A Novel Manifold Learning Algorithm for Localization Estimation in Wireless Sensor Networks

Abstract

We propose an accurate, distributed localization method that uses the connectivity measure to localize nodes in a wireless sensor network. The proposed method is based on a self-organizing isometric embedding algorithm that adaptively emphasizes the most accurate range of measurements and naturally accounts for communication constraints within the sensor network. Each node adaptively chooses a neighborhood of sensors and updates its estimate of position by minimizing a local cost function and then passes this update to the neighboring sensors. Simulations demonstrate that the proposed method is more robust to measurement error than previous methods and it can achieve comparable results using much fewer anchor nodes than previous methods.