Architectural heritage interventions often preserve visual form while leaving acoustic memory and everyday sound practices outside the design brief. This article positions soundscape as an architectural material for heritage media architecture and tests it through Sanggar Kungfu Kapasan, a historic Chinese-diaspora kampung in Surabaya, Indonesia. The research combined contextual and soundmark mapping, Pepper’s Ghost prototyping, architectural translation of a semi-transparent virtual layer, and comparative evaluation using 2D visualization and immersive VR. After deduplication, 37 participants evaluated the 2D material, 31 evaluated VR, and 24 completed both modes for within-subject analysis. VR significantly improved perceived physical quality (Δ = +0.46, p = 0.0007, dz = 0.80), communication quality (Δ = +0.42, p = 0.0218, dz = 0.50), and overall evaluation (Δ = +0.20, p = 0.0285, dz = 0.48). Sound-specific VR ratings were positive for place-meaning support (M = 5.87) and scene formation (M = 5.65), and the soundscape design index correlated with communication quality (r = 0.47, p = 0.007). The findings show that soundscape strengthens narrative legibility and architectural fit when deliberately coordinated with visual layering, scene sequencing, and cultural context. The study contributes a soundscape-informed, feng shui-readable workflow for pre-installation evaluation of multisensory heritage interventions. Because the respondent pool was predominantly composed of architecture students, the results are interpreted as a preliminary design-user evaluation rather than community validation.
Bioreceptive building envelopes offer a potential pathway for integrating biological colonization into architectural surfaces. This article proposes a geometric design framework for bioreceptive façade components in which the surface itself is shaped to increase the exposed area available to the environment, and asks which admissible regular Euclidean tessellation maximizes that area. Triangular, square, and hexagonal tessellations are compared under a common circumscribed radius R and a common absolute indentation depth hj, counting only the inclined faces generated by the indentation. A closed-form expression is derived for the exposed-surface density σn=hj2+rn2/rn, where rn is the apothem of the regular cell, and the triangular tessellation is shown to maximize it uniquely for every hj>0; when hj=0 the three configurations coincide. Because each inclined face has constant slope magnitude hj/rn, the area Jacobian is constant, so clipping the indented surface with any measurable footprint Ω of finite positive area gives Sn(Ω)=σn|Ω| exactly, with no boundary-error term. For the representative case hj/R=45/34, the hexagonal density is 0.6454 times the triangular one, equivalent to a 54.93% triangular advantage specific to that ratio. An independently constructed CAD model reproduces the closed-form panel areas at both reference footprints to within 10−3% and preserves the same ordering. Exposed area is a geometric descriptor of the available surface–environment interface and a candidate design parameter, not evidence of colonization, water behavior, or durability; no material, fabrication, or biological validation is claimed.
Recent scholarship on twentieth century West African architecture examines the intersections of decolonisation, nation formation, and development aid. While this shift highlights a transnational body of architects, the role of indigenous actors and building professionals remain under-researched. Using the University of Nigeria, Nsukka (UNN) as a case study, this paper analyses how architecture reflects Nigeria’s transition from a colonial entity to an independent state. It employs a transnational and multi-institutional archival research approach. Government, academic and architectural archives in Nigeria, the UK and the USA were examined. Non-institutional sources like newspapers and biographical accounts of students and building professionals were also analysed. The research reveals that the Eastern Nigerian political class envisioned UNN’s architecture as a nationalist and utilitarian alternative to the elitist and expensive colonial University College Ibadan (1948). The university was designed in three stages by the British firm James Cubitt & Partners; Nigerian contractors like Eastern General Contractors; and American architects through technical assistance. The stages illustrate how the architecture of universities and state projects in early independence Nigeria were impacted by decolonisation, nation-building and development aid. Furthermore, the research introduces local figures—Nigerian political elites and contractors—who are often overlooked in commonly used architectural records.
