Abstract Accurately characterizing existing building envelope materials is critical for retrofit prioritization, yet current nondestructive testing methods remain expensive, equipment-intensive, and inaccessible for routine use. This study explored whether low-cost WiFi signal attenuation could serve as a practical screening indicator for identifying building wall assemblies. A Raspberry Pi-based sensing system measured the received signal strength indicator at 2.4 and 5 GHz across 10 distinct wall assemblies (8 campus buildings plus a controlled test box and an open-air baseline). Because each assembly was characterized by a single 3-min measurement run at one location, assembly identity is fully confounded with measurement location, and the analysis is therefore reported as exploratory and descriptive. On that basis, the grouping of measurement cases was associated with 92.5%–94.9% of the observed signal variance across both frequency bands, and 84.4% of case pairs were separated beyond a conservative Bonferroni-corrected threshold. Every wall case was separated from the open-air baseline by at least 18.7 dB. These results do not establish a validated method for identifying wall assemblies; rather, they present an initial low-cost measurement and analysis framework and quantify the magnitudes of separation. By requiring only a sub-$100 Raspberry Pi and a smartphone, this approach lowers the barrier for nonspecialist building assessment, contributing to the emerging paradigm of citizen building science in which ordinary occupants participate meaningfully in retrofit decision-making.
Abstract The indoor environment quality (IEQ) of classrooms significantly impacts the teaching and learning performance of students and, in turn, can affect their academic achievement. Although national and international standards, such as NBC 2016, ISHRAE, and ASHRAE, specify the comfort limits of the IEQ parameters, studies have found that students were not satisfied with the indoor environment in spite of these specifications being met. This study empirically validates that the comfort limits for IEQ parameters in naturally ventilated school classrooms in a warm-humid climate are contextually different from the generic recommendations made in Standards, and aims to define these limits. Accordingly, fourteen classrooms in four schools in India were studied using qualitative and quantitative methods. In total, 45 spot instrument measurements along with 1,087 questionnaire survey responses were collected from April 2023 to January 2024 across summer and winter periods. It was found that, on average, students were not satisfied with the thermal environment, were satisfied with the visual environment, and were neutral toward the acoustic environment. However, they could not perceive the air quality. Upon correlation of the instrument data with the questionnaire survey responses, it was found that the derived comfort limits for this context were significantly different from the general recommendations for educational buildings in national and international standards, as was hypothesized. Therefore, the derived contextually appropriate IEQ comfort limits can support building engineers and architects in optimizing the design of school classrooms to improve IEQ and, in turn, enhance occupant comfort for effective learning.
Abstract Improving daylighting conditions typically conflicts with energy savings goals. Multiobjective optimization methods are often used to balance these competing design aspects, but their high computational time, especially for daylight simulations, limits their practical application. In this study, machine learning (ML) models were used to predict daylighting and energy performance in US classrooms among four climate zones. A leave-one-climate-out cross-validation scheme was used to test the generalizability to other climates. The parameters examined include classroom dimensions, window head height, orientation, window-to-wall ratio (WWR), and window width in single- and double-loaded school typologies. Results show that Random Forest repeatedly provided the highest prediction accuracy for daylighting performance, while Support Vector Machine and Artificial Neural Network performed best for energy performance. The analysis shows that for the single-loaded corridor typology, orientation, and WWR are the most influential factors across all optimization objectives. For the double-loaded corridor typology, classroom geometry, expressed by the width-to-depth ratio, is the dominant parameter affecting total energy use. Daylighting performance at the horizontal desk-plane is mainly affected by WWR, orientation, and width-to-depth ratio, whereas daylighting at the vertical eye-plane varies among climate zones. These findings demonstrate that ML models can reliably predict daylighting and energy outcomes and highlight the key design drivers for optimizing classroom performance across US climate zones. The results can support early design decision-making and reduce the computational burden of simulation-based optimization.
