A Novel Approach for Automation of Smart Homes, Based on Internet of Things, Using Fuzzy Ontology

Abstract

The number of intelligent devices that are able to connect to the Internet and create networks to communicate with each other is increasing every day. These devices and networks are called Internet of Things (IoT). These networks usually contain wireless sensors. In addition to heterogeneity of these devices, formats of their data, measurement methods, data management and interoperability are the main challenges of these networks. On the other hand, semantic technology and ontology can address some of these challenges, and provide capabilities such as management, queries, and combining sensors and observed data. The current ontology structure is not capable of working with fuzzy or implicit information that are found in numerous application domains. In this paper, a fuzzy ontology for semantic sensor networks is proposed to automate smart homes based on Semantic Sensor Networks (SSN), which has the following phases: first, using the WordNet ontology, the location and type of objects is identified. Then, using a graphical interface, information other than location and type of object are delivered, if necessary. Next, the object and its synonyms are saved in a list, and it is added to the list known objects set. In the next phase, the relation of the object with other groups is assessed based on the similarity measure using the fuzzy ontology, and finally, this is done according to three measures of temperature humidity and light and for the dependency function of each measure. The performance and accuracy of the system is compared to two existing works, and it is shown that the proposed method outperforms them in terms of the consumed water, gas and electricity.