Show simple item record

dc.contributor.advisorAzar, Ehsan Rezazadeh
dc.contributor.authorTorkanfar, Navid
dc.date.accessioned2019-12-06T18:49:15Z
dc.date.available2019-12-06T18:49:15Z
dc.date.created2019
dc.date.issued2019
dc.identifier.urihttp://knowledgecommons.lakeheadu.ca/handle/2453/4530
dc.description.abstractLessons learned and the knowledge gained from previous projects could save a considerable amount of time and budget in planning and construction of future projects. In the process of knowledge and experiment reuse, finding the most similar case(s) to the current project is critical and therefore, a number of methods have been developed which use different variables to represent each specific sub-area of knowledge and also to measure the similarity of the documented cases to the current project. It is hypothesized that the hierarchy of project activities, which is represented as Work Breakdown Structure (WBS) of the project, encompasses the entire scope of the project and contains the necessary information to measure the semantic similarity of construction projects. Thus, WBS could be used as an appropriate representative of the projects. In this research project, a novel method is proposed to assess the semantic similarity of projects by means of Natural Language Processing (NLP) techniques. In this method, the current project is compared with the documented as-built projects based on their WBS and the most similar ones to the current project are retrieved. The proposed WBS similarity measurement is implemented using two metrics, (1) node similarity that compares the semantics of elements in two WBSs; (2) structural similarity which compares the topology of Work Breakdown Structures. The proposed processes to estimate each of these two metrics produce a similarity score between 0 and 1. The average of these two scores provides the final similarity score between two WBSs. The method was tested using nine WBS test samples with promising results in compliance with similarity properties. Finally, the metrics were experimentally evaluated in terms of precision and recall. The results showed that the structural similarity slightly outperformed the other metric.en_US
dc.language.isoen_USen_US
dc.subjectWork breakdown structureen_US
dc.subjectNatural language processingen_US
dc.subjectCase-based reasoning (construction industry)en_US
dc.subjectSemantic web and ontologyen_US
dc.titleSemantic similarity measurement of construction projects using WBS-based similarity metricsen_US
dc.typeThesisen_US
etd.degree.nameMaster of Scienceen_US
etd.degree.levelMasteren_US
etd.degree.disciplineEngineering : Civilen_US
etd.degree.grantorLakehead Universityen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record