Modelling construction labour productivity using evolutionary polynomial regression

Golnaraghi, Sasan; Moselhi, Osama; Alkass, Sabah; Zangenehmadar, Zahra

doi:10.1504/ijpqm.2020.110024

Cited by 3 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2019) specified the R 2 value as 0.85 and the MSE value as 0.018 in the radial basis function neural network model using artificial neural network techniques in their study. Also, Golnaraghi et al. (2020a), in another study, applied the evolutionary polynomial regression model on the same data and found the prediction results R 2 value as 52.69 and MSE value as 0.057.…”

Section: Resultsmentioning

confidence: 94%

“…Golnaraghi et al (2019) specified the R 2 value as 0.85 and the MSE value as 0.018 in the radial basis function neural network model using artificial neural network techniques in their study. Also, Golnaraghi et al (2020a), in another study, applied the evolutionary polynomial regression model on the same data and found the prediction results R 2 value as 52.69 and MSE value as 0.057. In another study conducted in recent years, Cheng et al (2021) tried to predict formwork labor productivity with the symbiotic organism search-optimized least square support vector machine model.…”

Section: Meta-ensemble Machine Learning Modelmentioning

confidence: 94%

“…In addition, when the parameters used in the studies are examined, it is seen that not all parameters are used in the prediction studies to determine labor productivity, because the parameter values to be used must be measurable and useable in prediction models (Heravi and Eslamdoost, 2015). Therefore, the parameters that are frequently used in predicting labor productivity are temperature, humidity, precipitation, wind speed, gang size, labor percentage, work type, floor level and work method (Cheng et al, 2021;Golnaraghi et al, 2019Golnaraghi et al, , 2020a.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Labor productivity plays a fundamental role in building production (Golnaraghi et al, 2020a), because the share of labor productivity is great at every critical stage of the construction process, including cost, time and quality (Al-Zwainy et al, 2013;Mlybari, 2020;Momade et al, 2020). One of the most important reasons for this is that many factors impact labor productivity (Mlybari, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity

Karatas

Budak²

2022

ECAM

View full text Add to dashboard Cite

PurposeThe study is aimed to compare the prediction success of basic machine learning and ensemble machine learning models and accordingly create novel prediction models by combining machine learning models to increase the prediction success in construction labor productivity prediction models.Design/methodology/approachCategorical and numerical data used in prediction models in many studies in the literature for the prediction of construction labor productivity were made ready for analysis by preprocessing. The Python programming language was used to develop machine learning models. As a result of many variation trials, the models were combined and the proposed novel voting and stacking meta-ensemble machine learning models were constituted. Finally, the models were compared to Target and Taylor diagram.FindingsMeta-ensemble models have been developed for labor productivity prediction by combining machine learning models. Voting ensemble by combining et, gbm, xgboost, lightgbm, catboost and mlp models and stacking ensemble by combining et, gbm, xgboost, catboost and mlp models were created and finally the Et model as meta-learner was selected. Considering the prediction success, it has been determined that the voting and stacking meta-ensemble algorithms have higher prediction success than other machine learning algorithms. Model evaluation metrics, namely MAE, MSE, RMSE and R2, were selected to measure the prediction success. For the voting meta-ensemble algorithm, the values of the model evaluation metrics MAE, MSE, RMSE and R2 are 0.0499, 0.0045, 0.0671 and 0.7886, respectively. For the stacking meta-ensemble algorithm, the values of the model evaluation metrics MAE, MSE, RMSE and R2 are 0.0469, 0.0043, 0.0658 and 0.7967, respectively.Research limitations/implicationsThe study shows the comparison between machine learning algorithms and created novel meta-ensemble machine learning algorithms to predict the labor productivity of construction formwork activity. The practitioners and project planners can use this model as reliable and accurate tool for predicting the labor productivity of construction formwork activity prior to construction planning.Originality/valueThe study provides insight into the application of ensemble machine learning algorithms in predicting construction labor productivity. Additionally, novel meta-ensemble algorithms have been used and proposed. Therefore, it is hoped that predicting the labor productivity of construction formwork activity with high accuracy will make a great contribution to construction project management.

