Analysis of Construction Productivity by using Soft Computing Tools - A Review

Abstract

The aim of this paper is to outline the process for creating activity construction labour productivity models in order to to improve the labour productivity level problems. Through a rigorous site supervision and site training, 38 days data collection was done and different elements of building construction were examined for this purpose. The regression analysis was done and the results are shown below. The findings of this analysis may provide construction organizations with insight into how to prioritize and execute the usage of soft computing technologies inside their operations.

Introduction

Construction labor productivity in India is mainly influenced by worker productivity, which is affected by low skill levels due to limited formal training. States like Gujarat and Maharashtra show high productivity, while West Bengal and Odisha have low productivity. Factors influencing labor productivity fall into three categories:

1. Management factors (team, equipment, materials, scheduling, etc.)

2. Project parameters (design, crew size, site conditions, weather)

3. Labor variables (morale, rewards, absenteeism, skill quality).

Productivity models are essential for planning, estimating, and scheduling construction projects to reduce labor costs and project duration. However, existing models often consider only one variable and lack comprehensive data.

Need for study:
The construction sector is labor-intensive and faces slow productivity growth compared to other industries. Labor costs account for 33-50% of project expenses, making productivity improvements critical for profitability.

Objectives:

• Review research on construction productivity.

• Identify key issues affecting productivity.

Literature review highlights:

• Adoption of technology (IT, digitalization) improves job satisfaction and productivity.

• Small and medium enterprises (SMEs) in construction lag in ICT adoption but can benefit from innovation.

• Digitalization and automation vary across project phases, with Building Information Modeling (BIM) aiding planning and design.

• Machine learning models (GRNN, SVM, Random Forest) effectively predict labor productivity.

• Factors like worker age, education, skills, and experience significantly impact productivity.

• No universal productivity definition exists; benchmarking and advanced modeling can improve understanding and project performance.

Conclusion

1) According to Ghalia and Sweis, making wise investments in the technology sector might lead to increased employee work satisfaction. 2) Mlybari estimated construction labor productivity using a variety of methods, and the GRNN model often provides the best answer for steel fixing. pouring and completing concrete, however SVM and RF were shown to be highly effective in assessing construction labor productivity by Momade, Shamsuddin, Hainin, Nashwan, and Umar. 3) According to Sawhney, Mukherjee, Rahimian, and Goulding, the construction industry\'s inadequate usage of ICT has a detrimental impact on several businesses. 4) While Shehata & El-Gohary claim that there is no universally accepted definition of productivity, Ahuja, Yang, and Shankar examined the use of analysis of quantitative data and questionnaire survey, the extent to which formal project management practices are used, and the significance of ICT in construction presented.

References

[1] Ahuja Vanita, Yang Jay, and Shankar Ravi, “Study of ICT adoption for building project management in the Indian construction industry”, Automation in Construction, Vol. 18, Issue 2, pp. 415 - 423, 2009. [2] Bartake Monali, Patil Y. S. and Swamy R. M., “Study of Barriers in Implementing ICT in Indian Construction Industry”, International Journal of Research and Scientific Innovation, Vol. 6, Issue 11, pp. 149 - 152, 2019. [3] Begi? Hana, Gali? Mario and Dola?ek-Alduk Zlata, “Digitalization and Automation in Construction Projects Life-cycle: A review”, Journal of Information Technology in Construction, Vol. 27, Issue 10, pp. 441 - 460, 2022. [4] Cherian Tisha Meriam and Kumaran L. Aravindh, “E-Business in Construction Industry: Opportunities and Challenges”, Indian Journal of Science and Technology, Vol. 9, Issue 32, pp. 1 - 6, 2016. [5] Gaith Farag H., Ismail Amiruddin and R. Khalim A, “Application and Efficacy of information technology in construction industry”, Scientific Research and Essays, Vol. 7, Issue 38, pp. 3223 - 3242, 2012. [6] Ghalia A. and Sweis Rateb J., “The relationship between information technology adoption and job satisfaction in contracting companies in Jordan”, Journal of Information Technology in Construction, Vol. 15, Issue 7, pp. 44 - 63, 2010. [7] Kasim N. B. and Soon Peniel Ang Ern, “The Awareness of ICT Implementation for Materials Management in Construction Projects”, International Journal of Computer and Communication Technology, Vol. 2, Issue 3, pp. 158 - 168, 2011. [8] Kasim Narimah, “Implementation for Materials Management in Construction Projects: Case Studies”, Journal of Construction Engineering and Project Management, Vol. 1, Issue 1, pp. 31 - 36, 2011. [9] Mlybari Ehab A., “Application of Soft Computing Techniques to Predict Construction Labour Productivity in Saudi Arabia”, International Journal of GEOMATE, Vol. 19, Issue 71, pp. 203 - 210, 2020. [10] Momade Mohammed Hamza, “Modelling labour productivity using SVM and RF: a comparative study on classifiers performance”, International Journal of Construction Management, Vol. 2, Issue 4, pp. 1238 - 1240, 2020. [11] Sawhney Anil, “Scenarioe thinking approach for leveraging ICT to support SMEs in the Indian construction industry”, Procedia Engineering, Vol. 85, Issue 4, pp. 446 - 453, 2014. [12] Shehata Mostafa E. and El-Gohary Khaled M., “Towards improving construction labor productivity and projects’ performance”, Alexandria Engineering Journal, Vol. 50, Issue 3, pp. 321- 330, 2011. [13] Sonmez Rifat, “Construction labor productivity modelling with neural networks and regression analysis”, Retrospective Theses and Dissertations, 1996. [14] Sreelakshmi S., “STUDY ON THE BARRIERS TO THE IMPLEMENTATION OF BUILDING INFORMATION MODELING”, International Journal of Civil Engineering and Technology, Vol. 8, Issue 5, pp. 42 - 50, 2017. [15] Taher Ghada, “Industrial Revolution 4.0 in the Construction Industry: Challenges and Opportunities”, Management Studies and Economic Systems, ASCE, Vol. 6, Issue 4, pp. 109 - 127, 2021. [16] Allmon, Hass, Borcherding, and Goodrum, “U.S. Construction labor productivity trends”, Journal of Construction Engineering and Management, Vol. 7, Issue 3, pp. 97 - 104, 1998. [17] Bernstein H., “Measuring Productivity: An Industry Challenge”, Journal of Civil Engineering, Vol. 73, Issue 12, pp. 46 - 53, 2003. [18] Caldas, C., Grau, D., and Haas, C., “A Review on Delay in Construction of Highway with a Case Study of Samruddhi Highway”, Journal of Construction Engineering and Management, Vol. 132, Issue 7, pp. 741 - 749, 2006. [19] Goodrum, P. and Haas, C., “Partial Factor Productivity and Equipment Technology Change at the Activity Level in the U.S. Construction Industry”, Journal of Construction Engineering and Management, Vol. 128, Issue 6, pp. 463 - 472, 2002.

Copyright

Copyright © 2025 Urvi Dusane, Ajay Shelorkar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.