AHFE Open AccessHuman Factors in Architecture, Sustainable Urban Planning and Infrastructure
Editors: Alicja Maciejko, Silvia Albano
Topics: Sustainable Urban Planning and Infrastructure
ISBN: 979-8-950676-05-5
DOI: 10.54941/ahfe1007248
Table of Contents
Impacts of Atrium Geometric Characteristics in University Research Buildings on Occupants’ Restorative Performance
University researchers who spend prolonged periods in indoor environments are prone to increased psychological stress and decreased attention, which is widely confirmed in previous research. Indoor open spaces in research buildings, particularly atriums, are recognized as restorative environments that can provide a temporary escape from work areas, facilitating emotional and cognitive recovery. Existing studies have primarily focused on the physical environmental performance of atrium, such as daylighting and ventilation. Although the geometric characteristics of atrium have been shown to influence indoor environmental performance, empirical evidence on their effects on occupants’ restorative experiences remains limited, which constrains a comprehensive evaluation of atrium performance.This study aims to investigate the effects of atrium geometric characteristics on occupants’ restorative performance in university research buildings through virtual reality. 6 experimental scenarios were designed, covering 4 geometric variables: bidirectional expansion, unidirectional elongation, number of stories, and overall form. 30 participants were recruited, and both psychological and physiological data were collected. The results indicate that certain experimental conditions significantly enhanced psychological restorative effects, whereas no significant between-scenario differences were observed in physiological indicators. This study empirically examines the restorative potential of indoor atrium geometry and provides methodological and theoretical contributions for evidence-based design of built environments aimed at enhancing occupants’ well-being.
Ziqi Zhang, Xiaoxi Cheng
Open Access
Article
Conference Proceedings
A Hierarchical Architectural Decision Model for Residential Heat Resilience (DMHR)
Contemporary residential architecture faces a structural tension between energy efficiency and heat resilience. While building regulations and sustainability standards have historically prioritized winter insulation and the reduction of heating demand, the increasing frequency, intensity, and duration of extreme heat events in Europe challenge this paradigm. The summer of 2022—associated with over 61,000 heat-related deaths across Europe—exposed the vulnerability of highly insulated housing stock, particularly among elderly and low-income populations (Ballester et al., 2023).This paper proposes DMHR, a hierarchical decision-support design model for thermal resilience, developed and demonstrated through an 8×16 m modular reference design adapted to three climatic contexts: Warsaw (Cfb), Istanbul (Csa—humid), and Seville (Csa/BSh—hot dry). The research applies climate-based analytical design modelling grounded in literature-derived thermal performance ranges and health-oriented thresholds, rather than dynamic simulations. DMHR structures interventions into three cumulative levels: (L1) passive architectural filtering (geometry, shading, and thermal mass), (L2) physiological support through controlled air movement and night ventilation, and (L3) targeted active cooling in a “Safe Room” as a life-safety layer during heat extremes. The findings indicate that passive strategies remain foundational but can reach physiological limits under severe heat, making minimal yet strategic active cooling relevant to protect nocturnal regeneration and reduce health risk. The study reframes thermal design as a matter of climate justice and positions architecture as an external regulator of human thermophysiology rather than merely a tool for annual energy optimization.
Alicja Maciejko, Michal Grzeskowiak, Antonina Kowalska
Open Access
Article
Conference Proceedings
Effects of Stair Geometry and Surrounding Factors on Perceived Vertical Ascending Distance
Stair design involves not only physical attributes such as form and material but also psychological factors that shape users’ perceptual experiences. However, empirical studies focusing on the perception of upward movement during stair ascent remain limited. This study examines how stair configuration and surrounding environmental factors influence the sense of upward movement, quantified as Perceived height, using an immersive virtual environment.Five factors were manipulated: WIDTH, WALL, TYPE, MATERIAL, and WALKING SPEED. Participants ascended virtual stairs corresponding to a 10-step staircase. After each ascent, they reproduced the vertical distance they perceived having ascended by adjusting the height of a virtual object, which was defined as Perceived height.As a result, WIDTH exerted the strongest influence on Perceived height. The 1200 mm width condition produced a significantly smaller Perceived height than the 1500 mm condition, whereas no significant differences were observed between the 900 mm and 1200 mm conditions or between the 900 mm and 1500 mm conditions. No significant effects were found for WALL, TYPE, MATERIAL, or WALKING SPEED.Overall, the results indicate that stair width independently modulates perceptual scaling during ascent. In particular, medium-width stairs may attenuate the perceived magnitude of vertical movement relative to wider stairs, highlighting stair width as an important design parameter for shaping psychological experiences of vertical movement.