In the hyper-arid climate of Riyadh, Saudi Arabia, the building envelope is a critical determinant of energy demand and occupant comfort. This paper reports an experiential-learning experiment in which undergraduate architectural-engineering students applied building performance simulation (BPS) as a generative design instrument rather than a post-design audit tool to their own real capstone building, a 6581 m2 mixed-use development. Using Sefaira (EnergyPlus/Radiance engines), they iteratively diagnosed, tested, and refined envelope decisions against the prescriptive thresholds of the Saudi Building Code (SBC 601). A baseline analysis revealed a high Energy Use Intensity (EUI) of 139 kWh/m2·yr, driven primarily by solar heat gains and an “overlit” floor plate that exceeded Annual Sunlight Exposure (ASE) thresholds. Students then implemented passive interventions—improved glazing U-value (0.50 W/m2·K), reduced Solar Heat Gain Coefficient (SHGC 0.20), and external shading fins. These produced a 6.95% EUI reduction (139→130 kWh/m2·yr) and a 17.24% fall in cooling energy. The energy outcomes are consistent with established findings for hot-arid envelopes and are therefore treated here not as the novelty but as the technical evidence the students generated. Daylighting analysis confirmed improved distribution and reduced glare risk, although ASE remained above the LEED v4 threshold. The contribution is pedagogical: the study documents a replicable framework through which a design studio develops students’ technical competence in performance-driven envelope design, evidenced by their progression from uninformed parameter selection to code-referenced design reasoning and by the difficulties and trade-offs they encountered.
Mirrors were crucial elements in defining the modern concept of the architectural interior in Europe during the seventeenth century. In the first section of this article we show how mirrors supported the development of Enlightenment theory of the psycho-social subject. This theme eventually reached its apex with Jacques Lacan’s essay ‘The Mirror Stage’ and came to define the prevailing critical approach. The mirror in premodern Islam, however, is less concerned with the psycho-social subject and its interior architecture. In the second section, we consider how mirrors such as those employed in ayeneh-kari tiling are understood to situate cosmically and act poetically. Dissolving, fragmenting, and scattering effects tend to have greater importance than questions of self-image. Having established these contrasting critical positions, we then consider two more current permutations of the mirror: the advent of the mirror-glass façade in the twentieth century, and the use of mirrors in contemporary installation art. In the third and fourth sections, we explore the way mirrors can decentre the individual as a source of meaning and suggest or evoke new macrocosmic identities. Critical emphasis on the psychological subject’s interior architecture falls short of recognising the many ways the physical design and construction of spaces might contribute to a wider range of spatial experiences and practices. In our concluding reflections, we suggest (without foreclosing other meanings or uses of the mirror as threshold) that practical and critical uses of the mirror have implications for spatial politics.
Reference building models can serve as a common baseline for research investigations and evaluations of design choices. Despite lighting being one of the largest single users of electricity in commercial buildings, lighting systems in reference buildings are commonly modeled as maximum building-type or space-type power densities defined in building energy codes. Further, energy use is typically estimated by modulating the lighting power over the course of a day via simple occupancy schedules that may not accurately portray human behavior or the performance of occupancy-based lighting controls. While this approach is suitable for some use cases, it is not adequate for exploring the impact of luminaire selection, space-specific control strategies, and occupant behavior. This paper presents the development of a high-fidelity reference model of a medium office building that includes interior architecture, an occupant distribution model, and a detailed lighting design intended to support more realistic evaluations of lighting control strategies and approaches to modeling occupant behavior. The model includes 13 market-representative LED luminaires, meets occupant lighting needs by complying with applicable recommended practices defined by the Illuminating Engineering Society (IES), and meets energy code power density and control strategy requirements in ANSI/ASHRAE/IES 90.1-2019. The luminaire-level connected load (26,037 W) of the lighting layout is lower than what would be estimated by simple building-type (34,304 W) and space-type (31,200 W) power density methods. The model includes 12 space types and 107 rooms with workstations for 268 occupants. The interior architecture varies on each of the three floors to introduce room and space-type diversity that further exposes the impact of design choices and occupant behavior. The model has already been used as a baseline for research on circadian lighting design strategies, lighting–HVAC data integration, and whole-building life-cycle assessments—demonstrating its utility as a common reference for a range of lighting research.
