Comparison of common machine learning algorithms trained with multi-zone models for identifying the location and strength of indoor pollutant sources

Abstract

The accurate identification of the characteristics of pollutant sources can effectively prevent the loss of human life and property damage caused by the sudden release of harmful chemicals in emergency situations. Machine learning algorithms, artificial neural network (ANN), support vector machine (SVM), k-nearest neighbour (KNN) and naive Bayesian (NB) classification can be used to identify the location of pollutant sources with limited sensor data inputs. In this study, the identification accuracy of the four above-mentioned machine learning algorithms was investigated and compared, considering the different sensor layouts, eigenvector inputs, meteorological parameters and number of samples. The results show that the collection of pollutant concentrations over an extended period of time could improve identification accuracy. Additional sensors were required to reach the same identification accuracy after the introduction of distributed meteorological parameters. Increasing the number of trained samples by a factor of five improved the identification accuracy of KNN by 22% and that of SVM by 1.7%; however, ANN and NB classification remained basically unchanged. When identifying the release mass of the pollutant source, multiple linear, ANN and SVM regression models were adopted. Results show that ANN performs best, whereas SVM provides the least optimal performance.

Application of polyhedral meshing strategy in indoor environment simulation: Model accuracy and computing time

“…From the available literature, many studies had been conducted to develop optimal CFD strategy for indoor environment simulations, 9 such as turbulence model choice, 10–12 airborne pollutant models, 13–15 parameters/variables of various indoor air conditioning systems and different meshing strategies. 16–19 The meshing strategy is how to determine mesh type and grid number/distribution in numerical simulations.…”

Prompt location of indoor instantaneous air contaminant source through multi-zone model-based probability method by utilizing airflow data from coarse-grid CFD model

“…By effectively monitoring the diffusion of pollutants, the pollutant concentration provided by sensors can be used to locate the pollutant source accurately and quickly, so that we can take timely measures before the pollutants affect the residents and cause more serious consequences. 5 Locating the source of indoor pollutants by limited sensor-provided information is a typical inverse problem. Regarding the solution of the inverse calculation problem, Liu and Zhai 6 summarized the previous research and categorized it into three methods, forward method, 7 backward method 8 and probability method.…”

“…By effectively monitoring the diffusion of pollutants, the pollutant concentration provided by sensors can be used to locate the pollutant source accurately and quickly, so that we can take timely measures before the pollutants affect the residents and cause more serious consequences. 5…”