İnşaat Ekibi Üretkenlik Tahmininde K-En Yakın Komşu ve Genelleştirilmiş Sinir Ağının Performansının Karşılaştırılması

Year 2021, , 131 - 140, 10.05.2021

Okyanus Oral Emel Latali Oral Mehmet Sait Andaç

https://doi.org/10.21605/cukurovaumfd.933867

Cited By: 1

Abstract

İnşaat işlerinde ekip verimliliğinin tahmini, inşaat süresi ve maliyetinin gerçekçi tahminini etkileyen en önemli faktörlerden biridir. Ekip verimliliği tahmini için İleri Besleme Sinir Ağı, Karınca Kolonisi, Yapay Arı Kolonisi, Parçacık Sürü Optimizasyonu, Radyal Tabanlı Sinir Ağları ve Kendi Kendini Düzenleyen Haritalar gibi farklı arama algoritmalarının kullanımı önceki çalışmalarda tartışılmıştır. Ancak, bu çalışmalarda tahmin performansında kullanılan yöntemin özellikleri ile verinin niteliği arasındaki tutarlılığın etkisi genellikle ihmal edilmiştir. Dolayısıyla mevcut araştırmanın amacı, iki çağdaş öğrenme algoritması olan K- En Yakın Komşu (K-NN) ve Genelleştirilmiş Sinir Ağı (GRNN) kullanılarak farklı dağılım özelliklerine sahip üç farklı ekibe (kalıp, döşeme ve duvar) ait verimlilikle ilgili veri seti için tahmin performansını analiz etmektir. Her iki yöntemin performansı da, değerlerin değişen katsayıları için farklılık göstermiştir. K-NN, tüm veri setleri için GRNN'den daha iyi performans göstermiş olup, her iki yöntem de en yüksek varyansa sahip veri kümesinde en kötü performansa sahiptir.

Keywords

İnşaat ekibi, Verimlilik, Yapay sinir ağları, K-en yakın komşu, Genelleştirilmiş sinir ağı

Comparison of the Performance of K-Nearest Neighbours and Generalized Neural Network in Construction Crew Productivity Prediction

Abstract

Construction crew productivity prediction is one of the most important issues that affect the realistic prediction of construction duration and cost. Use of different search algorithms like Feed Forward Neural Network, Ant Colony, Artificial Bee Colony, Particle Swarm Optimization, Radial Based Neural Networks and Self Organizing Maps for crew productivity prediction problem have been discussed in previous studies. However, the significant effect of the coherence between the nature of the data and the characteristics of the method used in prediction performance has generally been neglected. The aim of the current research thus has been to analyse the prediction performance of two contemporary learning algorithms; K- Nearest Neighbour (K-NN) and Generalized Neural Network (GRNN) when applied to three different crew (formwork, tiling and masonry) productivity related data sets with different distribution characteristics. Performance of both methods varied with the changing coefficient of variation values. K-NN outperformed GRNN for all data sets and both of the methods had their worst performance on the dataset with the highest variance.

Keywords

Construction crew, Productivity, Artifical neural networks, K-nearest neighbour, Generalized neural network

