Supervised vs. unsupervised learning for construction crew productivity prediction

Oral, Mustafa; Oral, Emel Laptalı; Aydın, Ahmet

doi:10.1016/j.autcon.2011.09.002

Cited by 27 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLP network usually consists of three layers; input, hidden and output (Oral et al 2012). Input layer contains as many neurons as the number of parameters affecting the problem.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Multi Layer Perceptron (Mlp) and Radial Basis Function (Rbf) for Construction Cost Estimation: The Case of Turkey

Bayram

Öçal

Oral

et al. 2015

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

In Turkey, for the preliminary construction cost estimation, a notice, which is updated and published annually by Turkish Ministry of the Environment and Urbanism, known as “unit area cost method” (UACM) is generally employed. However, it’s known that the costs obtained through this method in which only construction area is taken into consideration have significant differences from actual costs. The aim of this study is to compare the cost estimations obtained through “multi layer perceptron” (MLP) and “radial basis function” (RBF), which are commonly used artificial neural network (ANN) methods. The results of MLP and RBF were also compared with the results of UACM and the validity of UACM was interpreted. Dataobtained from 232 public construction projects, which completed between 2003 and 2011 in different regions of Turkey, were reviewed. Consequently, estimated costs obtained from RBF were found to be higher than the actual costs with a 0.28% variance, while the estimated costs obtained from MLP were higher than actual values with a 1.11% variance. The approximate costs obtained from UACM are higher than actual costs with a 28.73% variance. It was found that both ANN methods were showed better performance than the UACM but RBF was superior to MLP.

show abstract

“…MLP network usually consists of three layers; input, hidden and output (Oral et al 2012). Input layer contains as many neurons as the number of parameters affecting the problem.…”

Section: Methodsmentioning

confidence: 99%

“…One hidden layer is usually sufficient for nearly all problems. The number of the neurons in the hidden layer(s) should be selected arbitrarily (Oral et al 2012). A neuron has a logistic activation function in the hidden layer(s) and linear activation function in the output layer (Kangilaski 2002;Oral et al 2012).…”

Section: Methodsmentioning

confidence: 99%

Comparison of Multi Layer Perceptron (Mlp) and Radial Basis Function (Rbf) for Construction Cost Estimation: The Case of Turkey

Bayram

Öçal

Oral

et al. 2015

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

show abstract

“…Many ANN algorithms, such as feed forward neural networks (FFNN), radial basis neural network (RBNN), dynamic networks, learning vector quantization (LVQ) and self-organizing map (SOM) have been adopted in research studies, while being defined at different levels of abstraction, and modelled with a focus on different aspects of neural systems (Hancock 1995;Sudheer, Jain 2003, Oral et al 2012. For this research study, we chose two supervised techniques; the feed forward neural network (FFNN), and the radial basis neural network (RBNN).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Construction labour productivity is one of the most crucial factors affecting the overall performance of any construction project, whether large or small. In recent years, there have been numerous investigations dealing with labour productivity in construction, many of which are related to the quantification of the impact of productivity factors (Kazaz, Ulubeyli 2004;Fayek, Oduba 2005;Ayman et al 2008;Rateb et al 2009;Oral et al 2012). The factors affecting productivity may differ from project to project.…”

Section: Introductionmentioning

confidence: 98%

Modelling Masonry Crew Productivity Using Two Artificial Neural Network Techniques

Gerek

Erdiş

Mıstıkoğlu

et al. 2014

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

Artificial neural networks have been effectively used in various civil engineering fields, including construction management and labour productivity. In this study, the performance of the feed forward neural network (FFNN) was compared with radial basis neural network (RBNN) in modelling the productivity of masonry crews. A variety of input factors were incorporated and analysed. Mean absolute percentage error (MAPE) and correlation coefficient (R) were used to evaluate model performance. Research results indicated that the neural computing techniques could be successfully employed in modelling crew productivity. It was also found that successful models could be developed with different combinations of input factors, and several of the models which excluded one or more input factors turned out to be better than the baseline models. Based on the MAPE values obtained for the models, the RBNN technique was found to be better than the FFNN technique, although both slightly overestimated the masons' productivity.

show abstract

“…Artificial neural network methodologies, such as Feed Forward Neural Network (FFNN), Radial Basis Neural Network (RBNN), and Self Organizing Maps (SOM) were employed to model the relationship between the productivity output and selected input factors. The results of these studies have been disseminated in (Oral et al 2008(Oral et al , 2012Oral, E. L., Oral, M. 2010;Gerek et al 2014). This paper extends this work into the use of DEA for evaluating the performance of the plastering crews in terms of both productivity and efficiency, and then supplementing the findings by applying cross tabulation analysis.…”

Section: Introductionmentioning

confidence: 78%

Evaluation of Plastering Crew Performance in Building Projects Using Data Envelopment Analysis

Gerek

Erdiş

Mıstıkoğlu

et al. 2014

Technological and Economic Development of Economy

View full text Add to dashboard Cite

The research question addressed in this study was how the performance of construction crews working in a certain project or locality could be evaluated, ranked and improved. To develop and demonstrate the relevant framework, data envelopment analysis (DEA) was applied to establish the relative efficiency of plastering crews working in building projects located in different cities around Turkey. Data were collected from 40 crews of varying characteristics, and their technical efficiency scores were computed using the Banker, Charnes and Cooper (BCC) model, which is based on variable returns-to-scale (VRS). The model yields efficiency scores that range between 0 and 1, and a company or crew is considered efficient if its score is 1.0 (100%). Efficient and inefficient crews were identified and ranked on this basis in the study. Cross tabulation analyses were subsequently conducted to gain further insights into the relationships between the efficiency scores and input factors of numbers of skilled and unskilled laborers, daily labor unit costs, work hours, average age of crew members, total crew experience, plastering location, plastering technique, and plaster type. No discernible relationship could be identified between the efficiency scores and productivity outputs of the crews. It was found that plastering technique, plastering location, and total crew experience had a significant association with crew efficiency. Efficiency improvement strategies identified included training, hiring experienced plasterers, adopting more advanced plastering technology, implementing better jobsite management practices, and enhancing workers’ knowledge, skills and attitude towards productivity and quality.

show abstract

Supervised vs. unsupervised learning for construction crew productivity prediction

Cited by 27 publications

References 22 publications

Comparison of Multi Layer Perceptron (Mlp) and Radial Basis Function (Rbf) for Construction Cost Estimation: The Case of Turkey

Comparison of Multi Layer Perceptron (Mlp) and Radial Basis Function (Rbf) for Construction Cost Estimation: The Case of Turkey

Modelling Masonry Crew Productivity Using Two Artificial Neural Network Techniques

Evaluation of Plastering Crew Performance in Building Projects Using Data Envelopment Analysis

Contact Info

Product

Resources

About