Particulate matter (PM) of sizes less than 10 µm ($P{M}_{10}$) and 2.5 µm ($P{M}_{2.5}$) found in the environment is a major health concern. As PM is more prevalent in an enclosed environment, such as a subway station, this can have a negative impact on the health of commuters and staff. Therefore, it is essential to continuously monitor PM on underground subway platforms and control it using a subway ventilation control system. In order to operate the ventilation system in a predictive way, a credible prediction model for indoor air quality (IAQ) is proposed. While the existing deterministic methods require extensive calculations and domain knowledge, deep learning-based approaches showed good performance in recent studies. In this study, we develop an effective hybrid deep learning framework to forecast future $P{M}_{10}$ and $P{M}_{2.5}$ on a subway platform using past air quality data. This hybrid framework is an integration of several deep learning frameworks, namely, convolution neural network (CNN), long short-term memory (LSTM), and deep neural network (DNN), and is called hybrid CNN-LSTM-DNN; it has the characteristics to capture temporal patterns and informative characteristics from the indoor and outdoor air quality parameters compared with the standalone deep learning models. The effectiveness of the proposed $P{M}_{10}$ and $P{M}_{2.5}$ forecasting framework is demonstrated using comparisons with the different existing deep learning models.

The emergence of COVID-19 and the pandemic have changed and devastated every aspect of our lives. Before effective vaccines are widely used, it is important to predict the epidemic patterns of COVID-19. As SARS-CoV-2 is transferred primarily by droplets of infected people, the incorporation of human mobility is crucial in epidemic dynamics models. This study expands the susceptible–exposed–infected–recovered compartment model by considering human mobility among a number of regions. Although the expanded meta-population epidemic model exhibits better performance than general compartment models, it requires a more accurate estimation of the extended modeling parameters. To estimate the parameters of these epidemic models, the meta-population model is incorporated with deep learning models. The combined deep learning model generates more accurate modeling parameters, which are used for epidemic meta-population modeling. In order to demonstrate the effectiveness of the proposed hybrid deep learning framework, COVID-19 data in South Korea were tested, and the forecast of the epidemic patterns was compared with other estimation methods.

The purpose of this study is to introduce a new and efficient virtual model-based ergonomic simulation framework utilizing recent anthropometric data for a digitalized main control room in an advanced nuclear power plant. The system interface of the main control room has been undergoing digitalization via various information and control consoles. Console operators often face human–computer interactive problems due to inappropriate console design. Computational models with a process of visual perception and variables of anthropometric data are developed for designing and evaluating operator consoles with the requirements of human factor guidelines. From the 3D computational model and simulation application, console dimensions and a designing test module, which would be used for designing suitable consoles with safety concerns in a nuclear plant, are proposed. To efficiently carry out console design and evaluation feedback, an intelligent design review system comprising a virtual modeling and simulation framework is developed. The proposed automated and virtual design review system provides console design efficiency and evaluation effectiveness. This study may influence methods of employing suitable design concepts with various anthropometric data in many areas with safety concerns and may show a feasible solution to designing and evaluating the main control room.

International construction projects normally involve high levels of risk. To reduce such risk, contractors typically include a reserve to mitigate cost overruns and schedule delays. This reserve comprises two categories: (1) a contingency reserve covering potentially required changes, and (2) a management reserve (MR) covering unplanned changes. Since estimating an MR is difficult because the inherent risks are unpredictable, the traditional percentage method is still used for this purpose. To address this shortcoming, this study proposes an MR estimation method based on the cost and schedule performance ratios of international construction projects. K-nearest neighbor (k-NN) is applied to retrieve similar projects and a genetic algorithm is adopted to optimize the retrieved cases. Finally, case studies are conducted to validate the estimated ratios and test the applicability of the proposed MR estimation method. The case study results show that the proposed method can infer the cost and schedule performance ratios within a 5% error rate. As a result, it can estimate the MR more accurately than the traditional percentage method.