Local Patches Alignment Embedding Based Localization for Wireless Sensor Networks

摘要

Localization for wireless sensor networks (WSNs) is a challenging research topic. Let the set of sensor nodes that are close to each other be a "patch", in this paper, we propose a new manifold learning method named local patches alignment embedding (LPAE), and then present a computationally efficient range-based WSNs localization approach using LPAE. Unlike the existing range-based localization methods using "patching" techniques, LPAE approach has the following features: 1) learning local position of all sensor nodes efficiently on a set of overlapping patches, which are constructed based on anchor nodes, rather than on neighborhood of each node, 2) aligning patches with the constraints of anchor nodes thus avoiding the accumulation of error, and 3) obtaining absolute positions of all sensor nodes directly without any other refinement technology. The proposed approach has been shown to be able to achieve satisfactory performance on both accuracy and efficiency via extensive simulations.