In the modern era, mass-housing production has generally prioritized efficiency and standardization at the expense of architectural diversity and contextual sensitivity. This study proposes a computational decision-support model for the early design phase of mass housing that responds to site-specific conditions while maintaining the efficiency of industrialized housing production through the integration of parametric modeling and genetic algorithms. Using the Zeytinburnu-Kazlıçeşme district of Istanbul as a case study, a parametric model integrating the multi-objective genetic algorithm engine Wallacei X was developed in Rhino–Grasshopper. The model is structured around fundamental design variables, contextual rules, and planning constraints to generate feasible and diverse massing configurations. Four fitness objectives were evaluated simultaneously: total construction area, building footprint area, open (garden) area, and total terrace area. In a single exploratory run, 200 massing alternatives were generated, from which 32 solutions satisfying the adopted FAR/BCR screening criteria, 26 Pareto-optimal solutions, and five selected alternatives at the intersection of both sets were identified. These solutions were evaluated through a decision-support workflow based on objective performance, Pareto optimization, and the adopted local density-screening criteria. The findings indicate that genetic algorithm-based generative design can support architectural diversity, contextual sensitivity, and informed decision-making in residential housing design.
Public buildings play a critical role in national decarbonization strategies and green energy transitions due to their high energy consumption densities, large occupant capacities, and potential to drive public awareness. Optimizing energy efficiency in these structures not only alleviates the financial burden on public budgets but also serves as a benchmark for sustainable urban development. To investigate the energy-saving potentials, thermal comfort dynamics, and financial feasibilities within this sector, this study selects two university buildings from two different countries with distinct climatic, structural, and operational profiles as comparative case studies: university buildings in Türkiye (TR) and Italy (IT), respectively. A total of seven tailored retrofitting scenarios were developed based on country-specific legislative frameworks and subsidy mechanisms: the Minimum Environmental Criteria (CAM) and Conto Termico 3.0 for Italy, and the Public Buildings Energy Efficiency Project (KABEV), Energy Performance Contracting (EPC), and Nearly Zero Energy Buildings (NSEB) mandates for Türkiye. The scenarios evaluate deep building envelope insulation, high-efficiency window replacements, lighting automation (LED with daylighting controls), mechanical ventilation with heat recovery units (HRV), air-to-water heat pump integrations, and rooftop photovoltaic (PV) installations using calibrated DesignBuilder simulation models. The quantitative results demonstrate that country-specific green building incentives drastically enhance both the energy performance and financial viability of deep retrofits. For the Turkish case study, the comprehensive near-zero energy building (nZEB) retrofitting package (TR-4) successfully reduced annual primary energy consumption by 75% (from 284 to 71 kWh/m2·year) and cut annual thermal comfort discomfort hours by 72% (from 3147 to 880 h), yielding a Subsidized Net Present Value (NPV) of +310,600 €. Similarly, for the Italian case study, the holistic retrofit combined with rooftop photovoltaic integration (IT-4) achieved an 80% energy reduction (dropping from 128 to 25.6 kWh/m2·year), minimized annual discomfort hours to 45 h, and generated a Subsidized NPV of +425,500 €. Furthermore, national incentive mechanisms shortened simple payback periods by more than half, establishing that targeted public policy is vital to accelerate public sector building decarbonization while ensuring long-term fiscal profitability.
The use of photovoltaic technologies in building envelopes has attracted more and more interest as a promising solution to building sustainability by considering energy efficiency, economic feasibility, and environmental impact issues altogether. This paper will provide an overall comparative analysis on Building-Integrated Photovoltaic (BIPV) systems versus traditional building envelope materials based on a multi-dimensional analysis model. It is demonstrated in the analysis of energy performance that BIPV systems contribute greatly to building energy performance by capturing on-site renewable energy and reducing cooling loads through shading and regulated solar heat gain, in contrast to traditional materials, which only provide passive thermal insulation and energy conservation. Life cycle-based economic analysis shows that despite the higher initial costs of BIPV systems, thematic savings in long-run operations and lower requirements of electricity mean BIPV systems have better economic performance during the life of building services as compared to traditional envelopes, which offer lower upfront costs but have greater cumulative energy costs associated with their application. Environmental performance scorecard BIPV systems are shown to lead to significant reductions in greenhouse gas emissions through the replacement of grid-based electricity, and even though greater energy use is involved in the manufacturing and installation of BIPV systems, the operational carbon savings outweigh these effects in a relatively short time, leading to a net-positive lifecycle environmental impact. The overall multi-criteria comparison established an integrated viewpoint to demonstrate that BIPV systems generally outperform traditional envelope materials in energy, economical, and environmental aspects. The results underline the significance of lifecycle and context-related design approaches to building envelope solution choices in assisting the achievement of energy efficiency, economic stability, and environmental sustainability in the long term.
