Building the data association network of sensors in the internet of things Izgradnja podatkovne mreze senzora u Internetu stvari

In the Internet of Things, wireless sensor networks (WSN) is in charge of gathering and transferring environment data. It is an essential work to mine data semantic in WSN in the data derived from sensors to improve the WSN. This paper proposes the Data Association Network of sensors (DAN) to organize the mined association semantic relations among sensors into an effective form. Because DAN holds the rich data semantic of WSN, it can improve WSN in some aspects, such as detecting the abnormal sensors, simulating the data of faulty sensors, or optimizing the topology of WSN. Experimental results show that the proposed method can mine the associated relations among sensor nodes effectively, and the DAN is helpful in solving some problems of WSN.