Abstract
This chapter shows a useful application of self-organizing mapping artificial neural networks (SOM ANN) to actual data. The dataset comes from investigations in London about drug trafficking conducted by Scotland Yard Metropolitan Police. The SOM system used in this application is empowered by filtering the codebook through the minimum spanning tree and by the graph analysis of the codebooks themselves. This application represents a new way to use SOM ANN in an actual situation: MST and graph analysis permits the discovering of new hidden features and relationships in the dataset, usually not visible with the classic SOM approach. A massive drug trafficking database that has been collected over a period of time by the Scotland Yard Metropolitan Police is analyzed, and the results are explained that yield a series of useful profiles.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Dataset of seizures was extracted in March 2006 when the situation of the CDTD database was 954 tactic sequences, 1,084 persons, and 888 persons seized (40 incomplete cases).
- 2.
Dataset of arrest was extracted in January 2006 when the situation of the CDTD database was 338 tactic sequences, 513 persons, 351 accused persons (only 260 of whom were completed for processing).
References
Graham, R. L., & Hell, P. (1985). On the history of the minimum spanning tree. Annals of the History of Computing, 7(1), 43–57.
Kohonen, T. (1972). Correlation matrix memories. IEEE Transactions on Computers, C-21, 353–359. (Reprinted from Neurocomputing foundations of research, by J. A. Anderson & E. Rosenfeld, Eds., 1988, Cambridge, MA: MIT Press.)
Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 59–69. (Reprinted from Neurocomputing foundations of research, by J. A. Anderson & E. Rosenfeld, Eds., 1988, Cambridge, MA: MIT Press.)
Kohonen, T. (1984). Self-organization and associative memory (Springer series in information sciences, Vol. 8). Berlin: Springer.
Kohonen, T. (1990). The self-organizing map. Proceedings of the IEEE, 78, 1464–1480.
Kohonen, T. (1995a). Learning vector quantization. In M. A. Arbib (Ed.), The handbook of brain theory and neural networks. Cambridge, MA/London: The MIT Press, A Bradford Book.
Kohonen, T. (1995b). Self-organizing maps. Berlin/Heidelberg: Springer.
Software
Massini G. (2007). SOM (Self Organizing Maps), Semeion Software #19, v. 7.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
Appendix A: Variables of the Seizures
Appendix B: Variables of the Arrests
1. | Insufficient information available (TL) |
2. | Level1 OneBorough (TL) |
3. | Level2a Region (TL) |
4. | Level2 More Boroughs (TL) |
5. | Level3 International (TL) |
6. | Not Applicable (TL) |
7. | (A1)Asian-Indian (SE) |
8. | (A2)Asian-Pakistani (SE) |
9. | (A3)Asian-Bangladeshi (SE) |
10. | (A9)Any other Asian background (SE) |
11. | (B1)Black-Caribbean (SE) |
12. | (B2)Black-African (SE) |
13. | (B9)Any other Black background (SE) |
14. | (M1)White and Black Caribbean (SE) |
15. | (M3)White and Asian (SE) |
16. | (M9)Any other Mixed background (SE) |
17. | (N4)Persons declines to define (SE) |
18. | (NS)Not Stated (SE) |
19. | (O1)Chinese (SE) |
20. | (O9)Any Other (SE) |
21. | (W1)White British (SE) |
22. | (W2)White Irish (SE) |
23. | (W9)Any other White background (SE) |
24. | (EA1)White-European (Ethn) |
25. | (EA2)Dark-European (Ethn) |
26. | (EA3)Afro-Caribbean (Ethn) |
27. | (EA4)Asia (Ethn) |
28. | (EA5)Oriental (Ethn) |
29. | (EA6)Arab (Ethn) |
30. | ALGERIA (Nat) |
31. | FRANCE (Nat) |
32. | GAMBIA (Nat) |
33. | GHANA (Nat) |
34. | GREECE (Nat) |
35. | GRENADA (Nat) |
36. | IRELAND (Nat) |
37. | ITALY (Nat) |
38. | JAMAICA (Nat) |
39. | NIGERIA (Nat) |
40. | Not Known (Nat) |
41. | PHILIPPINES (Nat) |
42. | PORTUGAL (Nat) |
43. | SOMALIA (Nat) |
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Massini, G. (2013). Self-Organizing Maps: Identifying Nonlinear Relationships in Massive Drug Enforcement Databases. In: Buscema, M., Tastle, W. (eds) Intelligent Data Mining in Law Enforcement Analytics. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-4914-6_12
Download citation
DOI: https://doi.org/10.1007/978-94-007-4914-6_12
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-4913-9
Online ISBN: 978-94-007-4914-6
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)