No abstract

In this work, a prototype was developed to assess indoor air quality using an Arduino system. The system is based on the measurement of the light level, smoke concentration, temperature and air humidity. A thermal comfort index (TCI) was proposed, where a scale from 0 to 1 based on the weighted average of the individual indices was developed. Another approach, based on artificial neural networks, was formulated in which the parameters were used as input arguments of the network and the TCI was used as a target parameter. The response of the two models was compared, where it was possible to observe that the TCI values calculated by the network were considerably close to the values obtained by the deterministic model, with MSE of 1.73?10-5.