Supporting Information for Indoor air quality monitoring system with high accuracy of gas classification and concentration prediction via reasonable material selection

Reasonable selection of sensing materials is crucial for improving the recognition accuracy of sensor array. In this work, to identify and measure indoor air pollutants (C7H8, HCHO, CH4 and NO2), six oxides (WO3, ZnO, In2O3, W-doped NiO, Pd-loaded SnO2 and Co-doped SnO2) were screened based on Temperature Programmed Desorption/ Reduction experiments. Based on the sensor array made by these oxides, it can clearly detect low concentrations of C7H8 (Response (S) =1.6 to 50 ppb), HCHO (S=1.4 to 50 ppb) and NO2 (S=3.3 to 50 ppb), which satisfies the need of indoor air monitoring. Meanwhile, three machine learning models (extreme gradient boost, support vector machine and back propagation neural network) are used to classify the four gases. The classification accuracy of these models are 95.45%, 100% and 100%, while the R2 of the concentration prediction are 99.65%, 94.9% and 98.04% respectively, indicating the rationality of material selection. Furthermore,It can still achieve good gas classification and concentration prediction accuracy even if two sensor units are reduced.Finally, an indoor air quality monitoring system is developed, which enables real-time monitoring of indoor gas quality through the Internet of Things.