Estimation of Occupancy Using IoT Sensors and a Carbon Dioxide-Based Machine Learning Model with Ventilation System and Differential Pressure Data.

Infectious diseases such as the COVID-19 pandemic have necessitated preventive measures against the spread of indoor infections. There has been increasing interest in indoor air quality (IAQ) management. Air quality can be managed simply by alleviating the source of infection or pollution, but the person within a space can be the source of infection or pollution, thus necessitating an estimation of the exact number of people occupying the space. Generally, management plans for mitigating the spread of infections and maintaining the IAQ, such as ventilation, are based on the number of people occupying the space. In this study, carbon dioxide (CO2)-based machine learning was used to estimate the number of people occupying a space. For machine learning, the CO2 concentration, ventilation system operation status, and indoor-outdoor and indoor-corridor differential pressure data were used. In the random forest (RF) and artificial neural network (ANN) models, where the CO2 concentration and ventilation system operation modes were input, the accuracy was highest at 0.9102 and 0.9180, respectively. When the CO2 concentration and differential pressure data were included, the accuracy was lowest at 0.8916 and 0.8936, respectively. Future differential pressure data will be associated with the change in the CO2 concentration to increase the accuracy of occupancy estimation.

Comparison of Random Forest and Gradient Boosting Machine Models for Predicting Demolition Waste Based on Small Datasets and Categorical Variables.

Construction and demolition waste (DW) generation information has been recognized as a tool for providing useful information for waste management. Recently, numerous researchers have actively utilized artificial intelligence technology to establish accurate waste generation information. This study investigated the development of machine learning predictive models that can achieve predictive performance on small datasets composed of categorical variables. To this end, the random forest (RF) and gradient boosting machine (GBM) algorithms were adopted. To develop the models, 690 building datasets were established using data preprocessing and standardization. Hyperparameter tuning was performed to develop the RF and GBM models. The model performances were evaluated using the leave-one-out cross-validation technique. The study demonstrated that, for small datasets comprising mainly categorical variables, the bagging technique (RF) predictions were more stable and accurate than those of the boosting technique (GBM). However, GBM models demonstrated excellent predictive performance in some DW predictive models. Furthermore, the RF and GBM predictive models demonstrated significantly differing performance across different types of DW. Certain RF and GBM models demonstrated relatively low predictive performance. However, the remaining predictive models all demonstrated excellent predictive performance at R2 values > 0.6, and R values > 0.8. Such differences are mainly because of the characteristics of features applied to model development; we expect the application of additional features to improve the performance of the predictive models. The 11 DW predictive models developed in this study will be useful for establishing detailed DW management strategies.

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets.

Recently, artificial intelligence (AI) technologies have been employed to predict construction and demolition (C&D) waste generation. However, most studies have used machine learning models with continuous data input variables, applying algorithms, such as artificial neural networks, adaptive neuro-fuzzy inference systems, support vector machines, linear regression analysis, decision trees, and genetic algorithms. Therefore, machine learning algorithms may not perform as well when applied to categorical data. This article uses machine learning algorithms to predict C&D waste generation from a dataset, as a way to improve the accuracy of waste management in C&D facilities. These datasets include categorical (e.g., region, building structure, building use, wall material, and roofing material), and continuous data (particularly, gloss floor area), and a random forest (RF) algorithm was used. Results indicate that RF is an adequate machine learning algorithm for a small dataset consisting of categorical data, and even with a small dataset, an adequate prediction model can be developed. Despite the small dataset, the predictive performance according to the demolition waste (DW) type was R (Pearson's correlation coefficient) = 0.691-0.871, R2 (coefficient of determination) = 0.554-0.800, showing stable prediction performance. High prediction performance was observed using three (for mortar), five (for other DW types), or six (for concrete) input variables. This study is significant because the proposed RF model can predict DW generation using a small amount of data. Additionally, it demonstrates the possibility of applying AI to multi-purpose DW management.

The Effects of Data Collection Method and Monitoring of Workers' Behavior on the Generation of Demolition Waste.

The roles of both the data collection method (including proper classification) and the behavior of workers on the generation of demolition waste (DW) are important. By analyzing the effect of the data collection method used to estimate DW, and by investigating how workers' behavior can affect the total amount of DW generated during an actual demolition process, it was possible to identify strategies that could improve the prediction of DW. Therefore, this study surveyed demolition waste generation rates (DWGRs) for different types of building by conducting on-site surveys immediately before demolition in order to collect adequate and reliable data. In addition, the effects of DW management strategies and of monitoring the behavior of workers on the actual generation of DW were analyzed. The results showed that when monitoring was implemented, the estimates of DW obtained from the DWGRs that were surveyed immediately before demolition and the actual quantities of DW reported by the demolition contractors had an error rate of 0.63% when the results were compared. Therefore, this study has shown that the proper data collection method (i.e., data were collected immediately before demolition) applied in this paper and monitoring on the demolition site have a significant impact on waste generation.