A Knowledge-based Framework for Human-Centered Residential Built Environment Design

• Author / Creator

  Zhang, Yuxuan

• The considerable amount of time typically spent at home in contemporary society underscores the importance of understanding the interaction between occupants and built environments and implementing this knowledge into design practice to ensure occupant satisfaction and adequate building performance. In recent decades, the concept of human-centered design, which optimizes the environment around the occupant’s capability and preferences/requirements rather than forcing the user to change their behavior to accommodate the design, has been attracting increasing interest within building domain. However, due to the overwhelming volume of information, the dynamic nature of the decision-making context, and the multi-disciplinary knowledge (and multi-disciplinary stakeholders) involved in design knowledge management, the current practice of residential design tends to fall short of supporting well-informed decisions for creating an occupant-focused built environment. In this regard, this research aims to optimize the knowledge management of residential design in terms of knowledge explicitation, knowledge acquisition, knowledge representation, and knowledge communication in order to leverage knowledge in support of consistent and effective design decision-making, thereby maximizing design quality and improving occupant satisfaction. To accomplish this, the following four objectives targeting the optimization of the knowledge management process are pursued: (1) Develop a machine learning-based framework using the virtual reality and design-of-experiments techniques to model the implicit relationship between human perceived experience and building design attributes, where the proposed data-driven predictive model is used to evaluate the affective quality of design alternatives based on their specific design settings. (2) Develop a residential design knowledge-based decision support system to capture knowledge of occupant requirements and their associated impacts on design criteria in order to tail design specifications for specific occupant groups and support a rational resource allocation among specific design criteria. (This knowledge-based system aims to equips novice design practitioners with appropriate design knowledge and assist them in making user-centered design decisions consistently.) (3) Develop a domain ontology to formally represent the knowledge of human-centered residential design in a machine-readable format in order to promote knowledge reuse and sharing among design professionals and in computer-aided design systems, where the developed ontology is included in the knowledge-based decision support system as the knowledge resource input. (4) Develop an integrated framework for collaborative decision-making in residential design to anticipate and address potential design conflicts between stakeholders and to aid in developing consensus design solutions. The virtual reality technique is integrated with group decision-making models to eliminate barriers to knowledge communication and to the consensus-building process. Overall, this research optimizes knowledge management in residential built environment design, thereby enhancing the intelligent decision-making process and delivering a built environment that meets occupant expectations.

• Subjects / Keywords

  • residential design
  • knowledge management
  • decision making
  • human-centered design

• Graduation date

  Fall 2022

• Type of Item

  Thesis

• Degree

  Doctor of Philosophy

• DOI

  https://doi.org/10.7939/r3-dxmg-xp45

• License

  This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.