Energy efficient localization in wireless ad-hoc sensor networks using probabilistic neural network and Independent Component Analysis

Recently, wireless ad-hoc sensor networks due to their abilities are being rapidly developed to collect data across the area of deployment. To describe the collected data and facilitate communication protocols, it is necessary to identify the location of each sensor. Usually, localization algorithms use trilateration or multilateration based on range measurements obtained from RSSI, TOA, TDOA and AoA. This paper addresses localization techniques in ad-hoc wireless networks, where anchors and unknown nodes are randomly positioned in a uniform distribution in a squared area. Here , we first review some existing sensor localization methods and then propose a localization method that with use of probabilistic neural network (PNN), estimates the locations of unknown nodes, Then we reduce calculations and energy consumption with the help of independent component analysis (ICA) by removing some unnecessary anchor nodes. A PNN can estimate the location of unknown nodes, properly and with the help of ICA we can easily reduce calculations and therefore energy consumption by about 43 percent in dense networks.