Visual tracking of the millennium development goals with a fuzzified self-organizing neural network

  • Peter Sarlin
Original Article


This paper uses the self-organizing map (SOM), a neural network-based projection and clustering technique, for monitoring the millennium development goals (MDGs). The eight MDGs represent commitments to reduce poverty and hunger, and to tackle ill-health, gender inequality, lack of education, lack of access to clean water and environmental degradation by 2015. This paper presents a SOM model for cross sectional and temporal visual benchmarking of countries and pairs the map with a geospatial dimension by mapping the clustering onto a geographic map. The temporal monitoring is facilitated by fuzzifying the second-level clustering with membership degrees. By creating an MDG index, and associating the SOM model with it, the model enables cross sectional and temporal analysis of the overall MDG progress of countries or regions. Further, the SOM model enables analysis of country-specific as well as regional performance according to a user-specified level of aggregation. The result of this paper is an MDG map for visual tracking and monitoring of the progress of MDG indicators.


Self-organizing maps Millennium development goals Projection Clustering Geospatial visualization 



I acknowledge Barbro Back and Tomas Eklund for helpful comments and suggestions.


  1. 1.
    Alkire S, Santos ME (2010) Acute multidimensional poverty: a new index for developing countries. Oxford Poverty and Human Development Initiative, Working Paper 38, University of OxfordGoogle Scholar
  2. 2.
    Boehme O, Hardoon D, Manevitz L (2011) Classifying cognitive states of brain activity via one-class neural networks with feature selection by genetic algorithms. Int J Mach Learn Cybern 2(3):125–134CrossRefGoogle Scholar
  3. 3.
    Collan M, Eklund T, Back B (2007) Using the self-organizing map to visualize and explore socio-economic development. EBS Rev 22(1):6–15Google Scholar
  4. 4.
    Coudouel A, Hentschel JS, Wodon QD (2002) Poverty measurement and analysis. In: Klugman J (ed) A sourcebook for poverty reduction strategies. The International Bank for Reconstruction and Development/The World Bank, Washington, pp 29–69Google Scholar
  5. 5.
    Cox T, Cox M (2001) Multidimensional scaling. Chapman & Hall/CRC, Boca RatonzbMATHGoogle Scholar
  6. 6.
    Deboeck G (1998) Best practices in data mining using self-organizing maps. In: Deboeck G, Kohonen T (eds) Visual explorations in finance with self-organizing maps. Springer, Berlin, pp 201–229Google Scholar
  7. 7.
    Eklund T, Back B, Vanharanta H, Visa A (2008) Evaluating a SOM-based financial benchmarking tool. J Emerg Technol Acc 5(1):109–127CrossRefGoogle Scholar
  8. 8.
    Graaff AJ, Engelbrecht AP (2011) Clustering data in stationary environments with a local network neighborhood artificial immune system. Int J Mach Learn Cybern. doi: 10.1007/s13042-011-0041-0
  9. 9.
    Guo G, Chen S, Chen L (2011) Soft subspace clustering with an improved feature weight self-adjustment mechanism. Int J Mach Learn Cybern. doi: 10.1007/s13042-011-0038-8
  10. 10.
    Kaski S (1997) Data exploration using self-organizing maps. Acta Polytechnica Scandinavica, Mathematics, Computing and Management in Engineering Series No. 82., EspooGoogle Scholar
  11. 11.
    Kaski S, Kohonen T (1996) Exploratory data analysis by the self-organizing map: structures of welfare and poverty in the world. In: Proceedings of the 3rd International Conference on Neural Networks in the Capital Markets. World Scientific, London, pp 498–507Google Scholar
  12. 12.
    Kaski S, Venna J, Kohonen T (2000) Coloring that reveals cluster structures in multivariate data. Aust J Intell Inf Process Syst 6:82–88Google Scholar
  13. 13.
    Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 66:59–69MathSciNetCrossRefGoogle Scholar
  14. 14.
    Kohonen T (2001) Self-organizing maps, 3rd edn. Springer, BerlinzbMATHCrossRefGoogle Scholar
  15. 15.
    Liang J, Song W (2011) Clustering based on steiner points. Int J Mach Learn Cybern. doi: 10.1007/s13042-011-0047-7
  16. 16.
    Naq AK, Mitra A (2002) Identifying patterns of socio-economic development using self-organizing maps. J Soc Econ Dev 4(1):55–88Google Scholar
  17. 17.
    Noorbakhsh FA (1998) A modified human development index. World Dev 26:517–528CrossRefGoogle Scholar
  18. 18.