Transforming concepts into architectural designs is challenging, as it requires clear ideas and the ability to visualise them. AI-powered text-to-image tools help designers quickly convert concepts into visual representations, enabling faster exploration of design alternatives. This study introduces a proposed ten-step numerical procedure for assessing the richness of textual prompts submitted to text-to-image generative AI tools within an architectural design studio. Twenty-three architecture students were enrolled in the design studio; twenty-two submitted analyzable text prompts as part of a design assignment requiring AI-assisted conceptual visualisation. Each prompt was scored across seven weighted dimensions (subject specificity, style and medium, composition and framing, lighting and atmosphere, colour and palette, quality modifiers, and negative clauses) to produce a composite Prompt Richness Index (R, scale 0–100). Corresponding AI-generated images were independently scored using a parallel Output Richness Index (O, scale 0–100). Pearson’s r between per-student average R and O yielded r = 0.940 (p < 0.001, 95% confidence interval [0.86, 0.98]), confirming a nearly perfect positive linear relationship. Rich-tier prompts were produced by two students and yielded the most architecturally coherent and visually distinctive outputs. Two students produced Sparse-tier prompts (average R < 30) and consistently received undifferentiated, generically rendered outputs. Two further students scored just above the Sparse threshold but showed similarly limited output differentiation. Class-wide deficits were identified in lighting/atmosphere description and negative clause usage. Eight pedagogical recommendations are derived from the findings to guide prompt learning instruction in AI-integrated design studios.
Urban public spaces matter for young people, yet how youth visually engage with the spatial elements of Indian cities remains largely unstudied. This exploratory study uses screen-based eye tracking to examine how 43 design-discipline students (aged 18–29) allocate visual attention across urban public space scenes in Jaipur, India. Thirty photographic stimuli sampling five Lynch-derived spatial elements—edge, landmark, path, plaza, and transit node—across six public spaces were each analyzed through four semantic areas of interest (built form, human and vehicular activity, natural elements, and circulation), using fixation count, total fixation duration, time to first fixation, and visit count. Attention was allocated unevenly: built form and human activity dominated the youth gaze, while natural elements consistently drew less focal attention—interpreted as restorative background rather than low importance. Landmarks anchored attention most strongly and transit nodes least. Notably, socially active and visually complex elements did not capture the gaze earliest but held it longest, suggesting that what sustains youth attention is dissociable from what initially attracts it. Inferential tests are treated as exploratory given the repeated-measures design. As the first AOI-based account of youth visual attention in Indian heritage public space, this study offers a transferable protocol and preliminary, exploratory directions for youth-responsive design—including visual anchoring at neglected transit nodes and the use of greenery for ambient comfort rather than focal emphasis.
