Mining Network Hotspots with Holes: A Summary of Results

  • Emre Eftelioglu
  • Yan Li
  • Xun Tang
  • Shashi Shekhar
  • James M. Kang
  • Christopher Farah
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9927)


Given a spatial network and a collection of activities (e.g. crime locations), the problem of Mining Network Hotspots with Holes (MNHH) finds network hotspots with doughnut shaped spatial footprint, where the concentration of activities is unusually high (e.g. statistically significant). MNHH is important for societal applications such as criminology, where it may focus the efforts of officials to identify a crime source. MNHH is challenging because of the large number of candidates and the high computational cost of statistical significance test. Previous work focused either on geometry based hotspots (e.g. circular, ring-shaped) on Euclidean space or connected subgraphs (e.g. shortest path), limiting the ability to detect statistically significant hotspots with holes on a spatial network. This paper proposes a novel Network Hotspot with Hole Generator (NHHG) algorithm to detect network hotspots with holes. The proposed algorithm features refinements that improve the performance of a naïve approach. Case studies on real crime datasets confirm the superiority of NHHG over previous approaches. Experimental results on real data show that the proposed approach yields substantial computational savings without reducing result quality.


Hotspot detection Crime hotspots Spatial scan statistics 



This material is based upon work supported by the National Science Foundation under Grants No. 1029711, IIS-1320580, 0940818 and IIS-1218168, the USDOD under Grants No. HM1582-08-1-0017. We would like to thank Kim Koffolt and University of Minnesota Spatial Computing Research Group for their comments.


  1. 1.
    Fitterer, J., Nelson, T., Nathoo, F.: Predictive crime mapping. Police Pract. Res. 16(2), 121–135 (2015)CrossRefGoogle Scholar
  2. 2.
    Brantingham, P., et al.: Environmental Criminology. SAGE, Beverly Hills (1981)Google Scholar
  3. 3.
    Kulldorff, M.: SaTScan user guide for version 9.0 (2011)Google Scholar
  4. 4.
    Eftelioglu, E., Tang, X., Shekhar, S.: Geographically robust hotspot detection: a summary of results. In: ICDM International Workshop on Spatial and Spatiotemporal Data Mining (SSTDM) (2015)Google Scholar
  5. 5.
    Kulldorff, M., et al.: An elliptic spatial scan statistic. Stat. Med. 25(22), 3929–3943 (2006)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Tang, X., et al.: Elliptical hotspot detection: a summary of results. In: ACM SIGSPATIAL Workshops (2015)Google Scholar
  7. 7.
    Neill, D.B., et al.: A fast multi-resolution method for detection of significant spatial disease clusters. In: Advances in Neural Information Processing Systems (2003)Google Scholar
  8. 8.
    Eftelioglu, E., et al.: Ring-shaped hotspot detection: a summary of results. In: IEEE International Conference on Data Mining, pp. 815–820 (2014)Google Scholar
  9. 9.
    Grubesic, T.H., Wei, R., Murray, A.T.: Spatial clustering overview and comparison: accuracy, sensitivity, and computational expense. Ann. Assoc. Am. Geogr. 104(6), 1134–1156 (2014)CrossRefGoogle Scholar
  10. 10.
    Beavon, D.J., Brantingham, P.L., Brantingham, P.J.: The influence of street networks on the patterning of property offenses. Crime Prev. Stud. 2, 115–148 (1994)Google Scholar
  11. 11.
    Law, J., Quick, M., Chan, P.: Bayesian spatio-temporal modeling for analysing local patterns of crime over time at the small-area level. J. Quant. Criminol. 30(1), 57–78 (2014)CrossRefGoogle Scholar
  12. 12.
    Okabe, A., Okunuki, K.-I., Shiode, S.: The SANET toolbox: new methods for network spatial analysis. Trans. GIS 10(4), 535–550 (2006)CrossRefGoogle Scholar
  13. 13.
    Okabe, A., Sugihara, K.: Spatial Analysis Along Networks: Statistical and Computational Methods. Wiley, New York (2012)CrossRefMATHGoogle Scholar
  14. 14.
    Shiode, S., Shiode, N.: Network-based space-time search-window technique for hotspot detection of street-level crime incidents. Int. J. Geogr. Inf. Sci. 27(5), 866–882 (2013)CrossRefGoogle Scholar
  15. 15.
    Dev, O., et al.: Significant route discovery: a summary of results. In: Duckham, M., Pebesma, E., Stewart, K., Frank, A.U. (eds.) GIScience 2014. LNCS, vol. 8728, pp. 284–300. Springer, Heidelberg (2014)Google Scholar
  16. 16.
    Shi, L., Janeja, V.P.: Anomalous window discovery for linear intersecting paths. IEEE Trans. Knowl. Data Eng. 23(12), 1857–1871 (2011)CrossRefGoogle Scholar
  17. 17.
    Costa, M.A., Assunção, R.M., Kulldorff, M.: Constrained spanning tree algorithms for irregularly-shaped spatial clustering. Comput. Stat. Data Anal. 56(6), 1771–1783 (2012)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Levine, N.: Crime mapping and the crimestat program. Geogr. Anal. 38(1), 41–56 (2006)CrossRefGoogle Scholar
  19. 19.
    Kuratowski, K.: Topology, vol. 1. Elsevier, Amsterdam (2014)Google Scholar
  20. 20.
    Kulldorff, M.: A spatial scan statistic. Commun. Stat.-Theor. Methods 26, 1481–1496 (1997)MathSciNetCrossRefMATHGoogle Scholar
  21. 21.
    MacKay, D.J.: Information Theory, Inference and Learning Algorithms. Cambridge University Press, Cambridge (2003)MATHGoogle Scholar
  22. 22.
    Us census bureau tiger/line shapefiles. Accessed 9 Dec 2015
  23. 23.
  24. 24.
    City of Oakland data portal. Accessed 1 May 2016
  25. 25.
    Ester, M., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise, pp. 226–231. AAAI Press (1996)Google Scholar
  26. 26.
    Hartigan, J.A., Wong, M.A.: Algorithm AS 136: a K-means clustering algorithm. Appl. Stat. 28, 100–108 (1979)CrossRefMATHGoogle Scholar
  27. 27.
    Oliver, D., et al.: A k-main routes approach to spatial network activity summarization. IEEE Trans. Knowl. Data Eng. 26, 1464–1478 (2014)CrossRefGoogle Scholar
  28. 28.
    Guo, D.: Local entropy map: a nonparametric approach to detecting spatially varying multivariate relationships. Int. J. Geogr. Inf. Sci. 24(9), 1367–1389 (2010)CrossRefGoogle Scholar
  29. 29.
    Wolfe, M.K., Mennis, J.: Does vegetation encourage or suppress urban crime? Evidence from Philadelphia, PA. Landscape and Urban Planning 108, 112–122 (2012)CrossRefGoogle Scholar
  30. 30.
    Hirschfield, A., Birkin, M., Brunsdon, C., Malleson, N., Newton, A.: How places influence crime: the impact of surrounding areas on neighbourhood burglary rates in a British city. Urban Stud. 51(5), 1057–1072 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Emre Eftelioglu
    • 1
  • Yan Li
    • 1
  • Xun Tang
    • 1
  • Shashi Shekhar
    • 1
  • James M. Kang
    • 2
  • Christopher Farah
    • 2
  1. 1.Department of Computer ScienceUniversity of MinnesotaMinneapolisUSA
  2. 2.National Geospatial-Intelligence AgencySpringfieldUSA

Personalised recommendations