Evidence theory‐based framework for improving automation in home automation system

Summary An easy and better way of life is the topic of the day and stays an important theme for the future. New researches focusing on this aspect are increasingly emerging. In recent years, improving automation in home automation systems and making homes even smarter seem to be a major issue. Automation of daily life functioning of home devices makes life easier for inhabitants, and then saves them from manual adjustments. Home automation systems encompass different communication and networking technologies. They are embedded with sensor networks that perceive information about the environment and occupants. The collected data can mainly be processed to infer sequential patterns defining the home behavior. However, the imperfection, particularly uncertainty of sensor readings, is a significant factor to consider. Also, time is an important aspect when reasoning about home behavior, as each pattern (scenario) performs at a given time throughout the day. Evidence theory is recently gaining great attention. It is suitable for dealing with imperfection of sensor data and for including temporal features into the reasoning process to discover the appropriate pattern to launch. This paper presents a new framework based on evidence theory with the inclusion of time features, for improving automation in home automation systems. The effectiveness of the proposed approach is evaluated by conducting experiments on synthetic dataset. The results show the efficiency of the discovery process when multiple working sensors are available. The results demonstrate also that reliability and accuracy of the process improve significantly when temporal information is provided. This paper presents a new framework based on evidence theory to improve the automation in home automation systems and make homes even smarter. The proposal was evaluated on a synthetic dataset in its 2 versions, including a case with and without temporal features. It was found that the framework operates more efficiently when multiple working sensors are available, and also, the reliability improves significantly when temporal features are considered.