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

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.

Automated summary

Accurate identification of pollutant sources is crucial in preventing human casualties and property damage. Machine learning algorithms such as ANN, SVM, KNN, and NB can be used with limited sensor data inputs to identify the location of pollutant sources. The study found that collecting pollutant concentrations over an extended period improves identification accuracy, and additional sensors are needed for the same accuracy after introducing distributed meteorological parameters. Increasing trained samples by a factor of five improved KNN's accuracy by 22% and SVM's by 1.7%, while ANN and NB remained unchanged.