Traditional HVAC designs often struggle to respond promptly and accurately to dynamic changes in complex environments like hospital usage. This paper introduces a novel framework that integrates Building Information Modeling (BIM), digital twin technology, and practical medical processes to transform HVAC design for hospital construction. The framework ensured a smarter (with a reduction of 90% in calculation time and an improvement of 38.20–53.24% in respondence speed) and cleaner environment after identifying and calculating the rational layout of functional areas and optimizing intersecting flow lines. A key innovation of this research was the application of Support Vector Machine (SVM) and deep learning algorithm (Long Short-Term Memory) networks for real-time pedestrian traffic prediction. The implementation was validated through multiple simulations and applications including horizontal and vertical traffic flow and negative pressure analyses for three distinct departments. The findings underline the potential of BIM and digital twins to optimize HVAC systems and hospital design, providing adaptive, data-driven solutions for both routine operations and emergency scenarios. This framework offers a scalable approach for modernizing healthcare infrastructure, ensuring resilience and efficiency in diverse operational contexts.
Because concrete strengths and quality are affected by various factors, multivariate regression models are often used to analyze the differences between predicted and target outputs. However, the variableness of a predicted output and how individual input parameters affect prediction reliabilities are still uncertain in practical applications, especially for the prediction of compressive strengths of concrete. This study aims to develop multivariate models for predicting concrete strengths and providing the variance analysis of prediction results by comparisons with experiment outcomes. First, this paper provides an in-depth examination of established variance analysis methods in the context of commonly used multivariate regression models. Then, based on Gaussian process regression, this study melds principal component analysis (PCA), linear discriminant analysis (LDA), and multivariate analysis of variance (MANOVA) to assess the variability in concrete strength prediction using different curing methods. This innovative approach proves effective in evaluating the precision of the correlation and regression models (R-squared values ≥ 0.9049). The comparison between prediction results and experiment outcomes shows that retaining heat in cylinders can make them become too hot and overestimate in-place concrete strength. This study improves the methodologies of regression modeling for variance analysis and improves the reliability of concrete strength prediction. Additionally, the outcomes of this research can help save a substantial amount of financial resources and time that are required to obtain experimental data on the strengths of concrete components.