Prediction model adaptation thanks to control chart monitoring application to pollutants prediction

Philippe Thomas (1) , William Derigent (1) , Marie-Christine Suhner (1)

1 CRAN - Centre de Recherche en Automatique de Nancy

Indoor air quality is a major determinant of personal exposure to pollutants in today's world since people spend much of their time in numerous different indoor environments. The Anaximen company develops a smart and connected object named Alima, which can measure every minute several physical parameters: temperature, humidity, concentrations of COV, CO 2 , formaldehyde and particulate matter (pm). Beyond the measurement aspect, Alima presents some data analysis feature named 'predictive analytics', whose primary aim is to predict the evolution of indoor pollutants in time. In this article, the neural network (NN) model, embedded in this object and designed for pollutant prediction, is presented. In addition with this NN model, this article also details an approach where batch learning is performed periodically when a too important drift between the model and the system is detected. This approach is based on control charts.

Mots clés: Indoor Air Quality; Neural Networks; Relearning; Control Charts

Domaines: Réseau de neurones [cs.NE]

Philippe Thomas, William Derigent, Marie-Christine Suhner. Prediction model adaptation thanks to control chart monitoring application to pollutants prediction. 6th International Joint Conference on Computational Intelligence, IJCCI'14, Oct 2014, Rome, Italy. ⟨hal-01086851⟩