Takumi Nagata, Yohsuke Yoshioka
Open Access
Article
Conference Proceedings
Collaborative Governance for Urban Regeneration: Mapping the contributions of Real Estate Professionals, Local Authorities, and Investors in Harare's CBD Renewal
Sustainable inner-city regeneration is a complex process that requires the collaboration of various stakeholders, including real estate industry practitioners. This study aimed to determine the contribution of real estate professionals in the quest for sustainable inner-city regeneration in Harare's Central Business District (CBD). A mixed-methods approach was employed, involving a survey of 131 respondents and interviews with key stakeholders. The findings revealed that real estate professionals, including property managers, investors, brokers, and valuers, play a crucial role in driving and benefiting from regeneration efforts. Their expertise spans across planning and analysis, advocacy and policy reform, project management and risk mitigation, property valuation and financial modelling, community engagement and social inclusion, capacity building and training, and enabling public-private partnerships. The study found that the involvement of real estate experts enhances property values, triggers economic activity, and promotes the diversification of property development. The engagement of real estate professionals also brings widespread sectoral benefits, including improved housing value, increased investor confidence, stimulated demand for green building materials, enhanced urban aesthetics, increased diversification of property development types, and improved public health and environmental outcomes. The study concludes that harnessing the potential of real estate practitioners and other stakeholders is essential for moving Harare toward a resilient, inclusive, and sustainable urban future.
Faith Dowelani, Progress Kamonere
Open Access
Article
Conference Proceedings
A Relational Architectural Model for Health-Oriented Housing
This paper proposes Relational Healing Housing (RHH) as a conceptual architectural research model integrating environmental health, relational configuration, and regenerative spatial principles within residential design. Drawing on salutogenic theory, environmental psychology, biophilic research, and evidence-informed healthcare design, the model translates therapeutic spatial logics from institutional settings into housing and settlement structures. The elementary 35 m² unit is defined as a spatial threshold supporting autonomy, internal zoning, and cognitive stability, while allowing aggregation for caregiving and multi-generational arrangements. At the settlement scale, a circular configuration of houses is organized through layered spatial gradients, including a rain-garden canal buffer, a service ring, and a minimally programmed central open space. The model synthesizes literature-based indicators and empirical survey findings, including preferences for spatial autonomy, access to greenery, and cohabitation with animals. Positioned as a pre-implementation research instrument, RHH enables structured spatial analysis and comparative evaluation at the conceptual design stage. The study contributes an adaptable archetype for health-oriented communal housing in contemporary urban contexts.
Alicja Maciejko
Open Access
Article
Conference Proceedings
Distinct Roles of Route and Node Memory in Indoor Wayfinding: Evidence from a Virtual Reality Study
Large public buildings often pose wayfinding challenges, which can affect users’ spatial experience and comfort. Understanding how people navigate these environments is important for both design and experimental research. How people navigate indoor spaces depends on how they remember paths and decision points. This study looks at how two types of memory – route-based and node-based -- affect wayfinding performance in virtual reality (VR) environments. Participants completed wayfinding tasks in four representative layouts and subsequently reconstructed their travelled routes and visited decision points. We analysed how route memory and node memory predicted wayfinding efficiency. The results show that in linear, corridor-like layouts, wayfinding performance is mainly linked to route memory. In layouts with open activity spaces at intersections or central nodes, node memory becomes more important. Some layouts showed no clear link with either memory type, suggesting that the influence of route and node information varies with spatial layout.These findings demonstrate that route and node memory play distinct roles in indoor wayfinding, influenced by spatial configuration, and provide empirical guidance for VR-based studies on spatial cognition and experimental design. Understanding these patterns can also inform building design and layout strategies to improve users’ wayfinding experience in complex indoor environments.
