Evolutionary support vector machine inference system for construction management

Problems in construction management are complex, full of uncertainty, and vary based on site environment. Two tools, the fast messy genetic algorithms (fmGA) and support vector machine (SVM), have been successfully applied to solve various problems in construction management. Considering the characteristics and merits of each, this paper combines the two to propose an Evolutionary Support Vector Machine Inference Model (ESIM). In the ESIM, the SVM is primarily employed to address learning and curve fitting, while fmGA addresses optimization. This model was developed to achieve the fittest C and γ parameters with minimal prediction error. This research further integrates the developed ESIM with an object-oriented (OO) computer technique to create an Evolutionary Support Vector Machine Inference System (ESIS). Simulations conducted to demonstrate the robustness of the model in application indicate that ESIS may be used as a multifarious intelligent decision support system in decision-making to help solve a wide range of construction management problems.     

Forecasting enterprise resource planning software effort using evolutionary support vector machine inference model

Despite significant advances in procedures that facilitate project management, the continued reliance of software managers on guesswork and subjective judgment causes frequent project time overruns. This study uses an Evolutionary Support Vector Machine Inference Model (ESIM) for efficiently and accurately estimating the person-hour of ERP system development projects. The proposed ESIM is a hybrid intelligence model integrating a support vector machine (SVM) with a fast messy genetic algorithm (fmGA). The SVM mainly provides learning and curve fitting while the fmGA minimizes errors. The analytical results in this study confirm that, compared to artificial neural networks and SVM, the proposed ESIM provides preliminary prediction at early phase of ERP software development effort for the manufacturing firms with superior accuracy, shorter training time and less overfitting. Future research can develop user-friendly expert systems with window or browser interfaces that can be used by planning personnel to flexibly input related variables and to estimate development effort and corresponding project time/cost.     

Estimate at Completion for construction projects using Evolutionary Support Vector Machine Inference Model

Construction projects are influenced by a range of factors that impact upon final project cost. Estimate at Completion (EAC) is an important approach used to estimate final project cost, which takes into consideration probable project performance and risks. EAC helps project managers identify potential but still unknown problems and adopt response strategies. This study constructed an evolutionary EAC model to generate project cost estimates that proved significantly more reliable than estimates achievable using currently prevailing formulae. The developed learning model fused two artificial intelligence approaches, namely the fast messy genetic algorithm (fmGA) and Support Vector Machine (SVM), to create an Evolutionary Support Vector Machine Inference Model (ESIM). The ESIM was then applied to estimate final project costs for historical cases. Finally, using the EAC estimate, project cost influence indices, and project cost diagrams, the discrepancy between estimate and practical values was examined to determine potential problems in order to help project managers better control project costs. The learning results were validated in real applications that showed good performance for training models. Providing project managers reliable EAC trend estimates is helpful for their effective control of project costs and taking appropriate peremptory measures to handle potential problems.     

The impact of contractors’ attributes on construction project success: A post construction evaluation

The success of construction projects is a fundamental issue for most governments, users and communities. In the literature that deals with construction project success and causes of time and cost overruns in the construction industry, there is some literature that highlights the role of the contractors in project success. While most studies rank contractors’ success attribute from tendering, prequalification, and a long term historical perception perspective, this paper aims to study the impact of contractors’ attributes on project success from a post construction evaluation perspective to identify what critical success factors (CSFs) that greatly impact the success of project. In an attempt to understand and investigate this impact, a questionnaire survey is used to establish construction professionals’ perception of CSFs of contractors that greatly impact on the success of construction projects. Factor analysis reveals nine underlying clusters namely :(i) safety and quality; (ii) past performance; (iii) environment; (iv) management and technical aspects; (v) resource; (vi) organisation; (vii) experience; (viii) size/type of pervious projects; and (ix) finance. Logistic regression techniques were used to develop models that predict the probability of project success. Factors such as turnover history, quality policy, adequacy of labour and plant resources, waste disposal, size of past projects completed, and company image are the most significant factors affecting projects success. Assuming that project success is repeatable, these findings provide clear understanding of contractors’ performance and could potentially enhance existing knowledge of construction project success.     

