Journals / Çukurova Üniversitesi Mühendislik-Mimarlik Fakültesi Dergisi / 2018 / Cilt: 33 - Sayı: 4

Prediction of Employee Leadership Perception in Construction Management Using Feature Selection with Genetic Algorithm

Genetik Algoritma ile Öznitelik Seçimi Kullanılarak Yapım Yönetiminde Çalışan Liderlik Algısının Tahmini

Pages
97–110
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of the study, after the feature selection was done in the data set prepared to predict the employee leadership perception, Naive Bayes, SMO, MLP, RBF Network, Decision Table and J48 classifiers were run, and it was observed that the accuracy rate with J48 classifier was increased to 78.43% with respect to the raw data set.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Artificial intelligence, which is a scientific basis for rapidly growing commercial technologies and has many application areas, has recently begun to draw attention to its use in construction projects.
📊
Key Findings & Data:In this study, the use of artificial intelligence systems in construction management, which is the basis of construction projects, was examined, and after the literature review was performed in Turkey in particular, the importance of feature selection with genetic algorithm that were successful in the artificial intelligence methods in these reviewed literatures was investigated in classification of employee leadership perception, which has an important place in construction management.
💡
Conclusion & Impact:As a result of the study, after the feature selection was done in the data set prepared to predict the employee leadership perception, Naive Bayes, SMO, MLP, RBF Network, Decision Table and J48 classifiers were run, and it was observed that the accuracy rate with J48 classifier was increased to 78.43% with respect to the raw data set.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Artificial intelligence, which is a scientific basis for rapidly growing commercial technologies and has many application areas, has recently begun to draw attention to its use in construction projects. In this study, the use of artificial intelligence systems in construction management, which is the basis of construction projects, was examined, and after the literature review was performed in Turkey in particular, the importance of feature selection with genetic algorithm that were successful in the artificial intelligence methods in these reviewed literatures was investigated in classification of employee leadership perception, which has an important place in construction management. As a result of the study, after the feature selection was done in the data set prepared to predict the employee leadership perception, Naive Bayes, SMO, MLP, RBF Network, Decision Table and J48 classifiers were run, and it was observed that the accuracy rate with J48 classifier was increased to 78.43% with respect to the raw data set.

Özet

Hızla büyüyen ticari teknolojiler için bilimsel bir temel hazırlayan ve birçok uygulama alanına sahip olan yapay zekânın son zamanlarda inşaat projelerinde de kullanımı dikkat çekmeye başlamıştır. Bu çalışmada, inşaat projelerinin temelini oluşturan yapım yönetimi konusunda yapay zekâ sistemlerinin kullanım alanları incelenmiş olup, Türkiye özelinde literatür taraması gerçekleştirildikten sonra yapım yönetiminde önemli bir yeri olan çalışan liderlik algısının sınıflandırılmasında taranan bu literatürlerde yapay zeka yöntemlerinden başarılı olan genetik algoritma ile öznitelik seçiminin önemi araştırılmıştır. Çalışma sonucunda, çalışan liderlik algısının tahmin edilebilmesi amacıyla hazırlanmış olan veri setinde öznitelik seçimi yapıldıktan sonra Naive Bayes, Destek Vektör Makineleri (SMO), Çok Katmanlı Algılayıcı (MLP), Radyal Tabanlı Fonksiyon Ağları (RBF Network), Karar Tablosu (Decision Table) ve J48 sınıflayıcıları çalıştırılmış, J48 sınıflayıcısı ile doğruluk oranının ham veri setine göre artarak %78,43 olduğu gözlenmiştir.

🔖

Cite This Article

KELEŞ, A. E., KELEŞ, M. K. (2018). Prediction of Employee Leadership Perception in Construction Management Using Feature Selection with Genetic Algorithm. Çukurova Üniversitesi Mühendislik-Mimarlik Fakültesi Dergisi, Cilt: 33 - Sayı: 4, 97–110. https://ajindex.com/articles/350589

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (15)

  1. Adalı, E., 1996.
  2. Üretimde Uzman Sistem Çözümü, Proceedings of the First Turkish Symposium on Intelligent Manufacturing Systems, Sakarya, 525-535.
  3. Kızılkaya, Y.M., Oğuzlar, A., 2018. Bazı Denetimli Öğrenme Algoritmalarının R Programlama Dili ile Kıyaslanması, Karadeniz Uluslararası Bilimsel Dergi, 37(37), 90-98.
  4. Gök, M., 2017. Makine Öğrenmesi Yöntemleri ile Akademik Başarının Tahmin Edilmesi, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 5(3), 139-148.
  5. Steppe, J., Bauer, K.W., 1997.
  6. Feature Saliency Measures, Computers & Mathematics with Applications, 33(8), 109-126.
  7. Tsai, C.F., Chou, J.S., 2011. Data Pre-processing by Genetic Algorithms for Bankruptcy Prediction, 2011 IEEE International Conference on Industrial Engineering and Engineering Management, Singapore, 1780-1783.
  8. Tanyer, A.M., Pekeriçli, M.K., 2008. İnşaat Sektörü İçin Bilgi Teknolojilerindeki Son Gelişmeler, TMH-Türkiye Mühendislik Haberleri, Sayı: 451-2008/5, 21-26. Japan’s Komatsu Selects NVIDIA as Partner for Deploying AI to Create Safer, More Efficient Construction Sites, https://nvidianews.nvidia.com/news/japans-komatsu-selects-nvidia-as-partner-for-deploying-ai-to-create-safer-more-efficient-construction-sites, 27.02.2018, 2017.
  9. Ödünç, B., 2018. Kule Vinçte Yapay Zeka Teknikleri Kullanılıyor, http://www.insaatdunyasi.com.tr/arsiv/yazi/105 -kule-vincte-yapay-zeka-teknikleri-kullaniliyor, 27.02.2018.
  10. Günaydın, H.M., Doğan, S.Z., 2004. A Neural Network Approach for Early Cost Estimation of Structural Systems of Buildings, Int. J. Proj. Manag., 22, 595–602.
  11. Doğan, S.Z., Arditi, D., Günaydın, H.M., 2006. Determining Attribute Weights in a CBR Model for Early Cost Prediction of Structural Systems, J. Constr. Eng. Manag., 132, 1092–1098.
  12. Demirel, Y., 2007. Toplu Konut İnşaat Maliyetlerinin Yapay Sinir Ağları ile Tahmini, J. Fac. Eng. Arch. Selcuk Univ., 22(4). Dikmen, İ., Birgönül, M.T., Han, S., 2007. Using Fuzzy Risk Assessment to Rate Cost Overrun Risk in International Construction Projects, International Journal of Project Management, 25, 494-505.
  13. Uğur, L.O., 2007. Yapı Maliyetinin Yapay Sinir Ağı ile Analizi, Doktora Tezi, Gazi Üniversitesi Fen Bilimleri Enstitüsü, Ankara.
  14. Kuşan, H., Özdemir, İ., 2008. İnşaat Projelerinde Risk Yönetimi ve Yapay Zeka Yöntemlerinin Kullanımı, TMH-Türkiye Mühendislik Haberleri, 451(5), 38-43.
  15. Uğur, L.O., Baykan, U.N., Korkmaz, S., 2011. Yığma Konutların Maliyet Tahmininde Yapay Sinir Ağlarının (YSA) Kullanılması, 6. İnşaat Yönetimi Kongr