Smart curiosity sink node prediction mining algorithm for path optimization in wireless sensor network

Abstract

engineering, for example, the dispersed frameworks, the database frameworks, and the data mining. Dealing with the extensive sums of information and efficiently using this information in improved path optimization has become increasingly challenging. In this paper, we will demonstrate how sink node predicted and integrated for path relationships and patterns in linked data, i.e., the interdependencies between data items at the lowest elemental level. The problem of path optimization has been approached using various techniques. The path selection plays the vital role in achieving the quality of service parameter and secure communication. Considering multiple routing, the security can be enforced with various strategies. Using few parameters namely the congestion, delay and hop count would support improve the performance of the network as well as lifetime. With the motivation, an efficient smart curiosity sink node prediction mining algorithm has been presented in this paper. First, both the source and destination nodes maintain information about the routes and network conditions. Based on that a single efficient path has been selected for data transmission. On the other side, the receiver verifies the path being followed, the route available and their conditions. Using this information the delay approximation is performed to decide the legitimate of the path being selected and the traffic incur in the way. The proposed method identifies several network threats and detects the presence of the node in the route. The proposed plan improves the performance of mining data efficiency as well as increases the throughput.