazılımı geliştirilmiştir. Bu bağlamda TÜİK’ten yıllara göre yapılan sayım bilgileri
baz alınmış ve geliştirilen yazılım sayesinde ileriki yıllar için nüfus artış
tahmini yapılabilmiştir. Çalışma kapsamında, hız ve performans açısından ikili
kodlu genetik algoritma yerine Gerçek Kodlu Genetik Algoritma; seçme
yöntemi olarak da Turnuva Seçim Yöntemi kullanılmıştır.
Çünkü Genetik Algoritmalarda (GA) İkili kodlu
algoritmalar; parametrelerin “1” ve “0” larla ifade edilmesi, kromozomların
boyutlarını oldukça artırdığından sınırlı hassasiyete sahip olmaktadırlar. Oysa
bunun yerine gerçek rakamlarla kodlama yapabilen, gerçek kodlu GA’yı kullanmak
daha avantajlıdır. Gerçek kodlu GA, hem daha hassas hem de PC belleğinde daha
az yer kaplamaktadır. Ayrıca mevcut
yazılımların kullanım karmaşıklığının ve zorluğunun önüne geçmek için
geliştirilen yazılımda, başlangıçta kullanıcı
tarafından popülasyon sayısı, iterasyon sayısı, çaprazlama oranı, mutasyon oranı
ve TÜİK’ten alınmış geçmiş yıllara ait nüfus sayım verileri girişi kullanıcı
tarafından girişi yapıldıktan sonra eldeki veriler doğrultusunda istenen yıla
ait nüfus artış tahmini yapılmaktadır. Bu çalışma kapsamında da TÜİK’ten alınan veriler
kullanılarak öncelikle Türkiye ve Konya ili için 2016 yılı nüfus artış
tahminleri yapılmış ve bu tahmini artış oranı gerçek verilerle
karşılaştırılmıştır. Daha sonra ise Türkiye geneli ve Konya ili için 2020
yılına ait nüfus artış tahmini oranına yer verilmiştir. Ayrıca geliştirilen
yazılım eldeki veriler doğrultusunda kıtalar, ülkeler, şehirler, beldeler ve
hatta köyler için nüfus artış tahmini yapabilecek esneklik ve yapıda
tasarlanmıştır.
Keywords
Yapay Zeka Genetik Algoritma Gerçek Kodlu Genetik Algoritma Nüfus Artış Tahmini C# .NET Görsel Arayüz
References
- [1] Bolat, B., Erol, K. O. ve İmrak, C. E. (2004). “Genetic Algorithms in Engineering Applications and the Function of Operators”. Journal of Engineering and Natural Sciences, ss 264-271.[2] http://www.atasoyweb.net/Genetik-Algoritma, Erişim Tarihi:05.02.2017.[3] Akbari, M., Rashidi, H. And Alizadeh, S. H. (2017). “An Enhanced Genetic Algorithm With New Operators For Task Scheduling In Heterogeneous Computing Systems”. 61, pp 35–46.[4] John H. Holland. Adaptation in Natural and Artificial Systems, 1974.[5] Zhang, K., Du, H. and Feldman, M. V. (2017). “Maximizing influence in a social network: Improved Results Using a Genetic Algorithm”, 478, ss 20–30.[6] http://tr.wikipedia.org/wiki/Genetik_algoritma, Erişim Tarihi:02.01.2017.[7] Cunkaş, M. (2006). Genetik Algoritmalar ve Uygulamaları. Selçuk Üniversitesi, Teknik Eğitim Fakültesi, Konya, ss 1-78.[8] Baker, J.E. (1985). “Adaptive selection methods for Genetic Algorithms”. In Proceedings of the 1st International Conference on Genetic Algorithms and their Applications, pp 101-111, ISBN:0-8058-0426-9. [9] Sivaraj, R. and Ravichandran, T. (2011). “A Review Of Selection Methods In Genetic Algorithm”, International Journal of Engineering Science and Technology (IJEST), 3(5), pp 3792–3797, ISSN : 0975-5462, 3792-3797.
