Predictive model for construction labour productivity using hybrid feature selection and principal component analysis

Abstract

Construction labour productivity (CLP) is affected by numerous variables made up of subjective and objective factors. Thus, CLP modeling and prediction is a complex task, leading to high computational cost and the risk of overfitting of data. This paper proposes a predictive model for CLP by integrating hybrid feature selection (HFS), as a combination of filter and wrapper methods, with principal component analysis (PCA). This developed HFS-PCA method reduces the dimensionality and complexity of CLP data and obtains better prediction performance by identifying the most predictive factors. Identified factors are utilized as inputs for various classification methods to predict CLP. Finally, prediction error of the classification methods with and without using the proposed HFS-PCA method are compared, and the most accurate classification method is selected to develop the CLP predictive model. Experimental results show that using HFS-PCA for CLP prediction leads to better performances compared with past studies.

Identifying the Factors Impacting Bridge Deterioration in the Gulf Cooperation Council

“…Abdelhady and Moselhi [79,80] mentioned that ranking the factors improves the performance of the model's prediction by reducing the dimensionality of the data, computational time and complexity, and memory requirements. Moreover, factor ranking helps in developing more interpretable predictive models and provides better insights into and understanding of the most influential factors affecting bridge deterioration conditions [74,[113][114][115][116]. In this step, the objective of the research will be accomplished by identifying the final ranking of factors that impact bridge deterioration in the GCC.…”

Hybrid feature selection framework for predicting bridge deck conditions

“…Feature selection methods can be clustered into two main categories: filter methods and wrapper methods. It is also worth pointing out that a hybrid of these methods can be utilized (Ebrahimi et al 2022). Filter methods include: t-test, correlation analysis, chi-square test, and principal component analysis; while wrapper methods include: stepwise regression, forward selection, and backward elimination.…”

“…, provide better insights and understanding of the most influential features affecting deck deterioration conditions(Assaad and El-adaway 2020;Ebrahimi et al 2022;Jain et al 2014;Nik-Bakht 2021;Solorio-Fernández et al 2020). Feature selection or selecting significant parameters was employed in different areas, including: selecting the best subset of features for predicting deterioration conditions in NBI data (Althaqafi 2021; Assaad and El-adaway 2020); finding significant parameters impacting construction labour productivity(Ebrahimi et al 2022;Moselhi and Khan 2012); identification of significant impact factors affecting process times at workstations in modular construction(Bhatia et al 2022); and determining the significant design parameters in modular construction workplace that contribute most to ergonomic risk scores(Zaalouk and Han 2021). Age will be derived fro m this variabl e.** This item is calculated b y FHWA and do not has an item number (variable ID) in the Recording and Coding Guide.…”

Exploring Machine Learning Techniques to Maximize Efficiency in Construction Industry Electrical and Electronics Engineering Projects

“…Those factors can lead to schedule delays, finances overruns, and substandard pleasant. Therefore, the trouble announcement for these studies is to investigate how device gaining knowledge of techniques can be hired to cope with those challenges and maximize efficiency in construction enterprise electrical and electronics engineering tasks (Ebrahimi et al, 2022).…”