Evolutionary fuzzy decision model for cash flow prediction using time-dependent support vector machines

The ability of project managers to make reliable cash flow predictions enhances project cost flow control and management. Reliable cash flow prediction over the course of a construction project puts the project manager in a better position to identify potential problems and develop appropriate strategies to mitigate the negative effects of such on overall project success. Therefore, managers should monitor project progress using cash flow data, which has unique characteristics, as time series data. However, the complex, mutable nature of construction projects currently requires significant reliance on experience and expert opinions to predict cash flow on an ongoing basis. Recent studies have indicated good potential for using artificial intelligence to reduce reliance on human input in cash flow prediction processes. The Evolutionary Fuzzy Support Vector Machine Inference Model for Time Series Data (EFSIM_T), an artificial intelligence hybrid system focusing on the management of time series data characteristics which fuses fuzzy logic (FL), weighted support vector machines (weighted SVMs) and a fast messy genetic algorithm (fmGA), represents a promising alternative approach to predicting cash flow. Simulations performed on historical cash flow data demonstrate the EFSIM_T is an effective tool for predicting cash flow.     

Using neural network to predict performance of design-build projects in Singapore

Design-build (DB) project success may be operationalised into 11 performance metrics. 65 factors that may affect DB project success are identified. Using data from 33 DB projects, correlation analysis shows that there are several factors that affect each performance metric significantly. Artificial neural network (ANN) technique is used to construct the models to predict project performance, and these models are tested using data from five new projects.This study finds that six performance metrics can be predicted with a reasonable degree of accuracy: project intensity; construction and delivery speeds; turnover, system and equipment quality. The key variables that affect project performance may be attributed to both contractors and clients. To ensure project success, contractors should have adequate staffing level, a good track record for completion on budget, and ability in financial management and quality control. Consultants should have a high level of construction sophistication, and have handled DB projects in the past. Clients also play an important part in ensuring DB project success. They would need to have construction experience and handled DB projects in the past. In addition, they should decide on the optimal level of design completion when the budget is fixed and tenders are invited. It is recommended that owners and contractors take note of the factors identified in this study, which significantly affect DB project performance.     

Neuro‐Fuzzy Cost Estimation Model Enhanced by Fast Messy Genetic Algorithms for Semiconductor Hookup Construction

Abstract: Semiconductor hookup construction (i.e., constructing process tool piping systems) is critical to semiconductor fabrication plant completion. During the conceptual project phase, it is difficult to conduct an accurate cost estimate due to the great amount of uncertain cost items. This study proposes a new model for estimating semiconductor hookup construction project costs. The developed model, called FALCON‐COST, integrates the component ratios method, fuzzy adaptive learning control network (FALCON), fast messy genetic algorithm (fmGA), and three‐point cost estimation method to systematically deal with a cost‐estimating environment involving limited and uncertain data. In addition, the proposed model improves the current FALCON by devising a new algorithm to conduct building block selection and random gene deletion so that fmGA operations can be implemented in FALCON. The results of 54 case studies demonstrate that the proposed model has estimation accuracy of 83.82%, meaning it is approximately 22.74%, 23.08%, and 21.95% more accurate than the conventional average cost method, component ratios method, and modified FALCON‐COST method, respectively. Providing project managers with reliable cost estimates is essential for effectively controlling project costs.     

Exploring the critical nexus between authoritarian leadership,project team member's silence and multi-dimensional success in a state-owned mega construction project

State-owned mega construction projects are greatly driven by the top-down authoritarian leadership that ironically restricts two-way communication and free flow of ideas. Prominent studies have highlighted various critical success factors of project success; however, the effects of authoritarian leadership and project team member's silence have been completely overlooked, especially in mega construction projects. The present study makes a pioneering effort to address this critical research gap and investigate the effects of authoritarian leadership and project team member's silence on the multi-dimensional success (including project management success, project ownership success and project investment success) in a mega construction project. Drawing on data from 357 project professionals directly associated with the China Pakistan Economic Corridor (CPEC) and covariance based structural equation modeling (CB-SEM) with Mplus, the findings provide new empirical evidence that authoritarian leadership has a significant negative influence on the multi-dimensional success in the CPEC mega construction project. The findings also establish that project team member's silence negatively mediates the relationship between authoritarian leadership and the multi-dimensional mega construction project success. The study implications offer new strategic insights for managing mega construction projects, especially in transition economies that still have deep roots of authoritarian cultures.     

