Bayesian Network and Hidden Markov Model for Estimating occupancy from measurements and knowledge

Manar Amayri (1) , Quoc-Dung Ngo , El Abed El Safadi (1) , Stéphane Ploix (1)

1 G-SCOP_GCSP - Gestion et Conduite des Systèmes de Production

– A general approach is proposed to determine the occupancy in a room using sensor data and knowledge coming respectively from observation and questioning are determined. Means to estimate occupancy include motion detections, power consumptions and acoustic pressure rewarded by a microphone. The proposed approach is inspired from machine learning. It starts by determining the most useful measurements in calculating information gains. Then, a non supervised estimation algorithm is proposed: it relies on Hidden Markov Model and Bayesian Network algorithms to model a human behaviour with probabilistic cause-effect relations and states based on knowledge and questioning. Bayesian Network(BN) and Hidden Markov Model (HMM) based approaches have been applied to an office setting, with an average estimation error of 0.1-0.08 and an accuracy of 89%-91%. This approach avoids the usage of a camera to determine the actual occupancy required for supervised learning.

Mots clés: – Bayesian methods; networks; Artificial intelligence; Learning theory; Knowledge modelling and knowledge based systems; Sensor

Domaines: Intelligence artificielle [cs.AI]

Manar Amayri, Quoc-Dung Ngo, El Abed El Safadi, Stéphane Ploix. Bayesian Network and Hidden Markov Model for Estimating occupancy from measurements and knowledge. 2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Sep 2017, Bucharest, Romania. ⟨10.1109/IDAACS.2017.8095179⟩. ⟨hal-01864832⟩