Big data analytic architecture for intruder detection in heterogeneous wireless sensor networks

Barrier coverage in Wireless Sensor Networks (WSNs) is an important research issue as intruder detection is the main purpose of deploying wireless sensors over a specified monitoring region. In WSNs, excessive volume and variety of sensor data are generated, which need to be analyzed for accurate measurement of the image in terms of width and resolution. In this paper, a three layered big data analytic architecture is designed to analyze the data generated during the construction of the barrier and detection of the intruder using camera sensors. Besides, a cloud layer is designed for storing the analyzed data to study the behavior of the intruder. In order to minimize the number of camera sensors for constructing the barrier, algorithms are designed to construct the single barrier with limited node mobility and the barrier path Quality of Sensing (QoS) is maintained with a minimum number of camera sensors. Simulation results show that our algorithms can construct 100% of the barrier with fewer number of camera sensors and average data processing time can be reduced by using parallel servers even if for larger size of data.