Structural equation model for assessing impacts of contractor's performance on project success

Contactor's expertise and performance play a significant role in successful delivery of a project. While clients strive hard to make the best decisions in selecting the right contractor for the right job, a clear understanding of the underlying attributes associated with contractors' selection in the context of achieving successful project outcomes is critical. In an attempt to understand these pre-emptive qualification criteria and their links to contractors' performance on a project, a hierarchical structural model is established. By employing the structural equation modelling technique, the model adapts a total of 29 technical attributes across five confirmatory factors namely, soundness of business and workforce (SBW), planning and control (PC), quality performance (QP), past performance (PP) and overall project success (OPS). Based on the survey data collected across medium size construction projects in Australia, the results of the model confirmed that technical planning and controlling expertise of contractor is key in achieving success on projects. With a clear understanding of the significance of these factors in the context of contractors' performance, these findings could potentially contribute to the development of a company's procedures or to enhance existing knowledge of contractor prequalification practices.     

Traversing and querying constraint driven temporal networks to estimate construction contingencies

Effective estimation of possible project futures is crucial to the success of construction projects. The focus of this paper is identifying and classifying possible construction crisis scenarios using an interactive simulation. We present a mathematical representation of construction processes, with foundations in temporal constraint networks, that can be used to infer alternative futures of a project as it unfolds. We present algorithms that can traverse the network in time, reason about the constraints driving the construction project, and present the combinatorial possibilities of futures that can emerge from one or more constraint violations during project implementation. The graphical depictions of the traversal results will aid construction managers in anticipating and reacting to crisis scenarios as they evolve in time. We present a case study and illustrate how the proposed algorithms can be used to represent and model uncertainty and estimate contingencies in construction projects. This research is part of a broader framework that integrates construction education, the study of expert decision making, and intelligent decision making aids.     

Key relationship-based determinants of project performance in China

The aim of this paper is to investigate the relationship-based factors that affect performance of general building projects in China. Thirteen performance metrics that may be used to measure the success level of construction projects are defined and categorized into four groups namely cost, schedule, quality and relationship performance. Fourteen risks inherent in relationships and 16 tools expected to facilitate relationship building that may affect project success are identified. Data of different projects were collected in China via a self-administered postal survey. Multiple linear regression models are developed to help explain the variance in different performance metrics. It has been found that ten risks and nine tools have either positive or negative influence on project performance to some different extents and in different project development process stages. Detailed explanations are made, especially to those variables bearing unexpected signs. It is recommended that firms in the Chinese construction industry manage the relationship-based factors that are significant in the MLR models so as to achieve project success.     

A study of preproject planning and project success using ANNs and regression models

It has long been recognized by the industry practitioners that how well preproject planning is conducted has a great impact on project outcome. Through industry project data collection and model analysis, this research intends to investigate the relationship between preproject planning and project success. Preproject planning and project performance information from 62 industrial projects and 78 building projects, representing approximately $5 billion U.S.D. in total construction cost, is collected and used for this research analysis. Based on the information obtained, preproject planning is identified as having direct impact on the project success (cost and schedule performance). Two techniques were then used to develop models for predicting cost and schedule performance: statistical regression analysis, and artificial neural networks (ANNs). The research results provide a valuable source of information that supports better planning in the early stage of the project life cycle and have positive impact on the final project outcome.     

Bidding strategy to support decision-making by integrating fuzzy AHP and regression-based simulation

This study proposes a new bidding strategy to support decision-making that is based on a combined framework of the Fuzzy Analytical Hierarchy Process (FAHP) and regression-based simulation. First, the FAHP method integrates the AHP with fuzzy set theory to determine the weights of factors that influence the cost of a project. Second, the integration of the cumulative distribution functions that are generated by the Monte Carlo simulation with a regression model yields bid amounts that correspond to various confidence levels. The proposed approach is used to analyze data on bridge construction projects that are taken from a database of the Taiwan Public Construction Commission. The systematic bid assessment model and the cost-probability curve can be used as strategic tools for quantifying project risks and calculating bids for construction projects.     

Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models

It is commonly perceived that how well the planning is performed during the early stage will have significant impact on final project outcome. This paper outlines the development of artificial neural networks ensemble and support vector machines classification models to predict project cost and schedule success, using status of early planning as the model inputs. Through industry survey, early planning and project performance information from a total of 92 building projects is collected. The results show that early planning status can be effectively used to predict project success and the proposed artificial intelligence models produce satisfactory prediction results.     

Strategic change towards cost-efficient public construction projects

The cost of public construction projects is a central topic in project management. However, studies have primarily focused on cost at the project level, not on cost management at the portfolio level. In this paper, we take the perspective of a government agency, conducting a strategic initiative to increase cost-efficiency in their portfolio of construction projects. We use an action research approach to investigate the dynamics of the initiative and the implementation of resulting actions to achieve lasting change towards cost-efficiency. Co-creating actions for cost-efficiency together with the project teams was important for the success of the strategic initiative. For successful implementation, alignment of the objectives of the initiative with organizational strategy, and knowledge transfer between projects is central. This study expands the project management literature regarding strategic cost management of portfolios of construction projects and provides practical guidance for organizations.     

