Architectural façades significantly influence human health as primary interfaces between individuals and urban visual environments, however neurophysiological responses to architectural features across historical periods and at varied viewing distances remains an area yet to be examined. This study identifies visual stressors in Seoul’s building façades across five historical epochs and examines how design characteristics influence visual stress at different viewing distances. This study analyzed 77 façade samples using Visual Stress Analysis (ViStA) across five architectural periods: Late Joseon Dynasty, Japanese Colonial, Post-Korean War Reconstruction, High-Density Urban Expansion, and Digital-Transitional Era. Standardized photographs at three distances (10–15, 20–30, 40–60 m) were assessed using Fourier-based computational methods. In doing so, this research identifies specific design characteristics within each epoch that correlate with distinct patterns that may be visually stressful. Traditional Korean architecture demonstrates a spatial profile associated with organic surface variations and traditional screening systems, while Colonial period façades exhibit a spatial profile linked to systematic fenestration and regularized compositions. Post-war reconstruction architecture shows spatial features correlated with repetition and standardized building elements, whereas the Post-Industrial Transition period (1980–2000) displays the highest peak visual stress levels—associated with contrasting material juxtapositions and complex geometric arrangements. Contemporary architecture reveals visual stress characteristics linked to advanced glazing systems, perforated metal cladding, and computationally derived patterns; nonetheless, these systems afford fine-grained control over spatial frequency and contrast that can reduce predicted stress despite their complexity. The study integrates image-based computational analysis with architectural feature identification to offer insights into how specific design elements, rather than historical periods per se, influence neurophysiological responses in urban visual environments.
Fires in industrial complexes cause property damage and casualties, but the spatial conditions under which fires result in casualties are rarely assessed. This study proposes a two-stage framework that combines expert-based Analytic Hierarchy Process (AHP)–geographic information system (GIS) assessment with machine-learning feature-importance analysis of observed fires. Seven spatial indicators—four vulnerability indicators (building density, aged-building share, fire-engine access, and hazardous-facility proximity) and three reverse-coded mitigation indicators (fire-station response time, firefighting water-supply coverage, and evacuation-facility accessibility)—were defined with largely common scoring rules. In Stage 1, weights from an AHP survey of 62 experts were applied in GIS to map fire-casualty vulnerability on a 250 m grid in the Myeongji Noksan National Industrial Complex, Busan, Republic of Korea. In Stage 2, scores for the same indicators were assigned to 5417 factory fires recorded in Busan’s 41 industrial complexes during 2019–2023 (32.9% with casualties); four classifiers were trained to predict casualty occurrence, and Shapley additive explanations (SHAP) were computed for XGBoost, which achieved the highest recall (0.621). The map identified a localized high-vulnerability zone in the south-central part of the complex, where hazardous-facility proximity was concentrated, although recorded casualty fires were not clearly concentrated in these cells. SHAP ranked aged-building share and building density highest, whereas experts emphasized fire-engine access and response time. Comparing the two perspectives shows where expert emphasis and data-driven importance diverge and offers an exploratory basis for spatial prioritization and for re-examining indicator weights.
The rising housing cost burden has emerged as a serious social issue that threatens residents' living stability and housing sustainability. High-rise, high-density apartment complexes have been regarded as a sustainable housing model consistent with the compact city strategy in terms of land-use and infrastructure efficiency and large-scale housing supply. However, whether such high-density housing types are equally efficient with respect to residents' energy expenditure has not been sufficiently examined. Notably, per-household energy expenditure comprises not only each household's in-unit energy use but also its apportioned share of common-area energy consumption (e.g., corridors, elevators, and common lighting). Accordingly, this study investigates how architectural planning characteristics, building life-cycle and operational characteristics, and neighborhood characteristics affect annual per-household energy expenditure in apartment complexes in Seoul. To this end, machine learning models and the SHAP interpretation technique were employed to identify key cost drivers and nonlinear thresholds. The results show that per-household energy expenditure is more strongly influenced by internal architectural, planning and operational characteristics than by locational factors. The nonlinear analysis revealed that (1) household energy costs surged sharply once building age exceeded 38 years; (2) economies of scale operated effectively up to 700 households, beyond which marginal cost reductions diminished; and (3) buildings below 10 stories incurred lower energy expenditure, whereas costs escalated above 30 stories. This study provides empirical evidence for the design and management of energy-efficient residential complexes and for policies to reduce household energy cost burdens.