Early-stage architectural design is characterized by high decision uncertainty, ill-defined requirements, and limited opportunities to elicit reliable user feedback, despite the disproportionate impact of early decisions on downstream outcomes. While recent AI-enabled design tools increasingly support generative exploration and performance-driven optimization, they largely rely on static models trained on aggregated data, thereby producing “average-user” responses that fail to capture pronounced inter-individual variation in architectural preferences. This conceptual framework paper, developed through critical narrative synthesis of interdisciplinary literature, argues that meta-learning—i.e., learning-to-learn—offers a conceptually appropriate mechanism to address this personalization gap by enabling rapid adaptation to a new user’s preference structure from limited interactions, while leveraging transferable knowledge learned across many users. Drawing on a structured, PRISMA-informed literature identification process complemented by purposive theoretical sampling across user-centered design traditions in architecture, computational preference-elicitation methods, and contemporary meta-learning research, the paper develops a theoretically grounded conceptual framework for adaptive user preference modeling in early-stage design workflows. The framework articulates four interdependent constructs—(1) Preference Representation, (2) Adaptation Engine, (3) Design Space Navigator, and (4) Feedback Loop—describing how iterative preference refinement can co-evolve with design-space exploration without displacing architectural agency. An illustrative application scenario is also presented to demonstrate the operational logic of the framework in a realistic early-stage design context. The paper further formulates a set of testable propositions and evaluation pathways to guide future empirical investigation, alongside a discussion of implications for practice and education and key ethical considerations (bias, privacy, and digital equity). The proposed framework provides conceptual scaffolding for developing AI-augmented, user-responsive design systems that are aligned with the epistemic conditions of early-stage architectural design.
Design studio education requires sustained attention and prolonged occupancy of a shared workspace, making environmental opportunities for brief recovery potentially relevant to students’ well-being. This exploratory study used affordance theory as an interpretive lens to examine the environmental modifications students proposed from their assigned desk positions and the extent to which sketch content was associated with academic year, studio location, and desk-level window view access. The dataset comprised 71 structured sketches, geometric view metrics for 85 workstations that were linked to the 71 sketch participants for inferential analyses, and a nonmatched lighting survey administered to the same cohorts one year later (n = 57). Sketches were coded into 17 modification categories. Water and Collaborative/Social Space were retained descriptively but excluded from inferential interpretation because of quasi-complete separation. Fifteen ordinary logistic regression models were evaluated with Benjamini–Hochberg false-discovery-rate correction, together with a complementary specification omitting studio location. Plants (73.2%), natural shapes/patterns (52.1%), and electric light quality (52.1%) were the most frequent modifications. In the primary models, Technology (q = 0.033) and Plants (q = 0.047) retained FDR-supported omnibus fit; only the academic-year coefficient for Technology retained FDR support (OR = 0.17, 95% CI [0.06, 0.50], q = 0.021). The study identifies environmental preferences and hypotheses for future intervention in restorative learning environments research.
This essay complicates the distinction between of “North” and “South” as spaces of knowledge production—which usually entails the privileging of the South as an emancipatory space—by directing attention to Southern actors’ imbrication with forms of colonialism. It calls for situating both Northern and Southern actors within networks of global knowledge exchanges by critically examining their positionality vis-à-vis colonial relations domestically and internationally. More specifically, it asks how interstitial colonial positions gave rise to new centers of knowledge production and expertise in the postcolonial world. It considers these positions not as static identities but as strategic, adaptative, dynamic, relational, and contingent upon geopolitically determined itineraries of global exchange.
Imperial and colonial history has mostly been founded on the tradition of writing biographies of great men, and more rarely, great women. These lean inherently towards the aggrandizement or hagiography of individuals who, particularly in the early decades of life, may deserve no such attention. Yet for postcolonial and decolonial progression, the unattractive necessity of revising the lives of such influential individuals remains. We cannot now change or eliminate the archive’s overwhelming propensity to amplify (and thereby value and embolden) elite voices and experiences, but we can turn down the volume by placing key episodes firmly within an individual’s relevant or entire life experience, by reading the other less explicit motives for travel or collecting and by focusing on silent absences rather than noisy presences. Sara E. Johnson’s 2023 book ‘Encyclopédie Noire: The making of Moreau de Saint-Méry’s intellectual world’, is presented as a ‘communal biography’ of one such great imperialist, by intentionally, and sometimes creatively, adding in the actors, voices and narratives missing from the sources and archives of European colonial history. In trying to methodologically undermine how imperial biography has traditionally sidestepped complicity or guilt, Johnson attempted to paint a more complete picture of the societies, enslaved or not, in which such elite men operated. Landscape history and architectural history play important roles in such essential revisionism because they can add provocatively spatial dimensions to colonial lives and experiences. As people are profoundly affected by the environment(s) in which they operate, particularly at key tipping points in their lives, spatial and environmental analysis can undermine traditional biography by focusing on where key life decisions were made, leading to a broader cognizance of why they were made. An individual’s spatial position, whether resident or absentee, at home or abroad, with family or without, reveals nuances in mentality that traditional analysis can miss. Taking the life and letters of Pierce Butler, Irishman, US Senator, signatory of the US constitution and the owner of a substantial estate of land and enslaved people in Georgia, as a case study, this article argues for the creative reimagining of biography as a fundamental postcolonial corrective to colonial and imperial history. Butler’s transnational identity, sometimes Irish, sometimes not, collapses any neat mapping of a grand national narrative onto one man’s life. The extraordinary level of detail provided by the correspondence also demands a more conventional or traditional history, one focused on individual identity, motive and relationships, that cannot be effectively discounted because of a landscape or architectural focus.