Xiaohan Mei, Shengxi Cao, Haiming Zhao, Li Zhang
Open Access
Article
Conference Proceedings
Practices of Coexistence: Exploring Human-Nature Relations in Urban Community Gardens
This study examines how human–nature relations are enacted, negotiated, and made meaningful within two distinct community garden settings. The research explores how humans, nonhumans, and material entities co-constitute everyday practices and how these practices form, transform, and interconnect. Ethnographic fieldwork was conducted at two urban garden sites selected for their forms of community involvement and ecological engagement. Participatory observation and interviews were conducted, and the data were analyzed using thematic analysis of fieldnotes and interview transcripts. The first garden is characterized by long-term continuity, strong neighborhood identity, and a diverse group of local residents who receive plots through an annual lottery. Spatial and material decisions play an important role in place-making and reinforce communal belonging. The second site is a student-led community garden guided by ecological agriculture principles. Participants co-create social spaces, build infrastructures, and collectively solve problems arising from environmental conditions. These practices reveal cycles of experimentation, learning by doing, and close observation of natural processes. Gardeners actively negotiate the boundaries of intervention by adopting low-impact techniques, biodegradable materials and regeneration methods while constructing necessary infrastructures. Field observations from both sites show how gardening practices intertwine social, ecological, and material relationships. Both sites illustrate how self-built infrastructures, material improvisation, and everyday spatial decisions contribute to place-making and to the shaping of sustainable micro-environments. By analyzing how everyday practices and multispecies relations come together in these two community garden settings, the study contributes to understanding how ecological coexistence is cultivated and how community-led spaces model responsible human–nature relations.
Ayşe Yılmazaslan, Cigdem Kaya
Open Access
Article
Conference Proceedings
Childcare-Friendly Play Spaces for Parents in Community Parks
Childcare behavior refers to the attention and care provided by caregivers, especially parents, during outdoor activities. Caregivers’ level of engagement and demeanor directly affect children's self-protection, independence, and social skills. This study explores childcare behaviors in community parks, focusing on child safety and development. Using virtual reality (VR) to simulate park environments, we developed a method to quantitatively compare parental care across different site types. Grounded in urban ergonomics, the research analyzed eye-tracking data and survey responses from 28 parents in Beijing to assess how spatial design affects caregiving. Results show that site size influences perceived safety, with areas under 32 meters in diameter providing optimal visibility. Shrubs around 0.9 meters high were rated as the safest boundary type, balancing visibility and containment. This research informs evidence-based park design and enhances urban spatial research by integrating behavioral data with ergonomic principles. While findings offer valuable guidance for child-friendly park planning, the small sample size and use of VR may limit generalizability.
Xinran Li, Yifan Liu, Haichuan Li, Xiaoxi Cheng
Open Access
Article
Conference Proceedings
How Street–Building Geometry Modulates the Effectiveness of Smartphone Map Orientation Methods in Direction Judgment
This study investigates how variations in street patterns and building arrangements, combined with the orientation display methods of smartphone map applications—specifically North-Up and Heading-Up—influence users' map-reading performance. By establishing street configurations that combine simple or complex building shapes with various intersection geometries, the study isolated these factors to examine their respective impacts on self-localization. Using a Virtual Reality (VR) environment with a head-mounted display, 22 participants performed self-orientation tasks across eight experimental conditions. These conditions combined the two map display methods with four distinct street configurations, created by hybridizing two intersection types (orthogonal vs. skewed) and two building types (uniform vs. diverse). Analysis revealed that the Heading-Up orientation consistently resulted in shorter self-localization times than the North-Up orientation, with this difference being particularly pronounced in skewed intersections. In contrast, environments composed of orthogonal intersections and uniform building shapes led to longer task completion times, suggesting a lack of salient visual cues. Conversely, orthogonal intersections combined with diverse building shapes significantly facilitated self-localization.
