A Spatial Segmentation Algorithm for Resource Allocation in an Integrated Spatial and Networked Environment

摘要

We examine the discrete shortest path network interdiction problem and introduce an algorithm to determine defense resource location points based on network properties. Our proposed method examines how network density, complexity and connectivity can be used to establish improved discrete geographic locations for allocating defense resources. We test performance of the algorithmically-derived locations on the real-world sub-networks of Washington DC, Houston and New York City and compare the resulting discrete shortest path network interdiction results to three grid-based location schemes using computational and spatial analysis techniques. Results demonstrate improved objective performance and a high degree of spatial dissimilarity between the algorithmic and grid-based location schemes. The observed dissimilarity illustrates the importance of strong resource location identification schemes and the propensity for erroneous decision-making under simplified resource location assumptions.