Jieh-Haur Chen

Mapping multi-spectral remote sensing images using rule extraction approach

To improve the accurate rate of mapping multi-spectral remote sensing images, in this paper we construct a class of HyperRectangular Composite Neural Networks (HRCNNs), integrating the paradigms of neural networks with the rule-based approach. The supervised decision-directed learning (SDDL) algorithm is also adopted to construct a two-layer network in a sequential manner by adding hidden nodes as needed. Thus, the classification knowledge embedded in the numerical weights of trained HRCNNs can be extracted and represented in the form of If-Then rules. The rules facilitate justification on the responses to increase accuracy of the classification. A sample of remote sensing image containing forest land, river, dam area, and built-up land is used to examine the proposed approach. The accurate recognition rate reaching over 99% demonstrates that the proposed approach is capable of dealing with image mapping.

Contractor Costs of Factoring Account Receivables for a Construction Project

Abstract Literature reveals that approximately 66% of construction project funds are raised from financial institutions. The burden of capital costs on contractors is heavy and financial alternatives for the reduction of capital costs are always desired. The objective of this study is to derive a mathematical way of defining the contractors costs for factoring account receivables, which is a form of commercial finance whereby a business sells its account receivables at a discount. Factoring can be thus considered as a contractor selling his/her accounts receivable to a factor, a financial institution that provides the services of financing, credit management, and collection. Nevertheless, factoring has far not been used for construction project financing. The relevant literature, empirical practices, and factoring theories from outside the construction industry are all evaluated and the features needed to derive the cost function are explored and integrated. This includes commission costs, expected debt ...

A hybrid knowledge-sharing model for corporate foreign investment in China's construction market

The research proposes a hybrid knowledge-sharing model, which integrates the concepts of the self-organizing feature map optimization, fuzzy logic control, and hyper-rectangular composite neural networks, to provide 32 rules that suggest performing or not performing foreign construction investment. The database is derived from 520 quarterly financial reports of all listed construction companies in Taiwan that have now or in the past five years made foreign investment in Chinas construction industry. The input variables are set to all 25 financial ratios assessable in public, reducing to 11 ratios after feature deduction using t-test. The model yields a high successful classification rate of 90.6% and generates 14 and 18 rules for Taiwan construction companies performing or not performing foreign investment in China, respectively. The valuable rules give user a closer look at what is the appropriate corporate financial status, what knowledge can be shared from the interpretations of the rules, and the impact by investment on corporate finance.

Requirements Definition and Management Practice to Improve Project Outcomes

Abstract Poor project requirements definition and management (RDM) is one of the major causes of project failure. However, many organizations do not adequately manage a projects requirements leading to a poor design basis. Thus, quality of requirements is critical to the success of any construction project. The primary purpose of this research was to investigate the mediating effect of requirements quality on the relationship between RDM practice and project performance. The second objective was to determine whether the impact of RDM practice on project performance was moderated by project characteristics. A three-phase approach was employed to investigate construction projects in the Taiwanese building industry. The testing supports a role for requirements quality as a partial mediator in the relationship between RDM practice and project performance. The findings also indicate that project characteristics have a moderating effect on the relationship between requirements quality and overall project perfo...

Application of SOMO Based Clustering in Building Renovation

Building renovations are usually performed as required based on inconvenience or damage that has already taken place. Construction practitioners are seldom aware of the relationships between all the related factors and their corresponding costs. The purpose of this study is to apply the self-organizing feature map (SOM) optimization based clustering (SOMOC) algorithm to building renovations so as to evaluate its feasibility and provide solutions. We collected 1056 sets of building renovation data sampled from 102 buildings. The SOMOC algorithm is utilized to expose the tendency in view of basic building features. The results suggest that the SOMOC method is feasible and effectively divides the data into 8 clusters for cluster analysis. In the subsequent discussion, findings imply that: (1) all clusters have similar distributions in terms of proportion of building age and building size, and thus, no rule can be formed for renovation practice; and (2) location, structure type, renovation frequency and cost are all related to each other. The benefits of the study not only prove the practicability of SOMOC but help the construction practitioners to learn from the past.