Al-Wehdat open market, originating in a mid-20th-century Palestinian refugee camp in Amman, Jordan, has evolved into a vital urban common and a paradigmatic case of Everyday Architecture of Compromise. It demonstrates significant economic, social, political, and cultural dynamism, leveraging the relational and solidary capacities of a disenfranchised migrant community to build resilience and assert their Right to the (negated) City. This paper examines how the market’s mode of production responds to intersecting geopolitical, economic, and democratic crises. Employing a constructivist, conjunctural urbanism approach and scene-based analysis, we situate Al-Wehdat market within discourses on urban commons and relationality. Our theoretical framework draws on Hannah Arendt, Gilbert Simondon, and Ash Amin to reconceptualise the Right to the City as the Right to the Open Urban Market. We foreground customary territorial communing as a counterforce to corporative commodification, as essential in the struggle for urban justice, differential individuation, and immanent re-enchantment. Findings, presented through vivid market scenes, show how everyday interactions, creative material arrangements, and rich collaborative imagination sustain these commons. Thematic analysis identifies patterns in community relations, materiality, infrastructure, and acts of repair that sustain the regenerative capacity of key everyday relational, political, techno-material and convivial practices. We conclude by advocating for community empowerment policies that recognise the centrality of everyday relational individuation in shaping inclusive cities amidst polycrisis in the Global South.
Generative AI has reached the early, ideational phase of architectural design, the stage most tightly bound to conceptual creativity, yet its effect on student creativity remains unevenly investigated. This study examines the transfer of creativity from handmade concept to AI refinement. In a first-year studio, 45 students developed a bus-stop design and then reworked it using AI visualisation tools. Pre-AI and post-AI designs were rated by experts using the same nine-dimensional Consensual Assessment Technique (CAT) rubric; the prompt log was text-mined; and the two streams were linked for each student and analysed. Results suggest a modest rise in total creativity (3.38 to 3.71; Wilcoxon p = 0.022, dz = 0.38), yet concentrated in appropriateness; functional adequacy (+0.80), structural feasibility (+0.78), and environmental response (+0.56) increased significantly, while novelty dimensions remained unaltered. The cohort suggested a reordering: weaker starters gained most and several strong starters declined. Although baseline input creativity dominated the prediction of output quality and prompt behaviour added no significant variance once it was controlled, gains were largest when students let AI transform their original concepts. Results indicate that in the context of this study, generative AI acts as a leveller and redirector of creativity, strengthening the buildability of weaker designs without raising originality, with direct implications for how studios deploy and teach the tool. As results are based on a single first-year cohort, institution, design brief, and an observational within-student design, the findings are limited to exploratory evidence of conditional creativity transfer rather than causal evidence.
