Çalışkan, E B (2022) A data-driven requirement elicitation system for pre-project stage. PhD thesis, Middle East Technical University, Turkey.
Abstract
Requirement knowledge of a building project is the set of crucial statements governing all processes to achieve success by matching the objectives. Briefing is the process of capturing and identifying requirements with the involvement of project stakeholders. Various improvements on deficiencies and gaps, developments on technology, and definitions on frameworks for briefing have been explored and examined worldwide over the past three decades. Knowledge capturing is one of the major processes of knowledge management for creating valuable knowledge. The construction industry adopts and uses various techniques and technologies to increase the utilization of resources. The major aim of this study is to construct a framework for the elicitation of space requirements of building projects in the design briefing stage. The study considers the deficiencies and gaps in the creation and validation of the requirement knowledge. At the outset, a survey and interviews among industry practitioners in conjunction with a literature review were carried out to state the problem definition and research areas for improving requirement management in the design and pre-design briefing stages. Subsequently, the criteria and objectives were defined to propose a novel system by utilizing the evaluation and discussion of survey results and literature review. In the light of the findings, the proposed framework was utilized to develop a novel data-driven requirement elicitation system integrating database domain and machine learning activities. The proposed system was tested and validated with seven experiments in which experts executed requirement elicitation of spaces for the same session conditions. As to the judgment of experts, the system's overall performance was regarded as satisfactory. Knowledge capturing from data libraries of completed projects with machine learning activities has been pointed out in the first place as the potential contribution of the system. It also enables the requirement elicitation process without the involvement of experienced project stakeholders. The results were discussed with the recommendations for improvement of the proposed system.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Pekeriçli, M K |
| Uncontrolled Keywords: | briefing; knowledge management; learning; machine learning |
| Index terms: | database, judgment, construction industry, literature review, survey, experiment, interview, machine learning, knowledge management, briefing, practitioner, project stakeholder, validation |
| Subjects: | data analysis and analytics, artificial intelligence, data collection methods, dispute resolution, data management, sociology, industry analysis, professional development, scope management, practitioner |
| Topics: | Digital Applications, Information Management, Research Practice, Stakeholder Management, Roles and Professions, Legal Issues, Project Management |
| Descriptive scope: | 5 PCTEA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here