Momoko Sakai, Yohsuke Yoshioka
Open Access
Article
Conference Proceedings
An Examination of Challenges for Property Owners and Occupants in Decaying Urban Cores - A Case Study of Harare, Zimbabwe
Urban decay is a significant problem in major cities worldwide, and Harare, Zimbabwe, is no exception. The central business district (CBD) of Harare has experienced a significant decline in building quality, functionality, and visual attractiveness due to poor economic management, inadequate maintenance, and urban planning failures. This study examines the challenges faced by property owners and occupants in the decaying urban core of Harare. A mixed-method design was employed, involving a survey of 131 respondents and in-depth interviews with key stakeholders. The findings reveal that the top challenges identified by respondents include poor service delivery (mean = 4.40), lack of coordinated planning for building rehabilitation (mean = 4.34), lack of infrastructure development funding (mean = 4.11), overcrowding (mean = 4.04), and unemployment (mean = 4.02). Interview respondents confirmed these findings, emphasising broken infrastructure, poor planning, and insufficient political will. The study aligns with previous research on inner-city challenges, highlighting issues such as poor housing, unemployment, financing infrastructure development, and a lack of coordinated building rehabilitation. The results demonstrate the need for local government to prioritise improvements in service delivery, particularly in waste management, sanitation, and public safety. Additionally, access to financial and technical expertise is crucial for successfully implementing regeneration strategies. The study concludes that addressing the challenges in Harare's CBD requires a holistic, stakeholder-driven approach that reconciles short-term concerns with long-term sustainability targets.
Faith Dowelani, Progress Kamonere
Open Access
Article
Conference Proceedings
Travel Environment for the Elderly in Cultural Heritage Cities: Comparative Study
In the context of rapid urbanization and accelerating population aging, historic urban areas with rich cultural heritage are facing an increasingly acute contradiction between the historical characteristics of their spatial fabric and the contemporary travel needs of their elderly residents. This study selects three representative Chinese heritage cities—Xi'an (an inland dynastic capital), Quanzhou (a port trade city), and Macau (a colonial heritage city of East-West cultural fusion)—as comparative cases. Through a cross-case mixed-methods research design, we systematically investigate how different historic urban forms and heritage conservation paradigms shape elderly travel environments. The research methodology integrates the following elements: (1) a standardized 10-item environmental audit of pedestrian infrastructure in each city's core historic district; (2) a structured questionnaire survey of elderly residents, collecting data on travel habits, perceived barriers, and subjective needs; and (3) an analysis of local heritage conservation and age-friendly urban renewal policy documents. Key findings indicate that different urban forms generate distinctive core challenges: Xi'an's monumental grid layout results in a lack of long-distance walking transit nodes; Quanzhou's dense organic street network presents latent pedestrian-electric vehicle conflict hazards; Macau's high-density hillside terrain creates significant accessibility barriers due to steep gradients. Heritage conservation requirements impose qualitatively different constraints and opportunities on age-friendly intervention measures across all three cases. Each city has also developed unique local adaptive strategies: Xi'an's informal resting settlements along the ancient city wall base, Quanzhou's arcade-style shop corridors as natural sheltered spaces, and Macau's community-embedded informal escort network system. The study concludes that enhancing heritage city friendliness for older adults requires a context-sensitive Diagnose-Adapt-Transform (DAT) pathway rather than universal design standards.
Zhiyuan Zheng, Yaoyao Yu
Open Access
Article
Conference Proceedings
Impact of Street Landscape Factors on Noise Exposure: An XGBoost - SHAP Modelling Approach
Urban street sound exposure levels serve as critical physical indicators for assessing traffic noise pollution. While existing research has focused predominantly on source parameters such as traffic volume and speed, systematic investigations into the potential regulatory mechanisms of street landscapes remain limited. This study aims to quantify multidimensional street landscape factors and, employing an explainable machine learning approach, precisely decipher their impact degree and underlying mechanisms on noise exposure level (NEL). Through the collection of street view imagery and semantic segmentation techniques, morphological indicators, including the sky view factor, green view ratio, building interface height and continuity, and road width, were extracted. The daytime equivalent continuous A-weighted sound pressure level (LAeq) was used as the NEL metric. An XGBoost machine learning model was constructed, with street landscape factors as the core independent variables for NEL prediction. The SHapley additive exPlanations framework was incorporated to quantify the contribution of each factor, revealing nonlinear relationships and interaction effects with NEL. The results demonstrate the following findings. First of all, the XGBoost model achieved high predictive accuracy for NEL, outperforming traditional benchmark models. Secondly, street landscape factors exhibited significant explanatory power for NEL, with contribution levels comparable to those of some traditional source parameters.Additionally, pronounced nonlinear relationships were identified between key factors, such as building interface height and continuity. Lastly, interaction effects existed among street landscape factors, manifesting as synergistic noise reduction or antagonistic effects under specific combinations. This research deepens the understanding of urban sonic environment formation mechanisms both theoretically and methodologically. Theoretically, street landscape factors are key environmental variables regulating NEL, promoting a paradigm shift in noise research from “source management” to “environmental mediation”. Methodologically, the developed XGBoost-SHAP framework provides a powerful, explainable tool for addressing nonlinearity and interactions within complex urban systems. Practically, the findings offer a quantitative basis for implementing coordinated “source‒path” noise mitigation at the forefront of urban planning and design, translating abstract acoustic goals into precise spatial design language and advancing a data-driven preventive environmental governance model.