The early design courses engage and hone students’ visual, spatial, and communicative skills so that first-year design students begin to understand composition, abstraction, hierarchy, development of process, and representation through experimental, process-driven exercises. Exhibitions have traditionally presented the students’ final work; however, virtual exhibitions allow one to push past the physical studio and present student work as a sustained pedagogical experience. A case study was presented of the development and curation of a speculative gallery-style virtual exhibition for process work by first-year students undertaking Basic Design and a Design Communication course. Rather than falling into the pitfall of functioning as a “digital stand-in for the gallery” approaches were considered where virtual curation becomes an educative space for being literate in the visual, mindful learning, and observer witnessing peer students enculturating themselves into identity. Using a practice-based reflective approach, to examine curatorial decisions (visual sequencing, categorisation, representation, and navigational design), exploring how exhibition design frames beginner work and communicates thinking and process rather than simply “polished” outcomes. It is argued that virtual exhibition, by allowing for prolonged engagement with works, scaling access, and encouraging a visual dialogue among peers, may extend the foundation of design learning. The study contributes to discourse on design pedagogy, digital curation, and the shifting educational place of exhibitions in foundation-level design education.
Indoor environmental quality (IEQ) strongly influences occupant well-being and teaching conditions in educational buildings. This study proposes the Predicted Probability of Dissatisfaction Index (PPDieq.prof), a probabilistic ordinal learning framework based on the Consistent Rank Logits (CORAL) architecture to estimate university professors’ dissatisfaction while preserving the ordinal structure of subjective perception. The framework integrates operative temperature, CO2 concentration, illuminance, and sound pressure level through the CORAL architecture. A dataset comprising 77 synchronized environmental and subjective observations collected during regular teaching activities was evaluated using a Nested Stratified Group Cross-Validation benchmark. The proposed framework achieved an Accuracy of 0.670±0.122, Balanced Accuracy of 0.715±0.164, Macro-F1 score of 0.618±0.166, and a Quadratic Weighted Cohen’s Kappa of 0.604±0.176. Benchmark comparisons with conventional statistical and machine learning models demonstrated competitive predictive performance while preserving ordinal consistency. The representative CORAL architecture selected during the benchmark was subsequently retrained using the complete dataset for model interpretability analyses. Predictor contribution analysis identified CO2 concentration as the most influential environmental variable (48.2%), followed by operative temperature (24.8%), sound pressure level (14.7%), and illuminance (12.4%). Complementary One-Factor-at-a-Time (OFAT) response analysis and exploratory latent-space visualization further enhanced the interpretation of environmental dissatisfaction, demonstrating the potential of the proposed framework as an interpretable virtual sensing approach for supporting IEQ assessment in educational buildings.
Restorative environments have been widely associated with stress reduction, psychological recovery, and improved well-being; however, evidence regarding cognitive performance remains methodologically fragmented, particularly across sensory modalities and neurophysiological assessment approaches. This systematic review examined the relationship between restorative environments and cognitive performance, with specific attention to sensory modality, cognitive domain, and the neuroscientific and physiological methods used to assess these effects. The review was conducted in accordance with PRISMA 2020. Peer-reviewed studies published in English from 2000 onward were identified through PubMed, Web of Science, Scopus, ScienceDirect, and PsycINFO, with the final search conducted on 31 March 2026. Eligible studies involved healthy human participants exposed to restorative environmental conditions in built, natural, or simulated settings and included at least one objective measure of cognitive performance together with at least one central nervous system or autonomic nervous system measure. Due to substantial methodological heterogeneity, findings were synthesized narratively. Of the 517 records identified, 26 studies met the inclusion criteria: visual (n = 13), auditory (n = 1), thermal (n = 8), olfactory (n = 1), and multisensory (n = 3). Across the 26 included studies, study-level effect directions were predominantly mixed, comprising 13 mixed, 6 positive, 4 neutral, and 3 negative classifications. Visual studies showed the clearest recurring favorable pattern, particularly for attention-related performance and selected working-memory outcomes. Thermal effects were condition-dependent, whereas evidence for auditory, olfactory, and multisensory modalities remained limited and mixed. Overall, the strength and consistency of the findings varied substantially according to sensory modality, exposure design, and assessment method. The evidence base was uneven across sensory modalities and showed considerable heterogeneity in intervention design, exposure characteristics, cognitive tasks, and neurophysiological outcomes. These findings provide a structured, modality-specific map of how restorative environments have been linked with cognitive performance while highlighting the need for more methodologically consistent research, particularly on underexplored non-visual, tactile, and multisensory pathways.