show abstract

Section: Resultsmentioning

confidence: 94%

Section: Meta-ensemble Machine Learning Modelmentioning

confidence: 94%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity

Karatas

Budak²

2022

ECAM

View full text Add to dashboard Cite

show abstract

“…Besides the economic contribution, the construction industry also employs with a rate of 7%, 8% and 10.6% in Europe, the United States (US) and Malaysia, respectively (Proverbs et al, 1998;Thieblot, 2002;Najib et al, 2019). However, the contribution is more substantial in developing countries compared to the developed countries (Hussain, 1979;Golnaraghi et al, 2020). Therefore, the construction industry is classified as one of the biggest industry, performing a substantial role in the development of society (Musarat and Ahad, 2016;Alaloul et al, 2020) and is deemed to be most tough, labour demanding and having hazardous working circumstances (Premkumar and Rajkumar, 2015;Alaloul et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Inflation rate and labours’ wages in construction projects: economic relation investigation

Musarat

Alaloul

Liew

2021

ECAM

View full text Add to dashboard Cite

PurposeLabours are one of the key resources of construction projects having a significant impact on economic development. With time, the construction industry is getting a boom due to numerous construction projects in which labours’ contribution is significant. Project betterment is associated with the project productivity which relates to the labours. Wages play a vital role in retaining labours in the construction industry.Design/methodology/approachThis study focuses on investigating the increasing and decreasing behaviour of labour wages in the construction industry and observing the impact of the inflation rate in deviating labour wages. Initially, the percentage deviation was calculated to observe the changing behaviour of the data and then the Spearman correlation test was used to find the relationship between the inflation rate and the labour wages.FindingsIt is evident that even with a good economy and a stable construction sector, still, the labour wages faced a decline over time, which is a matter of concern. Also, based on the correlation coefficient, it was revealed that several labour wages categories are moderately and strongly correlated with the inflation rate and can impact project cost if the inflation rate is not considered while finalizing the budget. Besides that, the changing behaviour of labour wages due to the inflation rate impacts significantly on gross domestic product (GDP); therefore, it requires vital attention.Originality/valueChanges in labour wages are not considered in budget estimation which drag the project towards cost overrun. This study brings the attention of the stakeholders on the issue with experimental justification. Also, how the inflation rate is affecting the labour wages has also been addressed.

show abstract

Productivity Analysis and Associated Risks in Steel Structures

Petroutsatou

Kantilierakis

2023

Buildings

View full text Add to dashboard Cite

Construction can be analyzed at industry, firm, project, and activity/task levels. Given that there are differences between the concepts of productivity and uses of productivity data, depending on the level of analysis, there is no single meaning of construction productivity, except of an output/input ratio. Furthermore, there is little knowledge in the extant literature about steel structure productivity, sustainability, and risks. Moreover, through the investigation of the grey literature, i.e., the national or European reports on construction productivity, the indexes given are at aggregate levels. This paper aims to fill this gap and provide a holistic approach to the levels of productivity, sustainability, and the risks involved in the construction process in several steel structure types from similar projects constructed by a company that has operated within the field of steel structures for several decades. From a homogeneous database of 71 steel structure projects constructed in the last decade, several curves are derived concerning productivity per work phase. For this research, productivity is construed as a ratio of output/(cycle time). Through a literature review and interviews with experienced site engineers, a risk registry was compiled by the authors concerning sixteen (16) risks encountered in the construction process. The TOPSIS multi-criteria analysis program is used for the prioritization of risks and the @RISK program for the probabilistic cost analysis of the identified risks.

show abstract

Modelling construction labour productivity using evolutionary polynomial regression

Cited by 3 publications

References 0 publications

Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity

Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity

Inflation rate and labours’ wages in construction projects: economic relation investigation

Productivity Analysis and Associated Risks in Steel Structures

Contact Info

Product

Resources

About