Jui-Sheng Chou

Web-based CBR system applied to early cost budgeting for pavement maintenance project

With the growth of transportation networks in developing countries, the cost-efficacy control of maintenance operations has become critical to the infrastructure asset management after highway construction. To effectively manage numerous projects annually with limited resources, it is necessary to accurately estimate costs and leave a trail of project information during the process of making maintenance project selection decisions. This paper outlines the development of a case-based reasoning (CBR) expert prototype system that compares historical data at the work item-level across the case library. This study attempts to determine preliminary project cost with readily available information rapidly based on previous experience of pavement maintenance related construction to assist decision makers in project screening and budget allocation. Various CBR modeling approaches were presented and assessed in terms of their mean absolute prediction error rates. Design and implementation of a web-based CBR system is demonstrated in this study to efficiently handle the attribute and case similarity computation and the results are displayed using browsers. Furthermore, weighting attributes employed in the CBR system were compared via eigenvector and equal weighting methods for estimating aggregate cost and component costs. Historical generic pavement maintenance projects were gathered from the Taiwan transportation agencies and used for model training and testing. Furthermore, k-fold cross-validation was employed to verify the CBR estimating system. The analytical results demonstrate the ability of the system to estimate the item-level cost of pavement maintenance projects with the satisfactory precision during the conceptual project phase. The developed prototype web-based CBR system can efficiently provide timely and accurate information in an efficient way and provide an alternative estimation tool that can be combined with other evaluation criteria, such as indexes of pavement serviceability and structure strength, to improve the decision making in relation to budget allocation.

Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques

This study attempts to optimize the prediction accuracy of the compressive strength of high-performance concrete (HPC) by comparing data-mining methods. Modeling the dynamics of HPC, which is a highly complex composite material, is extremely challenging. Concrete compressive strength is also a highly nonlinear function of ingredients. Several studies have independently shown that concrete strength is determined not only by the water-to-cement ratio but also by additive materials. The compressive strength of HPC is a function of all concrete content, including cement, fly ash, blast-furnace slag, water, superplasticizer, age, and coarse and fine aggregate. The quantitative analyses in this study were performed by using five different data-mining methods: two machine learning models (artificial neural networks and support vector machines), one statistical model (multiple regression), and two metaclassifier models (multiple additive regression trees and bagging regression trees). The methods were developed and tested against a data set derived from 17 concrete strength test laboratories. The cross-validation of unbiased estimates of the prediction models for performance comparison purposes indicated that multiple additive regression tree (MART) was superior in prediction accuracy, training time, and aversion to overfitting. Analytical results suggested that MART-based modeling is effective for predicting the compressive strength of varying HPC age. DOI: 10.1061/(ASCE)CP.1943-5487 .0000088.

Smart Artificial Firefly Colony Algorithm-Based Support Vector Regression for Enhanced Forecasting in Civil Engineering

Advanced data mining techniques are potential tools for solving civil engineering (CE) problems. This study proposes a novel smart artificial firefly colony algorithm-based support vector regression (SAFCA-SVR) system that integrates firefly algorithm (FA), chaotic maps, adaptive inertia weight, Levy flight, and least squares support vector regression (LS-SVR). First, adaptive approach and randomization methods are incorporated in FA to construct a novel and highly effective metaheuristic algorithm for global optimization. The enhanced FA is then used to optimize parameters in LS-SVR model. The proposed system is validated by comparing its performance with those of empirical methods and previous works via cross-validation algorithm and hypothesis test through the real-world engineering cases. Specifically, high-performance concrete, resilient modulus of subgrade soils, and building cooling load are used as case studies. The SAFCA-SVR achieved 8.8%–91.3% better error rates than those of previous works. Analytical results confirm that using the proposed hybrid system significantly improves the accuracy in solving CE problems.

Project Management Knowledge and Effects on Construction Project Outcomes: An Empirical Study

This study examines the relationships among the PMBOK® Guide, project performance, customer satisfaction, and project success by assessing the efficacy of management techniques, tools, and skills for implementing infrastructure and building construction. Experienced interviewees from private engineering firms and public agencies were asked to complete a questionnaire, and the responses were analyzed by means of a structural equation model. The analytical results indicate the appropriateness of prioritizing the practice of the PMBOK® Guide in the construction industry. This study contributes to the literature by providing insight into interactions among the PMBOK® Guide and construction project outcomes in engineering practices. Particularly, the “bidders conference” and “procurement negotiations” are the priority techniques to minimize bidding and legal procurement problems. Moreover, the study recommends the use of “stakeholder analysis,” “communication requirements analysis,” and the “communication methods” to perform effective communication management. Although the conclusions are based on the sample collected in Taiwan, the research findings can be used by project managers and educators to tailor the PMBOK® Guide to their unique needs and to design effective training programs for construction specialists.

