PurposeThe purpose of this study to apply stacking ensemble machine learning algorithm for predicting the cost of highway construction projects.Design/methodology/approachThe proposed stacking ensemble model was developed by combining three distinct base predictive models automatically and optimally: linear regression, support vector machine and artificial neural network models using gradient boosting algorithm as meta-regressor.FindingsThe findings reveal that the proposed model predicted the final project cost with a very small prediction error value. This implies that the difference between predicted and actual cost was quite small. A comparison of the results of the models revealed that in all performance metrics, the stacking ensemble model outperforms the sole ones. The stacking ensemble cost model produces 86.8, 87.8 and 5.6 percent more accurate results than linear regression, vector machine support, and neural network models, respectively, based on the root mean square error values.Research limitations/implicationsThe study shows how stacking ensemble machine learning algorithm applies to predict the cost of construction projects. The estimators or practitioners can use the new model as an effectual and reliable tool for predicting the cost of Ethiopian highway construction projects at the preliminary stage.Originality/valueThe study provides insight into the machine learning algorithm application in forecasting the cost of future highway construction projects in Ethiopia.
Accurate cost estimates are vital to the effective realisation of construction projects. Extended knowledge, wide-ranging information, substantial expertise, and continuous improvement are required to attain accurate cost estimation. Cost estimation at the preliminary phase of the project is always a challenge as only limited information is available. Hence, rational selection of input variables for preliminary cost estimation could be imperative. A systematic input variable selection approach for preliminary estimating using an integrated methodology of factor analysis and fuzzy AHP is presented in this paper. First, the factor analysis is used to classify and reduce the input variables and their variable coefficients are determined. Second, fuzzy AHP based on the geometric mean method is employed to determine the weights of input variables in a fuzzy environment where the subjectivity and vagueness are handled with natural language expressions parameterized by triangular fuzzy numbers. Then, the input variables are suggested to be selected starting with those having high coefficient and high importance weight. A set of three variables, one from each group, can be added to the estimating model at a time so that the problem of collinearity can vanish and good accuracy of the estimate can be ensured. The proposed approach enables cost estimators to better understand the complete input variable selection process at the early stage of project development and provide a more accurate, rational, and systematic decision support tool.
Nanotechnology is one of the most common areas for current research and development in almost all technological fields. A significant factor is the synergistic benefit of nanoscale dimensions over larger scale alteration. Polymer nanoscience is the analysis and application of nanotechnology to polymer nanoparticle matrices, with nanoparticles described as those with at least one dimension of less than 100 nm. The use of polymer nanotechnology and nanocomposites in practical applications is a rapidly developing area. For making polymeric nanofibers from polymer melts and solutions, a spinning technique is used known as electrospinning. Electrospinning is an easy way to produce ultrafine fibers, which is nanosize. For its wide range of variety of spinning polymeric fibers, it is recommended, as well as producing fibers in nanosize accurately. The aim of this project is to use electrospinning to make nanoclay integrated polycaprolactone membranes. The effects of the nanoclay on morphology, thermal, and sorption behaviors of the electrospun membrane were further studied. The scope of this project work is that the electrospun nanocomposites are best studied for biomedical applications. Because of their influence over porosity, pore size, and fiber diameter, they make excellent scaffold materials.
Self-healing concrete is the ability of concrete to repair its cracks autogenously or autonomously. Since some years ago, several studies have been conducted towards the improvement of self-healing efficiency of cracked concrete structures through various methods for the betterment of its application. However, there is a need to prepare a thorough review report on the factors that affect self-healing efficiency of concrete. This paper focusses a review on several factors that affect the self-repairing efficiency of self-healing smart concrete from the extant recent literature. Based on the review carried out, it can be concluded that formation of CaCO 3 or Ca (OH) 2 in natural process, the dosage of capsule and type of healing agent in chemical process, and the type of bacteria and precipitation of CaCO 3 in biological process of self-healing are the most vivid factors. It can also be summarised as better self-healing efficiency is achieved during early age of concrete, with narrower cracks, higher concentration of Ca 2+ ions, optimum thickness of capsule shell and dosage of capsule.
Background: At the early phase of project development, highway engineering estimators seek to determine the duration of highway construction projects for the purpose of construction planning and administration. Thus, it is vital to study and analyze the estimation accuracy factors of highway construction project duration. In this regard, several studies have been conducted to identify and analyze the estimation accuracy factors of project duration in various ways to improve the estimation and management performance of all the contracting parties. However, very less effort has been devoted to evaluating the duration estimation accuracy factors in the case of the highway construction industry under fuzzy environment. Objective: This paper aims to analyze and prioritize the critical factors that potentially affect the duration estimation accuracy of the highway construction projects in Ethiopia under fuzzy environment. Methods: An extensive review and discussions with highway engineering experts were carried out to explore and identify the duration estimation accuracy factors. The study data collection process consists of two stages. The first stage is to conduct a questionnaire survey. Whereas, the second stage is to carry out the pair-wise comparison matrix to capture the imprecision and vagueness in subjective responses. Then, a λ-cut set method to reduce the initial list of factors and exploratory factor analysis was used to classify the reduced set of factors into smaller groups. Finally, a fuzzy hierarchy process algorithm with the use of triangular fuzzy numbers was presented for prioritizing critical factors. Results: A cut -off value, λ = 0.95, was verified which resulted in the identification of critical accuracy factors. Accordingly, 12 critical factors were opted and categorized as a cluster of similar items into 5 groups. Finally, the analytical results obtained from fuzzy AHP algorithm revealed that project complexity, project size, bridge type and complexity were found to be the four top-ranked factors based on the global priority weight. Conclusion: These factors must be a serious concern in estimating and administering the contract and the duration of highway construction projects at the early phases of project development so that the time deviation upon the completion of the project can be minimized.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.