Knowledge Management for Risk Hedging by Construction Material Suppliers

AbstractThe cost of construction materials has significantly increased in recent years, and construction material suppliers have started to utilize investment derivatives to mitigate risks. While much knowledge has been established on the predictions of using derivatives for risk-hedging, little is known about the evaluation of the risk mitigation by analyzing financial status of construction material suppliers. This paper presents a knowledge-sharing model to determine whether risk mitigation based on the use of derivatives would be beneficial to the companies. This model is developed by first establishing a comprehensive database comprising 560 financial reports on business capacity of construction material suppliers, followed by combining the technique for order preference by similarity to ideal solution (TOPSIS) and k-nearest neighbor (KNN) pattern classification. The benefits of the research described include a knowledge-sharing mechanism in regard to the behaviors of related construction material su...

Determining and Classifying Factors of Employees’ Expatriation Willingness Using Rough Set Theory

AbstractThe objective of this research is to identify and classify the factors affecting the expatriation willingness (EW) of engineering consulting company employees. A total of 13 EW impact factors are summarized from a review of the literature and divided into four categories. From the collected factors and expert interviews, 22 impact factors are obtained and divided into eight categories, with the exception of demographic variables. A survey aiming at the top five engineering consulting companies is carried out. Out of a total of 1,000 questionnaires sent out, 41.3% valid responses are returned. The statistical analysis shows that the survey is reliable and one of the 22 factors is removed. Rough set theory (RST) is utilized to classify these factors into three classes based on impact level. The conclusions provide practitioners with six core impact factors on employees’ EW. The findings can be of benefit to employers, helping them to save recourse and to target the most appropriate employees for exp...

Application of a SOM-Based Optimization Algorithm in Minimizing Construction Time for Secant Pile Wall

Construction time matters for activities where rental equipment must be used. The building of a secant pile wall requires the rental of equipment and finding the optimal sequence to minimize the construction time is one way to lower construction costs. In this study we develop an effective and efficient optimization algorithm, which we call self-organizing feature map (SOM)-based optimization (SOMO), to minimize the construction time. The algorithm is applied to a case study to obtain the optimal sequences for both primary and secondary bored piles for a secant pile wall. The new SOMO algorithm is developed based on the ability of the human brain to produce topologically ordered mapping, so as to exploit better solutions via updating the weighting vectors of the neurons in a self-organizing topological way that occurs in the evolution of the feature map for optimization. Given detailed building time of the 16 activities of each bored pile, we find that 143.92 h or 27.21% of the original construction can be saved. The optimal sequences for both primary and secondary bored piles are also determined. The practicability of the SOMO algorithm is substantiated.

Developing a damage assessment model for bridge surroundings: a study of the disaster caused by Typhoon Morakot in Taiwan

Typhoon Morakot has been the most severe typhoon disaster to strike Taiwan in recent decades causing tremendous damage to bridge surroundings in 2009. However, we still lack a means of assessing post-typhoon damage for follow-up rebuilding. This paper presents an integrated model that automatically measures changes in rivers, areas of damage to bridge surroundings, and changes in vegetation. The proposed model is based on a neurofuzzy mechanism enhanced by the self-organising map optimisation algorithm and also includes the particular functions of dilation, erosion, and skeletonisation to deal with river imagery. High resolution FORMOSAT-2 satellite imagery from before and after the invasion period is adopted. A bridge is randomly selected from the 129 destroyed due to the typhoon for applications of the model. The recognition results show that the river average width has increased 66% with a maximum increase of over 200%. The ruined segment of the bridge is located exactly in the most scoured region. There has also been a nearly 10% reduction in the vegetation coverage. The results yielded by the proposed model demonstrate a pinpoint accuracy rate of 99.94%. This study successfully develops a tool for large-scale damage assessment as well as for precise measurement after disasters.

Optimal construction sequencing for secant pile wall

Finding the optimal sequence so as to minimizing the construction time is one of the solutions to lower the construction costs. This study proposes an effective and efficient optimization algorithm, self-organizing feather map based optimization (SOMO), to minimize the construction time with an application to a case study in obtaining the optimal sequences for both primary and secondary bored piles of a secant pile wall. The SOMO is a new developed algorithm according to the human brain that is capable of producing topologically ordered mapping, and that can occur in the evolution of the feature map for optimization. The results demonstrate that the optimal sequences for both primary and secondary bored piles are determined with 27.21% of time saving. The practicability of the SOMO algorithm is substantiated.