Generalized linear model-based expert system for estimating the cost of transportation projects

Timely effective cost management requires reliable cost estimates at every stage of project development. While underestimation of transportation costs seems to be a global trend, improving early cost prediction accuracy in estimates is difficult. This paper presents a parametric estimating technique applied to Texas highway projects using a set of project characteristics. Generalized linear models (GLM) of early quantity prediction for geometry-related work activities, namely earthwork, pavement and traffic control were developed for continuous project cost tracking. The approach of cost breakdown demonstrates the potential to separate quantity uncertainty from price uncertainty for highway construction. The benefit of this approach is to provide a platform for evolving the preliminary parametric cost estimates to a fully detailed cost management as further information becomes available as the project progresses. During project execution, managers are given opportunities to review the associated work activities and make better decisions from the developed GLM-based estimating system. Compared to typical practice of applying a gross cost per lane length during pre-project planning phase, the proposed approach with the aid of the developed expert system provides more detailed basis and efficiency for tracking the effects of changes within the project life cycle.

Optimizing parameters of support vector machine using fast messy genetic algorithm for dispute classification

Hybrid system is a potential tool to deal with construction engineering and management problems. This study proposes an optimized hybrid artificial intelligence model to integrate a fast messy genetic algorithm (fmGA) with a support vector machine (SVM). The fmGA-based SVM (GASVM) is used for early prediction of dispute propensity in the initial phase of public-private partnership projects. Particularly, the SVM mainly provides learning and curve fitting while the fmGA optimizes SVM parameters. Measures in term of accuracy, precision, sensitivity, specificity, and area under the curve and synthesis index are used for performance evaluation of proposed hybrid intelligence classification model. Experimental comparisons indicate that GASVM achieves better cross-fold prediction accuracy compared to other baseline models (i.e., CART, CHAID, QUEST, and C5.0) and previous works. The forecasting results provide the proactive-warning and decision-support information needed to manage potential disputes.

Quantity-Based Approach to Preliminary Cost Estimates for Highway Projects

The preliminary cost estimate heavily influences the fate of a transportation project, yet it can be up to an order of magnitude off the final bid amount. Poor prediction of costs in state departments of transportation can lead to less-than-optimal project selection at the front end and delays later when funding is not adequate to cover planned projects. A demonstration is made of the potential to separate quantity uncertainty from price uncertainty. If item quantities can be predicted early, then readily available unit prices can be applied to create a semidetailed preliminary estimate. Compared with the typical practice of applying a gross cost per lane mile, the proposed approach provides a more detailed basis for tracking the effects of changes during project development. This methodology is being tested for implementation by the Texas Department of Transportation.

Smart meter monitoring and data mining techniques for predicting refrigeration system performance

A major challenge in many countries is providing sufficient energy for human beings and for supporting economic activities while minimizing social and environmental harm. This study predicted coefficient of performance (COP) for refrigeration equipment under varying amounts of refrigerant (R404A) with the aids of data mining (DM) techniques. The performance of artificial neural networks (ANNs), support vector machines (SVMs), classification and regression tree (CART), multiple regression (MR), generalized linear regression (GLR), and chi-squared automatic interaction detector (CHAID) were applied within DM process. After obtaining the COP value, abnormal equipment conditions can be evaluated for refrigerant leakage. Analytical results from cross-fold validation method are compared to determine the best models. The study shows that DM techniques can be used for accurately and efficiently predicting COP. In the liquid leakage phase, ANNs provide the best performance. In the vapor leakage phase, the best model is the GLR model. Experimental results confirm that systematic analyses of model construction processes are effective for evaluating and optimizing refrigeration equipment performance.

Predicting Disputes in Public-Private Partnership Projects: Classification and Ensemble Models

Proactively forecasting disputes in the initiation phase of public-private partnership (PPP) projects can considerably reduce the effort, time, and cost of managing potential claims. This comprehensive study compared classification models for PPP project dispute problems. Performance comparisons included four machine learners, four classification and regression trees, two multivariate statistical techniques, and combinations of techniques that have performed best according to a historical database. Experimental results indicate that an ensemble technique (i.e., SVMs+ANNs+C5.0) provides better cross-fold prediction accuracy (84.33%) compared with all other individual classification models. Notably, SVM (support vector machine) is the best single model for classifying dispute propensity in terms of overall performance measures. This study demonstrates the efficiency and effectiveness of data-mining techniques for early prediction of dispute propensity in PPP projects pertaining to public infrastructure services. The modeling results provide proactive-warning and decision-support information needed for managing potential disputes before disputes occur. DOI: 10.1061/(ASCE)CP.1943-5487.0000197.

Multiobjective optimization for manpower assignment in consulting engineering firms

In this article, a new multiobjective optimization model, MUST, is proposed to facilitate the staff-to-job assignment in consulting engineering firms. In addition to the typical objective of maximizing profits, other human resource related objectives are also incorporated to balance workloads, avoid excessive overtime, and eliminate demoralizing idleness while giving preference to projects with specified priorities. The present optimization problem is of significant complexity (nonlinear, non-smooth, and combinatorial) and has been proved NP- and #P-complete. To handle all the difficulties, MUST incorporates a particle swarm optimization algorithm to approximate the tradeoff surface consisting of non-dominated solutions. The application of MUST is demonstrated through a numerical case of assigning six engineering teams to fifteen incoming projects. It has been shown that non-dominated solutions generated by MUST help decision makers choose the compromised assignment plan which is otherwise hard and time-consuming to obtain. The comparisons with SPEA2 and LINGO verify the effectiveness and efficiency of MUST.