Use of optimised MLP neural networks for spatiotemporal estimation of indoor environmental conditions of existing buildings

Controlling the indoor environmental quality in real time is essential for health, well-being and productivity of occupants a building. In recent years, research has focused on improving monitoring devices strategies developing techniques estimating conditions. The use machine learning algorithms this context increased considerably. However, data from large multizone working areas challenging. aim work to provide an interpolation methodology based optimised multilayered perceptron neural networks estimate conditions building time. These estimations are obtained without need neither occupied area nor human intervention considering low-cost sensors. network by implementing multiobjective genetic algorithm NSGA-II find best architecture terms error complexity. This method was applied centre north-western Spain, where interpolated values air temperature, relative humidity CO2 concentration were obtained. results case study yielded errors close 6% 5% humidity, 12% concentration. validate developed estimation contribution improvement control