Abstract
In this study, it is aimed to predict population
growth by using software with visual interface C # programming language which
was developed in the .NET environment by making use of genetic algorithms which
is a sub-discipline of artificial intelligence. In this context, based on the
counting information conducted by Turkish Statistical Institute was taken as
basis and the developed software was able to estimate the population growth for
the following years. In the scope of the study, in terms of speed and
performance Genetic Algorithm with Real Coding was used instead of binary coded
genetic algorithm; Tournament Selection Method was used as the selection
method. Because Genetic Algorithms (GA) is binary coded algorithms; the
expression of the parameters with "1" and "0" increases
size of the chromosomes considerably and that results limited sensitivity.
However, it is more advantageous to use genuine coded GA, which can code with
real numbers instead. The real code GA is both more accurate and takes up less
space in the PC memory. In addition, in the developed software in order to
avoid the complexity and difficulties of use of existing software, population
growth forecast is being made initially after user enters the number of
populations, the number of iterations, the crossover rate and the population
counts of previous years information obtained from Turkish Statistical
Institute. Within the context of this study, data collected from Turkish
Statistical Institute for 2016 estimates of population growth were made for
Turkey and Konya provinces and estimated increase rate was compared with the
actual data. The estimated population increase rate for 2020 for Turkey and
Konya province is given thereafter. In addition to that, the developed
software is designed for flexibility and structure that can predict population
growth for continents, countries, cities, borders and even villages with
available data.
Keywords
Artificial Intelligence Genetic Algorithm Genetic Algorithm with Real Coding Population Growth Prediction C #. NET Visual Interface
References
- [1] Bolat, B., Erol, K. O. ve İmrak, C. E. (2004). “Genetic Algorithms in Engineering Applications and the Function of Operators”. Journal of Engineering and Natural Sciences, ss 264-271.[2] http://www.atasoyweb.net/Genetik-Algoritma, Erişim Tarihi:05.02.2017.[3] Akbari, M., Rashidi, H. And Alizadeh, S. H. (2017). “An Enhanced Genetic Algorithm With New Operators For Task Scheduling In Heterogeneous Computing Systems”. 61, pp 35–46.[4] John H. Holland. Adaptation in Natural and Artificial Systems, 1974.[5] Zhang, K., Du, H. and Feldman, M. V. (2017). “Maximizing influence in a social network: Improved Results Using a Genetic Algorithm”, 478, ss 20–30.[6] http://tr.wikipedia.org/wiki/Genetik_algoritma, Erişim Tarihi:02.01.2017.[7] Cunkaş, M. (2006). Genetik Algoritmalar ve Uygulamaları. Selçuk Üniversitesi, Teknik Eğitim Fakültesi, Konya, ss 1-78.[8] Baker, J.E. (1985). “Adaptive selection methods for Genetic Algorithms”. In Proceedings of the 1st International Conference on Genetic Algorithms and their Applications, pp 101-111, ISBN:0-8058-0426-9. [9] Sivaraj, R. and Ravichandran, T. (2011). “A Review Of Selection Methods In Genetic Algorithm”, International Journal of Engineering Science and Technology (IJEST), 3(5), pp 3792–3797, ISSN : 0975-5462, 3792-3797.
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Makaleler(Araştırma) |
| Authors | |
| Publication Date | June 5, 2018 |
| Published in Issue | Year 2018 Volume: 11 Issue: 1 |
Cite
Article Acceptance
Use user registration/login to upload articles online.
The acceptance process of the articles sent to the journal consists of the following stages:
1. Each submitted article is sent to at least two referees at the first stage.
2. Referee appointments are made by the journal editors. There are approximately 200 referees in the referee pool of the journal and these referees are classified according to their areas of interest. Each referee is sent an article on the subject he is interested in. The selection of the arbitrator is done in a way that does not cause any conflict of interest.
3. In the articles sent to the referees, the names of the authors are closed.
4. Referees are explained how to evaluate an article and are asked to fill in the evaluation form shown below.
5. The articles in which two referees give positive opinion are subjected to similarity review by the editors. The similarity in the articles is expected to be less than 25%.
6. A paper that has passed all stages is reviewed by the editor in terms of language and presentation, and necessary corrections and improvements are made. If necessary, the authors are notified of the situation.
.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.