You Li, Yuwei Wu, Yan Huang
Open Access
Article
Conference Proceedings
Effects of the Pony Wall Position and Memory Strategy on Reproduced Spatial Depth in a Virtual Environment
Physical occlusion, particularly of the ground surface, often distorts distance perception in indoor environments. However, how observers' visual search strategies modulate this effect remains unclear. This study investigated how pony wall placement (Non, Left, Center) affects egocentric distance perception under two instructional strategies: Geometric and Holistic. Using Virtual Reality, participants estimated distances while eye movements were recorded. Results revealed a significant difference between strategies. The Geometric group maintained distance accuracy even in the Center condition where the floor was occluded. Fixation analysis showed they actively compensated for missing ground information by increasing fixations on side walls to extract linear perspective cues. Conversely, the Holistic group—reflecting natural daily spatial experience—significantly underestimated distance in the Center condition. The salient pony wall attracted their gaze, reducing attention to the far wall, which provides crucial depth information for spatial boundaries. This gaze attraction hindered integrated perception of the entire space.These findings reveal an important distinction. The analytical search strategy overcame physical constraints through side walls that served as alternatives to the interrupted floor continuity. In contrast, the holistic strategy typical of daily experience was vulnerable to central occlusion due to gaze attraction. For architectural design, this suggests that ensuring visual permeability—specifically, maintaining gaze access to the far wall—is essential for preserving the sense of spaciousness and supporting natural spatial experience. Therefore, when placing pony walls, designers should consider not only physical area but also the psychological quality of spatial perception.
Amon Onodera, Yohsuke Yoshioka
Open Access
Article
Conference Proceedings
Human-Centered Risk Scenario Modelling for Urban and Infrastructure Resilience
Cities and infrastructure networks are increasingly exposed to interconnected risks that propagate across physical, digital and organizational boundaries. Traditional risk registers and isolated analyses do not capture this dynamic and multi-domain behavior. This paper proposes a human-centered risk scenario modelling methodology that integrates process logic, spatial dependencies, human roles and regulatory constraints into a unified architectural framework. The approach extends classical bow-tie analysis, introduces modular behavioral structures and applies human-factors principles, particularly situational awareness, to interpret evolving risk conditions. A prototype implementation demonstrates how the methodology can be embedded in an enterprise architecture environment to support coherent scenario reasoning. The proposed method provides a conceptual foundation for strengthening urban resilience through clearer causal understanding, improved situational awareness and more informed decision-making.
Taivo Kangilaski, Jaanus Kaugerand
Open Access
Article
Conference Proceedings
D-GAM: An Adaptable Gamification Framework for Enhancing Public Participation in Built Environment Design
Public engagement is central to decision-making in built-environment design, yet traditional participation methods are often limited in reaching diverse audiences or sustaining meaningful involvement. Gamification offers potential to support stakeholder engagement by introducing game-like elements that can guide participation and clarify user actions. However, many existing platforms rely on fixed, system-level implementations of gamification, limiting their ability to respond to the varying contexts and expectations of different design projects. Given the diversity of built-environment initiatives, more adaptable approaches are needed to support participation across projects and stakeholder groups.This work introduces D-GAM, a flexible gamification framework designed to support public participation in built-environment design processes. Rather than prescribing a fixed set of features, D-GAM is a platform-agnostic, project-level framework that allows gamification elements—such as rewards, progress tracking, and feedback—to be configured to meet specific project needs. Grounded in Self-Determination Theory, the framework emphasizes motivation through structured participation, recognition of user contributions, and clear interaction cues. To illustrate its adaptability, we present a scenario focused on social participation and community interaction. The scenario demonstrates how D-GAM can be operationalized within a design review context. Together, the framework and scenario establish a conceptual foundation for future prototype development, visual implementation, and empirical user studies to examine, in greater depth, usability, engagement, and participation outcomes.
