Ontolojik sensor verileri üzerine Türkiye için akıllı yönetim sistemi oluşturma

In recent years, sensors have become smaller enough to be used in every system, positive developments in the academic environment, and a decrease in prices have increased the interest in sensors. Sensor-based systems have spread rapidly to all areas of daily life, especially in industrial areas. Massive amounts of raw sensor data from sensor-based systems, the area of use of which has increased considerably, pose a fundamentally new set of research challenges, including their structuring, sharing, and management in a common framework. Although there are many academic studies on the integration of sensor data between different sensor-based systems, these studies focused on the integration of the data as syntax rather than semantic integration. Nowadays, the semantic sensor web approach, which enables us to enrich the meaning of sensor data in order to provide more advanced access to sensor data and add annotations, has been seen by some researchers as a critical technology in solving these problems. The grand goal of this thesis is to provide a standard data model for heterogeneous sensor data from different platforms by extending the ontology of semantic sensor networks. The proposed system was tested using 8 indoor parameters collected in the Application and Research Center and Intensive Care Unit within Abant Izzet Baysal University. Sensor data collected from selected use-cases were added to the proposed framework and an RDF data set was created. Classic machine learning algorithms have been implemented on the RDF data set created and compared from different angles.