Application of a New CO? Prediction Method Within Family House Occupancy Monitoring

The article describes the application of Python for verification a newly designed method CO2 prediction from measurements indoor parameters temperature and relative humidity within occupancy monitoring in real conditions family home. implementation non-electric quantities (indoor concentration, temperature, humidity) measurement five rooms home (living room, kitchen, children’s bathroom, bedroom) using Loxone technology sensors. IBM IoT (Internet Of Things) was used storing subsequent processing measured values time interval December 22, 2018, to 31, 2018. devised radial basis function (artificial neural networks (ANN)) mathematical (implementation environment) perform accurate predictions. For further increase accuracy reduction noise obtained course predicted signal, multiple variations LMS adaptive filter algorithm (Sign, Sign-Sign, Sign-Regressor) were (implemented MATLAB SW tool). proposed concentration exceeds 95% selected experiments.