Mehrun-nisa Raja, Halil Erhan
Open Access
Article
Conference Proceedings
Elevator Installation in Old Residential Communities (EIOC): Towards Sustainable Urban Renewal
The renovation of old residential neighborhoods is a key component of China’s urban renewal agenda, and elevator installation has emerged as an urgent need to improve older adults’ quality of life and promote sustainable community renewal. However, the rate of elevator installation remains relatively low. Therefore, this paper systematically reviewed relevant papers from CNKI and WoS, and adopted a bibliometrics study to identify the underlying issues and the research progress. The result shows there is a significant growth in EIOC research since 2020, focusing on the following five directions: (1) policy and governance; (2) finance and operations; (3) planning and design; (4) legal aspects; (5) construction and engineering. Research on EIOC is highly interdisciplinary. Future research with a truly interdisciplinary lens is needed. Advancing this integrated knowledge is paramount for transforming EIOC from a technical retrofit into a cornerstone of sustainable, age-friendly, and socially resilient urban communities, a core concern for the sustainable urban renewal agenda.
Xie Shiyang, Zhou Fang, Xiaorui Yang, Zhen Wang, Yao Hao Yang, Bingqing Tang
Open Access
Article
Conference Proceedings
Designing hospital modernisation using mathematical graph methods
Designing hospital modernisation projects is both a challenge and a necessity in view of the rapid development of medical technologies and treatment processes. In addition, ageing populations are driving an increasing demand for medical services. The quality of space has been proven to support treatment processes and the pace of patient recovery, as well as the comfort of staff and the organisational and economic efficiency of the hospital. It is therefore advisable to make very conscious investment decisions. A precise and objective assessment of the existing condition, including, above all, functional and spatial solutions, is very important in hospital modernisation processes. New technologies often necessitate changes to the existing functional layout, and sometimes the existing layouts are not without flaws. However, hospitals are highly complex facilities, where change management requires decision-making support and adequate tools.Research has demonstrated the applicability of mathematical graph theory to describe complex functions and the interrelationships between them, taking into account the lighting of selected rooms.Treating the functional layout of a building as a discrete structure with connections, i.e. as a simple graph, is a natural (though often unconscious) practice in the work of an architect. However, thinking of such a structure of connections as a dual graph to a certain flat graph provides additional opportunities for a deeper understanding of the ambiguous relationship between the functional layout of a building and its floor plan. This way of visualising data on the desired adjacencies of rooms, which in hospitals result from the necessary safety conditions and optimisation of medical processes through efficient space, shows enormous potential for supporting design decisions.The adopted method combines architecture and mathematics in a visual way, using graphs and matrices to illustrate the existing relationships between rooms.
Agata Banaszyk-Jakubowska, Agata Gawlak, Agnieszka Rumież
Open Access
Article
Conference Proceedings
Marine Protected Area (MPA) Digital Twin Framework and Its Perspectives
Marine Protected Areas (MPAs) are increasingly recognised as critical infrastructures for biodiversity conservation, climate regulation, and the resilience of coastal socio-ecological systems, while also supporting emerging Blue Economy strategies. Among the ecosystems they safeguard, Posidonia oceanica meadows represent a particularly valuable and vulnerable component of the Mediterranean seascape, providing long-term carbon sequestration. This paper proposes a Digital Twin (DT) framework for the Marine Protected Area of Ischia (Regno di Nettuno), conceived as a dynamic, data-driven system to support continuous monitoring, adaptive governance, and the development of Blue Carbon initiatives. By integrating heterogeneous data streams across ecological, infrastructural, and socio-economic dimensions, the system aims to support continuous monitoring, risk assessment, and evidence-based governance.The methodology combines an analysis of data availability and accessibility with a systematic mapping of stakeholders and activities. The DT is designed as a circular data–action–feedback chain, transforming input data into descriptive and predictive outputs—such as what-if scenarios and dynamic cartographies—which are disseminated through web, mobile, and Digital Twin interfaces. These outputs inform stakeholder activities and are enacted through a set of regulatory, ecological, socio-economic, participatory, and technical actuators, generating real-world interventions and new data inputs. The proposed framework shows the MPA DT designed as a socio-technical interface that connects marine ecosystems, informed decision-making, and civic engagement, fostering more resilient and inclusive approaches to marine conservation.
