Hidden Markov Model for Internet of Things Data Analysis

The Internet of Things for the household market will reach 1.7 trillion dollars by 2020. With fast growing innovation trends an important challenge consists in finding optimized algorithms for data prediction and interpretation. Building's energy behavior is influenced by a wide range of factors. The complexity of predicting the energy performance of the buildings has led to simplified models which use regression technics based on input-output relations. The current research is focused on finding an optimized Hidden Markov Model which fits the data acquired through IoT system. The current paper is motivated by the necessity of identifying a flexible and adaptive data driven model which can be used in intelligent buildings to reduce the energy demands for heating and cooling. In this paper, we propose a discrete model based on Hidden Markov Models (HMMs).