ABSTRACT
Given a set of points in two dimensional space, statistically significant hotspot detection aims to detect locations where the concentration of points inside the hotspot is much higher than outside. Statistically significant hotspot detection is an important task in application domains such as epidemiology, ecology, criminology, etc. where it may reveal interesting information for domain experts. However, significant hotspot detection is challenging because of a lack of a generic technique for different hotspot patterns (i.e. shapes) and thus a large number of candidate hotspots to be enumerated and tested. Previous hotspot detection techniques focus on specific shapes (e.g. circles, rectangles, ellipses) to identify hotspot areas, but they cannot be used interchangeably which cause a vast variety of complicated and sometimes confusing techniques for each individual hotspot pattern. For example, a circular hotspot detection technique can not be used to discover a rectangular or an elliptical hotspot. In this paper, we propose a generic dual grid based pruning approach for hotspot detection that can be used for different hotspot patterns. We also present a cost analysis, a simplified experiment on the dataset size and a case study on a synthetic dataset to show the applicability of our proposed approach to circular hotspots.
- E. Eftelioglu, S. Shekhar, et al. Ring-shaped hotspot detection: a summary of results. In 2014 IEEE International Conference on Data Mining, pages 815--820. IEEE, 2014. Google ScholarDigital Library
- E. Eftelioglu, X. Tang, and S. Shekhar. Geographically robust hotspot detection: A summary of results. In 2015 IEEE International Conference on Data Mining Workshop (ICDMW), pages 1447--1456. IEEE, 2015. Google ScholarDigital Library
- J. Illingworth and J. Kittler. A survey of the hough transform. Computer vision, graphics, and image processing, 44(1):87--116, 1988. Google ScholarDigital Library
- M. Kulldorff. A spatial scan statistic. Communications in Statistics-Theory and methods, 26:1481--1496, 1997.Google ScholarCross Ref
- M. Kulldorff. Satscan user guide for version 9.0, 2011.Google Scholar
- D. B. Neill and A. W. Moore. A fast multi-resolution method for detection of significant spatial disease clusters. In Advances in Neural Information Processing Systems, 2003. Google ScholarDigital Library
- S. Shekhar et al. Identifying patterns in spatial information: A survey of methods. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1(3):193, 2011.Google ScholarCross Ref
Index Terms
- A generic dual grid pruning approach for significant hotspot detection
Recommendations
Elliptical Hotspot Detection: A Summary of Results
BigSpatial '15: Proceedings of the 4th International ACM SIGSPATIAL Workshop on Analytics for Big Geospatial DataGiven a set of points in Euclidean space, a minimum log likelihood ratio threshold, and a statistical significance threshold, Elliptical Hotspot Detection (EHD) finds elliptical hotspot areas where the concentration of activities inside is significantly ...
DRC-based hotspot detection considering edge tolerance and incomplete specification
ICCAD '14: Proceedings of the 2014 IEEE/ACM International Conference on Computer-Aided DesignTo improve the yield in current manufacturing processes, the problematic layout configurations, so-called process-hotspots, should be detected and replaced with yield friendly patterns. A hotspot pattern with edge tolerances and incomplete ...
Significant lagrangian linear hotspot discovery
IWCTS '20: Proceedings of the 13th ACM SIGSPATIAL International Workshop on Computational Transportation ScienceGiven a collection of multi-attribute trajectories, an event definition, and a spatial network, the Significant Lagrangian Linear Hotspot Discovery (SLLHD) problem finds the paths where records in the trajectories tend to be events in the Lagrangian ...
Comments