Amr Kandil

Optimization research: Enhancing the robustness of large-scale multiobjective optimization in construction

Many construction planning problems require optimizing multiple and conflicting project objectives such as minimizing construction time and cost while maximizing safety, quality, and sustainability. To enable the optimization of these construction problems, a number of research studies focused on developing multiobjective optimization algorithms (MOAs). The robustness of these algorithms needs further research to ensure an efficient and effective optimization of large-scale real-life construction problems. This paper presents a review of current research efforts in the field of construction multiobjective optimization and two case studies that illustrate methods for enhancing the robustness of MOAs. The first case study utilizes a multiobjective genetic algorithm (MOGA) and an analytical optimization algorithm to optimize the planning of postdisaster temporary housing projects. The second case study utilizes a MOGA and parallel computing to optimize the planning of construction resource utilization in large-scale infrastructure projects. The paper also presents practical recommendations based on the main findings of the analyzed case studies to enhance the robustness of multiobjective optimization in construction engineering and management.

Multiagent System for Construction Dispute Resolution (MAS-COR)

This paper develops theoretical foundation and implements technologies for generation of legal arguments based on precedent construction disputes. First, the authors simulated the process of legal discourse in construction disputes using a formal logic algorithm that is based on adversarial precedent law. In this regard: (1) facts associated with construction change order cases were factorized into binary, dimensional, and abstract factors; (2) relevance of the developed factors was associated with the disputing parties; (3) logical predicates and rules were generated based on the said factors; (4) factors were logically analyzed into distinct classifications; and (5) an 11 stage logical induction algorithm was used to show similarities, differences, strengths, and weaknesses between current and precedent construction disputes. Second, the authors created a multiagent system for construction dispute resolution (MAS-COR) that automates the developed algorithm. In this connection: (1) an agent-based role model was developed to represent the developed algorithms; (2) an agent-based role model was built to represent the developed algorithm; and (3) system implementation was carried using object-oriented programming on NetBeans integrated development environment. Using 30 previously arbitrated construction disputes, testing and validation steps were rigorously applied to assess the developed formal logic algorithm as well as the associated created agents and their integration into the MAS-COR system through syntactical debugging using theorem proving, model checking, and system testing. The results of this validation process illustrated that the system was capable of deriving significant legal arguments that help save time and effort of construction claim and dispute professionals while preparing the defense for their respective positions.

Concept Relation Extraction from Construction Documents Using Natural Language Processing

The objective of this research is to present an innovative technique for managing the knowledge contained in construction contract documents to facilitate quick access and efficient use of such knowledge for project management and contract administration tasks. Knowledge Management has become the focus of a lot of scientific research during the second half of the 20th century as researchers discovered the importance of the knowledge resource to business organizations. Despite early expectations of improved document management techniques, document management systems used in the construction industry have failed to deliver the anticipated performance. Recent research attempts to utilize analysis of the contents of documents to improve document categorization and retrieval functions. It is hypothesized that natural language processing can be effectively used to perform document text analysis. The proposed system, technique for concept relation identification using shallow parsing (CRISP), utilizes a shallow parser to extract semantic knowledge from construction contract documents which can be used to improve electronic document management functions such as document categorization and retrieval. When compared with human evaluators, CRISP achieved almost 80% of the average kappa score attained by the evaluators, and approximately 90% of their F-measure score.

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...

Document Management in Construction: Practices and Opinions

AbstractPrevious surveys on document management (DM) have focused on certain aspects such as the adoption of electronic methods by construction firms and the important features of electronic document management systems. This study presents the results of a survey of practitioners on various aspects of DM, including document storage, classification, search, and transmittal. The survey aims to identify practices that are implemented in large firms in the industry and the opinions of practitioners regarding such practices. Statistical models were used to map the relations between DM practices, characteristics of firms, and opinions of practitioners. The results indicate elaborate interactions between the different components, in which traditional and advanced methods are used simultaneously. The metadata approach for organizing documents is dominant; however, the use of text content is also common, especially for document search and retrieval. The results are considered to be a snapshot to benchmark the deve...

Grand challenges in simulation for the architecture, engineering, construction, and facility management industries

Today’s Architecture, Engineering, Construction and Facility Management (AEC/FM) industry has to deal with complex obstacles (e.g., aging infrastructure, the protection of the natural environment, the need for resilient infrastructure). Among several technical fields that have been adopted and advanced, computer simulation has been widely researched and practiced for the effective delivery and maintenance of capital projects. Considering the unprecedented problems of today’s infrastructure and the rapid advancements in simulation research, it is very timely to investigate what grand challenges exist in simulation that if properly addressed, can help create a more sustainable and resilient engineering of infrastructure lifecycle. To this end, this paper aims to identify grand challenges in simulation by presenting major areas of interest that can benefit the AEC/FM domain and discussing three specific areas identified as challenges in simulation: 1) realistic simulation modeling; 2) applicability of simulation models to the industry; and 3) academic and educational obstacles. Specific foci are the knowledge gaps in these major areas, and the current efforts to mitigate these gaps based on extensive literature reviews. This paper also proposes the next steps for addressing these challenges based on the findings herein.

Contractors’ Claims Insurance: A Risk Retention Approach

The negative effects of claims and disputes have serious negative impacts on contracting parties, their projects, the construction industry as a whole, and consequently on the nation’s economy. This paper explores a method for mitigating the negative effects associated with contractors’ claims and disputes using a risk retention approach. This method can help contractors in getting early relief from the financial and economic burdens of construction claims. To meet the goals and objectives of this study, the writers have: (1) investigated the feasibility of pricing insurance premiums using the options pricing theory; (2) explored the applicability of modeling the options pricing theory using Monte Carlo simulation; (3) set up the principles required for optimal design of a risk retention group for construction claims; and (4) tested the possible impact of the newly developed risk retention group using historic data of 10,193 construction projects spanning over 12 different California districts. Pursuant t...

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.

Automatic Classification of Project Documents on the Basis of Text Content

AbstractOrganizing construction project documents based on semantic similarities offers several advantages over traditional metadata criteria, including facilitating document retrieval and enhancing knowledge reuse. In this study, the use of text classifiers for automatically classifying documents according to their corresponding group of semantically related documents is evaluated. Supporting documents of claims were used as representations of document discourses. The evaluation was performed under varying general conditions (such as dimensionality level and weighting method) to assess the effect of such conditions on performance, and varying classifier-specific parameters. The highest performance in terms of classification accuracy was achieved by a Rocchio classifier and a kNN classifier with the application of dimensionality reduction and using the tf-idf weighting method. A combined classifier approach was also evaluated in which the classification outcome is based on a majority vote strategy between...