Letizia Artioli, Giovanni Borga, Pietro Costa
Open Access
Article
Conference Proceedings
Bridge Inspection Support Framework Incorporating Human Reliability
In Japan, periodic road-bridge inspections rely primarily on inspectors’ close visual examination at five-year intervals. Concurrently, the proportion of aging bridges is increasing while the availability of experienced inspectors is expected to decline, amplifying the demand for support tools that reduce workload without compromising safety assurance. This study proposes a bridge-deck inspection support framework grounded in human–AI collaboration and presents its core application for crack-candidate visualization on concrete decks. The framework enforces an explicit division of roles: the AI is restricted to presenting and visualizing crack candidates, whereas inspectors retain responsibility for close visual inspection, on-site measurement, and final condition assessment. As the AI component, we developed a semantic-segmentation model that estimates crack presence at the pixel level and implemented post-processing to suppress short, spurious detections while preserving line-like crack structures. Evaluation results indicate that missed detections of cracks as continuous line-like structures were rare in our test set, including images with diverse surface appearances. False positives occurred predominantly as short segments, which—while requiring verification—are typically less hazardous than misses in safety-critical inspections and can be treated as conservative prompts for closer examination. Accordingly, this study frames crack detection not solely as an accuracy problem but as a human reliability intervention: a “safety-oriented filter” that redistributes attention from exhaustive search to prioritized verification, thereby mitigating lapse-type inspection errors. The findings suggest that the proposed framework can support safer attention allocation while maintaining inspector accountability.
Yuki Murata, Kosei Koizumi, Akito Sakurai, Yusaku Okada
Open Access
Article
Conference Proceedings
The Effect of Wall Shapes on the Startle Reaction of Pedestrians on Half-Turn Staircases
The present study investigated the influence of wall shape in half-turn staircases on startle reactions using a controlled virtual environment experiment.A virtual stairway model representing an ascent toward a landing was created in Unity. Participants viewed first-person walking footage through a head-mounted display (VIVE Pro Eye, HTC) while remaining seated, and their skin potential activity and walking continuation time were measured during the experiment. To simulate an unexpected encounter at the location where visibility is most restricted, a descending humanoid avatar appeared immediately before the participant reached the landing.Two experimental factors were manipulated: pedestrian presence (present/absent) and wall shape (four types). One full-height wall (2400 mm) and three handrail-wall configurations (700 mm, 900 mm, 1100 mm), each featuring a 1000 mm sloped coping, were tested. The results demonstrated that the inner wall configuration of a half-turn staircase significantly influenced both walking behavior and skin potential responses. Under the full-height wall condition, restricted visual information delayed the recognition of an approaching pedestrian. As a result, the decision to stop was delayed, leading to a longer walking continuation time. In contrast, under the handrail-wall configurations, improved visibility enabled earlier pedestrian detection and facilitated quicker avoidance decisions, resulting in a shorter walking continuation time. Furthermore, the presence of a pedestrian increased the startle response, and this effect was particularly pronounced under the full-height wall configuration, where visual occlusion was greater. By comparison, under the handrail-wall configurations, the increase in skin potential response associated with the pedestrian’s presence was relatively attenuated. Overall, these findings suggest that wall openness constitutes a meaningful architectural implication for improving psychological comfort and safety perceptions in circulation spaces.
