Tarek Mahfouz

Civil engineering grand challenges: Opportunities for data sensing, information analysis, and knowledge discovery

AbstractThis paper presents an exploratory analysis to identify civil engineering challenges that can be addressed with further data sensing and analysis (DSA) research. An initial literature review was followed by a web-based survey to solicit expert opinions in each civil engineering subdiscipline to select challenges that can be addressed by civil engineering DSA research. A total of 10 challenges were identified and evidence of economic, environmental, and societal impacts of these challenges is presented through a review of the literature. The challenges presented in this paper are high building energy consumption, crude estimation of sea level, increased soil and coastal erosion, inadequate water quality, untapped and depleting groundwater, increasing traffic congestion, poor infrastructure resilience to disasters, poor and degrading infrastructure, need for better mining and coal ash waste disposal, and low construction site safety. The paper aims to assist the civil engineering research community ...

Litigation Outcome Prediction of Differing Site Condition Disputes through Machine Learning Models

AbstractThe construction industry is one of the main sectors of the U.S. economy that has a major effect on the nation’s growth and prosperity. The construction industry’s contribution to the nation’s economy is, however, impeded by the increasing number of disputes that unfold and oftentimes escalate as projects progress. The majority of construction disputes are resolved in courts unless project contracts call for alternate dispute resolution mechanisms. Despite the numerous advantages offered by the litigation process, the extra financial burdens and additional time required by this process makes litigation less desirable in resolving the disputes of a very dynamic construction industry. It is believed that construction litigation could be reduced or even avoided if parties have a realistic understanding of their actual legal position and the likely outcome of their case. Consequently, researchers in the artificial intelligence field have developed tools and methodologies for modeling judicial reasonin...

Construction Legal Decision Support Using Support Vector Machine (SVM)

This paper represents a step in a line of research aiming at mitigating the negative effects of conflicts on the construction industry through developing a construction legal decision support methodology. This step developed Support Vector Machine (SVM) models to automatically extract latent legal factors, upon which judges base their verdicts, from precedent cases. The adopted research methodology developed and compared the output of first, second, and third degree polynomial kernel SVM models while implementing 4 weighing mechanisms namely term frequency (tf), logarithmic term frequency (ltf), augmented term frequency (atf), and term frequency inverse document frequency (tf.idf). The models were trained and tested over two sets of Differing Site Condition (DSC) cases compiled from the Federal Court of New York. The two sets were composed of 120 and 450 cases respectively. The highest accuracy of extraction of 76% was attained using first degree polynomial kernel SVM while implementing tf.idf weighing with the first set. With the second set, a higher accuracy of 85% was achieved using third degree polynomial kernel SVM while implementing tf.idf weighing.

Factors Affecting Litigation Outcomes of Differing Site Conditions (DSC) Disputes: A Logistic Regression Models (LRM)

Construction is one of the major contributing industries to the US economy. However, its advancement and contribution have always been negatively impacted by the vast number of conflicts associated with it. Traditional conflict resolution methods require legal knowledge and expertise that are not commonly available, thus cost considerable sums of money. A significant number of construction disputes could be attributed to the uncertainty in the conditions under which projects are executed, and especially site conditions. In an attempt to provide an outcome prediction system for differing site conditions (DSC) claims in the construction industry, this paper provides, as a first step, a statistical analysis of set of precedent cases to identify, quantify, and measure the impact of significant legal factors on outcomes prediction of litigation cases. The adopted methodology developed a statistical binary choice Logistic Regression Model (LRM) (a) to identify the effect of each legal factor on the prediction of the winning party; (b) to identify the best combination of factors with the highest prediction precision; and (c) to perform a sensitivity analysis to prioritize the most significant legal factors. Among the major findings of this paper are (1) 23 significant legal factors were identified; (2) A combination of 9 legal factors were found to attain the highest prediction precision of 93.33%; (3) Generally, cases in which the Federal Government is a concerned party, judgments are in its favor.

Unstructured Construction Document Classification Model through Support Vector Machine (SVM)

The dynamic nature of the construction industry yields enormous amount of documents that have to be stored, retrieved, and reused. Most of these documents are generated in an unstructured format. Therefore, in an attempt to provide a robust document classification methodology for the construction industry, the current research proposes an automated classifier model through Support Vector Machines (SVM). The adopted research methodology (1) gathered a corpus of documents including 300 correspondences, 150 meeting minutes, 25 claims, and 300 Differing Site Conditions (DSC) cases; (2) developed C++ algorithms which process unstructured documents into a readable format by the SVM algorithm; (4) developed 16 SVM automated classification models; and (5) tested and validated the developed models. The developed models under the current research attained higher accuracy, and better precision and recall than previous researches illustrated in the literature. The current research represents a continuation to previous researches performed within this realm.