    Prados de la Escosura L (2010) Improving human development: a long-run view. CEPR discussion Paper 7982Google Scholar
  19. 19.
    Prennushi G, Rubio G, Subbarao K (2002) Monitoring and evaluation. In: Klugman J (ed) A sourcebook for poverty reduction strategies. The International Bank for Reconstruction and Development/The World Bank, Washington, pp 105–130Google Scholar
  20. 20.
    Ravallion M (2010) Mashup indices of development. Policy Research Working Paper 5432, World BankGoogle Scholar
  21. 21.
    Resta M (2009) Early warning systems: an approach via self organizing maps with applications to emergent markets. In: Proceedings of the 2009 conference on New Directions in Neural Networks: 18th Italian Workshop on Neural Networks. IOS Press, The NetherlandsGoogle Scholar
  22. 22.
    Ripley BD (1996) Pattern recognition and neural networks. Cambridge University Press, CambridgezbMATHGoogle Scholar
  23. 23.
    Sagar AD, Najam A (1998) The human development index: a critical review. Ecol Econ 25:249–264CrossRefGoogle Scholar
  24. 24.
    Sahn DE, Stifel DC (2003) Progress toward the millennium development goals in Africa. World Dev 31(1):23–52CrossRefGoogle Scholar
  25. 25.
    Samad T, Harp SA (1992) Self-organization with partial data. Netw Comput Neural Syst 3:205–212CrossRefGoogle Scholar
  26. 26.
    Sammon JW (1969) A non-linear mapping for data structure analysis. IEEE Tran Comput 18(5):401–409CrossRefGoogle Scholar
  27. 27.
    Sarlin P, Eklund T (2011a) Financial performance analysis of European banks using a fuzzified self-organizing map. In: Proceedings of the 15th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES2011), Springer, Kaiserslautern, September 12–14, 2011, pp 185–194Google Scholar
  28. 28.
    Sarlin P, Eklund T (2011b) Fuzzy clustering of the self-organizing map: some applications on financial time series. In: Proceedings of the 8th International Workshop on Self-Organizing Maps (wSOM’11), Springer, Helsinki, June 13–15, 2011, pp 40–50Google Scholar
  29. 29.
    Sarlin P, Peltonen T (2011) Mapping the state of financial stability. ECB Working Papers No. 1382Google Scholar
  30. 30.
    Tong DL, Mintram R (2010) Genetic algorithm-neural network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection. Int J Mach Learn Cybern 1:75–87CrossRefGoogle Scholar
  31. 31.
    Tukey JW (1977) Exploratory data analysis. Addison-Wesley, ReadingzbMATHGoogle Scholar
  32. 32.
    Tyler Z, Gopal S (2010) Sub-Saharan Africa at a crossroads—a quantitative analysis of regional development. The Pardee Papers, No. 10, May 2010Google Scholar
  33. 33.
    UNDG (2003) Indicators for Monitoring the millennium development goals: definitions, rationale, concepts and methods. United Nations Development Group, New York. Available at: Accessed 5 December 2010
  34. 34.
    UNDP (1993) Human development report. Oxford University Press, New York, also published in various other yearsGoogle Scholar
  35. 35.
    UNECOSOC (2010) Assessing progress in Africa towards the millennium development goals report. E/ECA/COE/29/15 and AU/CAMEF/EXP/15(V). Available online: Accessed 10 December 2010
  36. 36.
    Vesanto J, Alhoniemi E (2000) Clustering of the self-organizing map. IEEE Trans Neural Netw 11(3):586–600CrossRefGoogle Scholar
  37. 37.
    Vesanto J, Sulkava M, Hollmén J (2003) On the decomposition of the self-organizing map distortion measure. In Proceedings of the Workshop on Self-Organizing Maps (wSOM’03), Springer, Hibikino, September 11–14, 2003, pp 11–16Google Scholar
  38. 38.
    Wang XZ, Dong CR (2009) Improving generalization of fuzzy if-then rules by maximizing fuzzy entropy. IEEE Trans Fuzzy Syst 17(3):556–567CrossRefGoogle Scholar
  39. 39.
    Wang XZ, Zhai JH, Lu SX (2008) Induction of multiple fuzzy decision trees based on rough set technique. Inf Sci 178(16):3188–3202MathSciNetzbMATHCrossRefGoogle Scholar
  40. 40.
    Wang XZ, Dong CR, Fan TG (2007) Training T-S norm neural networks to refine weights for fuzzy if-then rules. Neurocomputing 70(13–15):2581–2587CrossRefGoogle Scholar
  41. 41.
    Ward J (1963) Hierarchical grouping to optimize an objective function. J Am Stat Assoc 58:236–244CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2011

Authors and Affiliations

  1. 1.Department of Information Technologies, Turku Centre for Computer ScienceÅbo Akademi UniversityTurkuFinland

Personalised recommendations