Modelling labour productivity using SVM and RF: a comparative study on classifiers performance

Momade, Mohammed Hamza; Shahid, Shamsuddin; Hainin, Mohd Rosli; Nashwan, Mohamed Salem; Umar, Abdulhakim Tahir

doi:10.1080/15623599.2020.1744799

Cited by 28 publications

(27 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their model identified various sources of uncertainty affecting prediction. Momade et al [35] proposed a data-driven approach, using support vector machine (SVM) and random forest (RF) to model and predict CLP. Their results showed that SVM achieved a higher rate of accuracy, compared to RF.…”

Section: Literature Review On Construction Productivity Modelingmentioning

confidence: 99%

“…Another algorithm that shows accurate performance in a number of studies in other disciplines is RF, which was developed and compared with the other techniques in this study. Results from past studies show that RF is highly capable of solving non-linear classification problems, compared to other ML models [35]. As most crucial factors related to CLP do not follow a normal distribution, RF is a common ML technique in modeling construction productivity [57].…”

Section: Clp Predictive Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Artificial Intelligence HFS-RF-PSO Model for Construction Labor Productivity Prediction and Optimization

2021

View full text Add to dashboard Cite

This paper presents a novel approach, using hybrid feature selection (HFS), machine learning (ML), and particle swarm optimization (PSO) to predict and optimize construction labor productivity (CLP). HFS selects factors that are most predictive of CLP to reduce the complexity of CLP data. Selected factors are used as inputs for four ML models for CLP prediction. The study results showed that random forest (RF) obtains better performance in mapping the relationship between CLP and selected factors affecting CLP, compared with the other three models. Finally, the integration of RF and PSO is developed to identify the maximum CLP value and the optimum value of each selected factor. This paper introduces a new hybrid model named HFS-RF-PSO that addresses the main limitation of existing CLP prediction studies, which is the lack of capacity to optimize CLP and its most predictive factors with respect to a construction company’s preferences, such as a targeted CLP. The major contribution of this paper is the development of the hybrid HFS-RF-PSO model as a novel approach for optimizing factors that influence CLP and identifying the maximum CLP value.

show abstract

Section: Literature Review On Construction Productivity Modelingmentioning

confidence: 99%

Section: Clp Predictive Modelingmentioning

confidence: 99%

Hybrid Artificial Intelligence HFS-RF-PSO Model for Construction Labor Productivity Prediction and Optimization

2021

View full text Add to dashboard Cite

show abstract

“…The construction industry plays a vital and effective role in both developed and developing countries ( [1][2][3], and considered as one of the most labour-intensive industries all over the world [4]; this is because it has a dynamic nature and easily relates to other sectors in the economy [5,2,6]. The construction industry plays a key role all over the world as it accounts for a large proportion of the country's total employment and makes a significant contribution to a country's overall income.…”

Section: Introductionmentioning

confidence: 99%

“…The construction industry plays a key role all over the world as it accounts for a large proportion of the country's total employment and makes a significant contribution to a country's overall income. For instance, [5,7,8] reported that construction industry offers employment to people and a better quality of life to countries and positively associated with the success and progress of any economy. One of the most important factors affecting construction industry's growth is productivity and it is associated with the labour performance.…”

Section: Introductionmentioning

confidence: 99%

“…10 years and above [ ] Appendix B Listed below is series of factors (management; material; design and technical; supervision; labour; equipment; policy, political and legal; environmental; and motivational factors) With respect to your own point of view, please indicate the degree of your agreement or disagreement with each statement by marking. Strongly disagree (1) disagree (2) neutral (3) agree (4) and strongly agree(5).…”

mentioning

confidence: 99%

See 1 more Smart Citation

The Factors Affecting Labour Productivity in the Construction of Prestressed Concrete Buildings in Ghana

Akbar¹,

Darkwah²,

Amin³

et al. 2021

Preprint

View full text Add to dashboard Cite

The construction industries face several challenges related to productivity. Productivity mainly depends upon labour effort and performance. The poor productivity of labour is one of the major reasons of time over-runs and increasing cost in construction projects. Our study aims to build a comprehensive assessment on the relationship between various factors that affect labour productivity in the construction of prestressed concrete Buildings in Ghana. A sample of 200 re-spondents collected from workers of Construction Company in Ghana. The questionnaire was designed which comprises two parts; the first part contains background information of the staff of construction company while second section explores the opinion of the staff regarding factors af-fecting labour productivity. The Smart-PLS was utilized to analyze and estimate the relationship among construct variables. By utilizing relative importance index and multiple linear regressions, it is identified that the management factor such as inadequate incentives; material factor such as poor quality of material; labour factors such as poor quality and training of labors; supervision factor such as incompetence of site supervisor; equipment factor such as frequent damage of equipment have a negative and significant relationship with labour productivity in the construc-tion of prestressed concrete buildings in Ghana. The findings of this study recommend that in order to improve labour productivity, the construction industries must conduct labour productivity measurements by adopting schedule for procurement of materials, safety programs, motivational system, and frequent meeting with project professionals.

show abstract

Using Hybrid Artificial Intelligence Optimization Method to Predict Construction Labour Productivity

Efekan,

Celik,

Tokdemir

2023

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

Modelling labour productivity using SVM and RF: a comparative study on classifiers performance

Cited by 28 publications

References 70 publications

Hybrid Artificial Intelligence HFS-RF-PSO Model for Construction Labor Productivity Prediction and Optimization

Hybrid Artificial Intelligence HFS-RF-PSO Model for Construction Labor Productivity Prediction and Optimization

The Factors Affecting Labour Productivity in the Construction of Prestressed Concrete Buildings in Ghana

Using Hybrid Artificial Intelligence Optimization Method to Predict Construction Labour Productivity

Contact Info

Product

Resources

About