Decision-making Model by Specialty Subcontractors in Construction Projects

Specialty sub-contractors enter construction projects due to their expertise, possession of special machineries and skilled workers or both. Like other project based organizations, specialty sub-contractors gain their organizational knowledge during projects. However, experiencing specific limited tasks several times, in different circumstances, raises their level of knowledge over that of other parties and impedes knowledge deterioration over time. This organizational knowledge distinguishes them from other parties involved in construction projects. Despite their critical role in construction industry, specialty subcontractors have not received enough attention from academia. This study looks at the procedures of different knowledge that specialty sub-contractors acquire through their experience and the way they use it in their future jobs. This study proposes a decision making model exercised by the specialty contractors which differentiates events from routines. The model was validated through interviews with constructional professionals. This model clarifies the potential contribution of subcontractors in managing knowledge in different stages of construction projects. INTRODUCTION Project delivery in the Construction industry is a multidisciplinary and multiphase process, with different parties playing a variety of roles at different times. Such dynamic and complex procedures must be designed with adequate precision to avoid rework, cost overrun, hazard, delay, inferiority and defections with the product. Project design includes designing the project deliverables and their components, the temporary facilities and the construction process itself. Although design does not solely include decision making, decisions play a critical role in efficient design, as mentioned by Lewis (Lewis et al., 2007). Design consists of many interdependent decisions with knowledge about the technical process and object systems being an essential part of decision making (Eder and Hosnedl, 2010). Specialist contractors are of vital importance to the construction industry, decision making processes and their contribution to the total construction process can account for as much as 90% of the total project (Nobbs, 1993). 867 Construction Research Congress 2014 ©ASCE 2014

Legal Review of Conditions Precedent to Dispute Resolution in Construction Contracts

AbstractDispute resolution procedures specified in construction contracts commonly contain conditions precedent that can ultimately affect the entitlements of the parties in case a dispute occurs. This study discusses various aspects related to conditions precedent in dispute resolution provisions, namely, notifications of claims as a condition precedent, architect/engineer (A/E) decision as a condition precedent, mediation as a condition precedent, timely submissions as a condition precedent, language for establishing conditions precedent, waiver of conditions precedent by courts, and the authority to issue such waiver. Legal decisions related to each topic are discussed, and general guidelines for dealing with conditions precedent in dispute resolution procedures are given.

Application of Latent Semantic Analysis for Conceptual Cost Estimates Assessment in the construction Industry

Conceptual cost estimates represent the first benchmark upon which owners define their financial capability of performing a construction project. Consequently, the accuracy and quality assessments of these estimates are crucial. This paper proposes an automated conceptual cost estimate assessment model through Latent semantic Analysis (LSA). The use of LSA in the construction industry has rarely been implemented, which deprives this industry from utilizing its strengths to facilitate decision making. The research methodology adopted (1) utilizes data from a set of completed construction projects; (2) proposes an automated LSA model for the assessment of conceptual cost estimates based on error ranges; and (3) compares the attained outcomes to previous researches in the literature review. The outcomes of the current research illustrate that LSA modeling performs accurately in assessing conceptual cost estimate making it a powerful tool for construction decision making.

Analysis of Differing Site Condition (DSC) Litigation Reasoning Through Statistical Modeling

ABSTRACT Differing Site Conditions (DSC) is considered to be one of the most prominent reasons for claims within the construction industry. Thus, the purpose of this article is to facilitate decision making related to DSC claims through analysis of the judicial reasoning in such cases by identifying significant legal concepts and implementing statistical modeling. The implemented methodology utilizes 60 DSC cases from the Federal Court of New York, extracts legal concepts upon which verdicts are based through content analysis, and develops a binary choice probit regression model to identify (1) the effect of each concept, (2) the associations and precedence of concepts to each other, and (3) the probabilistic change due to parametric variation in these concepts. The findings provide better means of assessing the legal ramifications based on the identified factors. Such evaluation allows disputing parties to make more informed decision about their dispute resolution strategies. In addition, the current research provides knowledge to contractors about factors to which emphasis should be given while bidding for new projects and upon which control should be maintained while performing a project. Finally, this research creates a solid foundation for the development of robust construction legal decision support systems for DSC disputes.

Clustered simulation for the simulation of large repetitive construction projects

Construction planning methods have been in continuous evolution due to the increasing complexity of construction projects. Construction simulation modeling is one of the later stages of this evolution that has received much attention in research. Many simulation based construction planning methods developed modeling methods that attempt to cluster project activities into smaller sub-models that enhance model reusability. Many of these modeling methods, however, create new modeling elements that are not familiar to traditional construction simulation modelers. Therefore, the objective of this paper is to develop a method for clustering activities of large and repetitive construction projects for enhancing the reusability of those simulation models. The developed method does not create any new modeling elements and is called Clustered Simulation Modeling (CSM). CSM was evaluated in modeling an actual large-scale repetitive construction projects, and the results have illustrated the effectiveness of the method and the proposed clustering scheme.