Can project monitoring and control be fully automated?

An extended research programme has examined over the past two decades how productivity in construction projects can be improved through the development of models for project monitoring and control, which process automatically collected data on the actual project performance. Tests that were conducted with these models demonstrate that this approach can help overcome some of the limitations of existing manual methods. However, they also indicate that certain manually obtained data are still required in addition to the automatically collected data. A framework for semi-automated project monitoring and control is proposed, in which both manually and automatically collected data can be incorporated. This framework integrates the monitoring of projects with their control by taking into account the impact on productivity of existing deviations from the planned performance, and of the controlling actions that are proposed to deal with these deviations.     

Future criteria for success of building projects in Malaysia

Several success criteria (SC) and categorization models have been introduced and studied in the previous decades to address the issue of project success. However, most of these models have failed to align success criteria with company's success in the long-term. This paper aims at proposing a framework to categorize project success for building projects in Malaysia from the contractors' perspective. The proposed framework incorporates criteria that align the project efforts with both short and long-term goals of the companies; moreover provide an appropriate judgment of success at all stages of the project. If construction managers can judge the probability of success, they would be able to evaluate the overall relative strength of each project, and identify problems on current projects to direct them toward success.Based on the available literature, thirteen success criteria were found to be significantly and substantially related to building projects success. To develop the SC categorization framework, 151 participants, who are involved in building construction, were invited through a postal and e-mails survey to generate priorities of these criteria. The results of this study indicated that a categorization scheme for success criteria for building projects should include the categories of project management success, product success, along with market success. The findings of this study can further help future researchers seeking solutions in the challenges relating to improvement of building projects implementation and enhancement of project success.     

Key project management practices affecting Singaporean firms’ project performance in China

Foreign (non-mainland Chinese) architectural, engineering and construction (AEC) firms may face difficulties managing construction projects in China because they are unfamiliar with this new operating environment. This study investigates project management (PM) practices adopted by Singaporean AEC firms in China. It determines the performance level of their projects in China; identifies PM practices that led to better performance; and recommends key PM practices that could be adopted by foreign AEC firms in China to achieve project success. A structured questionnaire was designed and data were collected via a self-administered postal and email survey, targeting Singaporean AEC firms that had undertaken and managed projects in China. The study finds that certain PM practices do indeed affect project performance. The most important of these are practices relating to scope management, such as controlling the quality of the contract document, quality of response to perceived variations and extent of changes to the contract. It is recommended that foreign firms adopt some of the PM practices highlighted in this study to help them achieve better project performance in China.     

Measuring construction project participant satisfaction

Construction projects involve numerous stakeholders, and their satisfaction could directly influence the performance of subsequent projects. Driven by a desire to improve project success, the critical satisfaction factors pertinent to the construction management process should be identified. In this paper, an overall study regarding the behavioural management mechanisms amongst project participants is presented. Eleven behavioural management mechanisms are identified and 15 hypotheses are established for this study. The concepts of satisfaction, project goals, various management mechanisms and their interrelationships are discussed and investigated in relation to construction projects. The results indicate that management mechanisms rather than particular project goal could directly affect the participant satisfaction. Cooperation/participation, task/team conflict and goal commitment are the critical factors influencing the final outcome (satisfaction) in the complicated management process. Moreover, conflict on the task amongst the participants is the moderation mechanisms for the relationship between goal commitment and participant satisfaction. There is a significantly positive relationship between commitment and satisfaction in construction project management, while high level of conflict is stimulated in the goal setting process amongst the participants.     

基于DEMATEL 的全过程工程咨询流程影响因素分析

为了促进建筑业持续健康发展,业界开展全过程工程咨询试点工作,全国各个项目也纷纷落地。全过程工程咨询整合了建设项目各个阶段,因此其流程设计是咨询服务开展重要的一环。从流程模型角度出发,通过文献研究全过程工程咨询的控制和机制要素识别全过程工程咨询服务流程的影响因素,运用DEMATEL 方法分析各个影响因素之间的相互关系,发现项目团队、项目信息、管理资源是全过程工程咨询流程的关键影响因素,并据此提出发展全过程工程咨询的建议和对策。