M.S. (Master of Science)
Department of Electrical Engineering
In recent years, scattering sensors to produce wireless sensor networks (WSN) has been proposed for detecting localized events in large areas. Because sensor measurements are noisy, the WSN needs to use statistical methods such as the scan statistic. The scan statistic groups measurements into various clusters, computes a cluster statistic for each cluster, and decides that an event has happened if any of the statistics exceeds a threshold. Previous researchers have investigated the performance of the scan statistic to detect events; however, little attention was given to the optimization of which clusters the scan statistic should use. Using the scan statistic and a Gaussian sensor model, we present a local search approach for solving this optimization problem. Starting from multiple initial random cluster sets, our modified Gradient Ascent Search produces a cluster set that improves the worst-case detection performance of both grid and random sensor networks. By adding the best clusters to the worst emitter positions and removing the least valuable clusters, our search algorithm successfully produces a list of cluster sets that increase the minimum detection performance and outperforms baseline cluster sets by multiple standard deviations.
Shulgan, James, "Optimizing Cluster Sets For The Scan Statistic Using Local Search" (2020). Graduate Research Theses & Dissertations. 7664.
Northern Illinois University
Rights Statement 2
NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.