Juliana Croffi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juliana Croffi has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- David Kroll
The University of Adelaide
3 shared publications - Helen Barrie
College of Business and Law, Adelaide University, Australia
3 shared publications - Veronica Soebarto
The University of Adelaide
3 shared publications - Kelly McDougall
The Australian Alliance for Social Enterprise, University of South Australia, Adelaide, SA
1 shared publication
Latest Publications
- 3 December 2025
- Published by Architectural Science Association
SpinyLeaf App: A Tool for Human-Centric Assessment of High-Rise Building Performance in Fostering Wellbeing
Https://doi.org/10.65388/BYOJ5509 This study presents the development of a tool prototype that supports early-stage architectural design by integrating environmental simulation with machine learning models trained on post-occupancy evaluation (POE) data. The tool assesses how well high-rise buildings foster occupant wellbeing across three dimensions: Comfort, Delight, and Social. It bridges the gap between performance-based design and...
- 3 December 2025
- Published by Architectural Science Association
SpinyLeaf App: A Tool for Human-Centric Assessment of High-Rise Building Performance in Fostering Wellbeing
Https://doi.org/10.65388/BYOJ5509 This study presents the development of a tool prototype that supports early-stage architectural design by integrating environmental simulation with machine learning models trained on post-occupancy evaluation (POE) data. The tool assesses how well high-rise buildings foster occupant wellbeing across three dimensions: Comfort, Delight, and Social. It bridges the gap between performance-based design and...
- Open Access
- 7 November 2025
- Published by Emerald Publishing in Smart and Sustainable Built Environment
- p. 1-30
A machine-learning approach for evaluating occupants’ indoor environment satisfaction in high-rise mixed-use buildings
Purpose: This paper presents a pilot study of a machine learning (ML) approach to predict occupants' satisfaction with the indoor environment in high-rise mixed-use buildings, aiming to validate a proof of concept for integrating ML models into early-stage design tools to support occupant-centred performance evaluation. Design/methodology/approach: Using post-occupancy evaluation data from a case study building, Random Forest and Neural Network models were trained to classify satisfaction levels–Dissatisfied, Neutral or Satisfied–for both residents and workers based on indoor environmental factors. The methodology focuses on addressing class imbalance through data resampling and cost-sensitive learning, with model performance assessed using class-specific metrics. Findings: Both models achieved high overall accuracy (cross-validation score >0.80), with notable improved performance in identifying minority classes after balancing methods were employed. While limited to a single case study, future data collection across diverse buildings and occupant profiles has the potential to improve performance and enable generalisability. Originality/value: This research demonstrates the feasibility of a scalable framework for predicting indoor environmental satisfaction, enabling the integration of ML models into simulation-based workflows for data-driven, occupant-centric design evaluation. It advances the field by (1) classifying satisfaction into three actionable categories while explicitly addressing class imbalance, (2) operationalising POE data to move beyond retrospective reporting and (3) establishing a proof of concept for embedding ML models into early-stage design tools.
- 7 November 2025
- Published by Emerald Publishing in Smart and Sustainable Built Environment
- p. 1-30
Open AccessA machine-learning approach for evaluating occupants’ indoor environment satisfaction in high-rise mixed-use buildings
Purpose: This paper presents a pilot study of a machine learning (ML) approach to predict occupants' satisfaction with the indoor environment in high-rise mixed-use buildings, aiming to validate a proof of concept for integrating ML models into early-stage design tools to support occupant-centred performance evaluation. Design/methodology/approach: Using post-occupancy evaluation data from a case study building, Random Forest and Neural Network models were trained to classify satisfaction levels–Dissatisfied, Neutral or Satisfied–for both residents and workers based on indoor environmental factors. The methodology focuses on addressing class imbalance through data resampling and cost-sensitive learning, with model performance assessed using class-specific metrics. Findings: Both models achieved high overall accuracy (cross-validation score >0.80), with notable improved performance in identifying minority classes after balancing methods were employed. While limited to a single case study, future data collection across diverse buildings and occupant profiles has the potential to improve performance and enable generalisability. Originality/value: This research demonstrates the feasibility of a scalable framework for predicting indoor environmental satisfaction, enabling the integration of ML models into simulation-based workflows for data-driven, occupant-centric design evaluation. It advances the field by (1) classifying satisfaction into three actionable categories while explicitly addressing class imbalance, (2) operationalising POE data to move beyond retrospective reporting and (3) establishing a proof of concept for embedding ML models into early-stage design tools.
- Open Access
- 2 January 2023
- Published by Ubiquity Press, Ltd. in Buildings and Cities
- Vol. 4 (1) , 507-523
Wellbeing fostered by design: a framework for evaluating indoor environment performance
High-rise urban development has been controversial for its inability to foster cohesive and flourishing neighbourhoods. A social value perspective can help to better understand and evaluate how new developments in dense urban settings affect places and communities. While the link between wellbeing and social value is well-established in the literature, the question of how design can affect wellbeing and thus contribute to the social value of a development still requires further research and clarification. A better understanding of this relationship can assist architects, developers or consultants during the design process. A review is presented of relevant quantifiable aspects of building design that affect wellbeing in relation to the indoor environment and to social value specifically. A framework for fostering wellbeing is developed to test these aspects and evaluate the indoor environment performance. A case study building is used to analyse the relationship between building design and wellbeing. These lessons can be used to inform and evaluate building design during the design phases to complement the assessment of qualitative factors within a social value framework. Practice relevance This study identifies quantifiable aspects of the indoor environment affecting wellbeing in a high-rise development that can form part of a social value framework. This list of identified aspects provides a useful starting point for architects or consultants to assess designs. The indicators relate to quantifiable indoor environment aspects that can be directly controlled by building design and complement the broader concepts of wellbeing within a social value framework. The paper demonstrates how these aspects can be quantified in a case study mixed-use urban development as part of a post-occupancy evaluation. These quantifiable aspects could be integrated within digital tools to evaluate the building at the design stage to ensure that wellbeing is at the forefront of the project considerations.
- 2 January 2023
- Published by Ubiquity Press, Ltd. in Buildings and Cities
- Vol. 4 (1) , 507-523
Open AccessWellbeing fostered by design: a framework for evaluating indoor environment performance
High-rise urban development has been controversial for its inability to foster cohesive and flourishing neighbourhoods. A social value perspective can help to better understand and evaluate how new developments in dense urban settings affect places and communities. While the link between wellbeing and social value is well-established in the literature, the question of how design can affect wellbeing and thus contribute to the social value of a development still requires further research and clarification. A better understanding of this relationship can assist architects, developers or consultants during the design process. A review is presented of relevant quantifiable aspects of building design that affect wellbeing in relation to the indoor environment and to social value specifically. A framework for fostering wellbeing is developed to test these aspects and evaluate the indoor environment performance. A case study building is used to analyse the relationship between building design and wellbeing. These lessons can be used to inform and evaluate building design during the design phases to complement the assessment of qualitative factors within a social value framework. Practice relevance This study identifies quantifiable aspects of the indoor environment affecting wellbeing in a high-rise development that can form part of a social value framework. This list of identified aspects provides a useful starting point for architects or consultants to assess designs. The indicators relate to quantifiable indoor environment aspects that can be directly controlled by building design and complement the broader concepts of wellbeing within a social value framework. The paper demonstrates how these aspects can be quantified in a case study mixed-use urban development as part of a post-occupancy evaluation. These quantifiable aspects could be integrated within digital tools to evaluate the building at the design stage to ensure that wellbeing is at the forefront of the project considerations.