Date Added: Sep 2009
In Wireless Sensor Networks (WSN), location estimation is important for routing efficiency and location-aware services. Traditional received signal strength based localizations using propagation-loss model are often erroneous for the low-cost WSN devices. The reason is that the wireless channel is vulnerable to so many factors that deriving the appropriate propagation-loss model for the low cost WSN devices is not possible. Hence, the authors propose a flexible model based on neural network and grid sensor training phase for accurate localization of sensors. Simulation results show that the location accuracy can be increased by increasing the grid sensor density and the number of access points.