An ACO Improved Approach for Critical Node Tracking in WSN

Abstract

A wireless sensor network is composed by hundreds or thousands of small compact devices, called sensor nodes, equipped with sensors (e.g. acoustic, seismic or image), that are densely deployed in a large geographical area. One of the most effective sensor network type is critical sensor network. In such kind of network, some nodes are connected to environment called critical sensor nodes and some nodes are defined as normal sensor nodes. Complete system depends on the critical nodes. Because of this, it is required that the critical nodes are always in processing situation. To analyze whether these nodes are working or not it is required to monitor these nodes regularly. In this paper, an approach is defined to analyze these critical nodes. This research paper defines an approach to resolve number of associated problem in such critical node network. Support vector machine learning may be a comparatively recent methodology that gives a decent generalization performance. Like alternative ways, SVM learning has been applied to the task of face detection, wherever the drawbacks of the technique became evident. Analysis that specializes in accuracy found that competitive performance is feasible however training on adequately giant datasets is difficult. Others tackled the speed issue and whereas varied approximation ways created interactive response times potential, those usually came at a worth of reduced accuracy.