References

• 1. McCulloch, W.S., Pitts, W., 1943 Learning Based Industrial Bin-picking Trained with Approximate Physics Simulator. Bull Mat Biophys. 5, 115–133. https://doi.org/10.1007/978-3-030-01370-7_61.
• 2. Portas, J., Abou Rizk, S., 1997. Neural Network Model for Estimating Construction Productivity. J Constr Eng Manag. 123, 399–410. https://doi.org/10.1061/(ASCE)0733- 9364 (1997)123:4(399)
• 3. Sonmez, R., Rowings, J.E., 1998. Construction Labor Productivity Modeling with Neural Network. J Constr Eng Manag, 498–504.
• 4. AbouRizk, S., Knowles, P., Hermann, U.R., 2001. P Roduction R Eport/a Creage R Eport P Roduction R Eport/a Creage R Eport. J Constr Eng Manag. 127, 502–511.
• 5. Dikmen, U.S., Sonmez, M., 2011. An Artificial Neural Networks Model for the Estimation of Formwork Labour. J Civ Eng Manag, 17, 340-347. https://doi.org/10.3846/13923730. 2011.594154.
• 6. Heravi, G., Eslamdoost, E., 2015. Building Information Modeling Education for Construction Engineering and Management. II: Procedures and Implementation Case Study. J Constr Eng Manag. 1–13. https://doi.org/10.1061/(ASCE)CO.1943-7862.
• 7. Dissanayake, M., Fayek, A.R., Russell, A.D., Pedrycz, W., 2005. A Hybrid Neural Network for Predicting Construction Labour Productivity. Proc 2005 ASCE Int Conf Comput Civ Eng. 819–830. https://doi.org/ 10.1061/40794(179)78.
• 8. Oral, M., Oral, E.L., Aydin, A., 2012. Supervised vs. Unsupervised Learning for Construction Crew Productivity Prediction. Autom Constr. 22, 271–276. https://doi.org/10.1016/j.autcon.2011.09.002 Comparison of the Performance of K-Nearest Neighbours and Generalized Neural Network in Construction Crew Productivity Prediction.
• 9. Oral, E.L., Oral, M., 2010. Predicting Construction Crew Productivity by Using Self Organizing Maps. Autom Constr, 19, 791–797. https://doi.org/10.1016/j.autcon.2010.05.001.
• 10. Gerek, I.H., Erdis, E., Mistikoglu, G., Usmen, M., 2015. Modelling Masonry Crew Productivity Using Two Artificial Neural Network Techniques. J Civ Eng Manag, 21, 231–238. https://doi.org/1 0.3846/13923730.2013.802741.
• 11. Oral, E.L., Oral, M., Andaç, M., 2016. Construction Crew Productivity Prediction: Application of Two Novel Methods. Int J Civ Eng, 14, 181–186. https://doi.org/10.1007/ s40999-016-0009-2.
• 12. Andac, M.S., Oral, E., 2019. Crew Productivity Prediction by Using Artificial Bee Colony and Levenberg-Marquardt Algorithms-Compsrion of Performances. Int Civ Eng Archit Conf, 29-44.
• 13. Firat, M., Gungor, M., 2009. Generalized Regression Neural Networks and Feed Forward Neural Networks for Prediction of Scour Depth Around Bridge Piers. Adv Eng Softw, 40, 731-737. https://doi.org/10.1016/j.advengsoft. 2008.12.001.
• 14. Harikumar, S., Aravindakshan Savithri, A., Kaimal, R., 2019. A Depth-based Nearest Neighbor Algorithm for High-dimensional Data Classification. Turkish J Electr Eng Comput Sci, 27, 4082–4101. https://doi.org/10.3906/ELK-1807-163.
• 15. Prasath, S., Abu Alfeilat, H., Lasassmeh, O., Hassanat, A.B.A., Tarawneh, A.S., 2017. Distance and Similarity Measures Effect on the Performance of K-Nearest Neighbor Classifier -A Review. 1–39. https://doi.org/10.1089/big.2018.0175.
• 16. Mulak, P., Talhar, N., 2015. Analysis of Distance Measures Using K-Nearest Neighbor Algorithm on KDD Dataset. Int J Sci Res, 4, 2319–7064.
• 17. Yu, X.G., Yu, X.P., 2008. A New K-nearest Neighbor Searching Algorithm Based on Angular Similarity. Proc 7th Int Conf Mach Learn Cybern ICMLC 3, 1779–1784. https://doi.org/10.1109/ICMLC.2008.4620693.
• 18. A Complete Guide to K-Nearest-Neighbors with Applications in Python and R, https://kevinzakka.github.io/2016/07/13/knearest-neighbor/#more-on-k, Jul 13, 2016.