Takeshi Ona, Yohsuke Yoshioka
Open Access
Article
Conference Proceedings
PEFT Strategies for Human–AI Co-Creation in Architectural Morphogenesis
Generative AI is reshaping early-stage architectural design, yet the cognitive demands placed on designers navigating highly parameterised workflows remain underexamined. This study investigates how four parameter-efficient fine-tuning (PEFT) strategies in Stable Diffusion influence human–AI co-creation, interpretability, and designer control in biomimetic architectural morphogenesis. Four configurations—Baseline, Shared LoRA, IP-Adapter (w=0.8), and a custom fine-tuned LoRA—were evaluated using MorphEvalBench, a newly developed evaluation toolkit. Fidelity and diversity metrics were operationalised as proxies for designer cognition: biomimetic fidelity (DSS), distributional fidelity (FID/KID), and diversity (DIV). A visual benchmarking grid across representative token levels complemented quantitative analysis. Results reveal that IP-Adapter achieved the strongest quantitative profile across all dimensions, yet its visual conditioning mechanism introduces patterns independently of prompt specification at w≥0.6, reducing designer control and requiring management of multiple interacting parameters. Fine-tuned LoRA demonstrated a balanced profile with greater semantic stability, enabling prompt-driven control and emergent diversity driven by designer input. Notably, the fine-tuning process itself constitutes a design act, embedding the designer's intent into the model prior to generation. These findings demonstrate that quantitative superiority does not guarantee cognitive supportiveness, and propose four implications for designing cognitively supportive human–AI workflows in architectural practice.
Chie Fuyuki, Shuichi Nagao, Vadim Grigorev, Rim El Filali, Jian Du
Open Access
Article
Conference Proceedings
Application of Generative design in Urban Planning
Generative design is reshaping urban planning, becoming a major theme in modernisation; however, many aspects of this development are disjointed, with many methods and application areas scattered across the field. Performing this systematic review of literature, we integrated the adoption of generative techniques showing the transition from initial parametric rule-based systems to recent deep learning models, and found the main topics in the publications. Following PRISMA rules, our focused search and screening procedure resulted in 175 peer-reviewed papers that were classified according to eight main areas of investigation. The data shows a distinct move from using simple parametric rules to designing urban forms through probabilistic generative adversarial networks (GANs) and diffusion models; the considerable amount of performance-based design literature focusing on optimising energy consumption, environmental quality and mobility; and participatory planning gradually adopting human-in-the-loop generative systems, but scalability remains problematic. The use of large language models (LLMs) for policy simulation is an initial area that is growing very fast. Unfortunately, the problem of measuring effectiveness and considering ethics, such as bias, transparency, and accountability, is very weak across this research field. This paper posits that even when generative design can automate and improve urban planning processes to a great extent, substantial problems still exist in the lack of standard evaluation frameworks, ethical guidelines and the genuine interweaving of human agency. Future research should therefore prioritise robust validation methods and participatory governance models to ensure that generative urbanism delivers equitable and sustainable urban outcomes.
Udit Shivansh, Saptarshi Kolay, Vivek Jain
Open Access
Article
Conference Proceedings
Human-Level Barriers to Generative AI Adoption in Architectural Practice
Generative artificial intelligence is entering architectural practice rapidly, although it is not yet possible to speak of full adoption, since it is used for informal experimentation such as ideation, visualisation, drafting, text production, and workflow acceleration. This narrow interpretation overlooks a deeper human-level adoption gap. The central challenge is not only whether AI systems can produce useful design-related outputs, but whether architectural practices can integrate them responsibly within workflows shaped by key professional and procedural constraints. This paper addresses this gap by examining the barriers, readiness conditions, and governance requirements for responsible generative AI adoption in architectural practice. The study is a PRISMA‑guided systematic review and thematic synthesis of peer‑reviewed articles, proceedings, book chapters, and selected governance documents (2014–2026) from architecture, design research, HCI, human factors, automation, AI ethics, and governance. Instead of evaluating individual AI tools or collaboration models, it analyses reported human‑level barriers and enablers across five interrelated dimensions: trust and reliance, accountability and provenance, skills and role transformation, organisational readiness, and professional governance. The synthesis is then mapped to RIBA project stages to identify where risks, responsibilities, and verification thresholds change across the project lifecycle. The paper makes three contributions: a taxonomy of human‑level barriers to generative AI adoption, a stage‑specific risk and responsibility map, and a practical adoption‑readiness checklist for architectural firms. The paper argues that responsible AI adoption in architecture is a human and organisational challenge: AI can support professional work only when embedded within transparent, stage‑gated, and accountable systems of judgement.
Silvia Albano
Open Access
Article
Conference Proceedings