Advertisement

A Comprehensive Study of Crime Detection with PCA and Different Neural Network Approach

  • Ahmad Kadri Junoh
  • Muhammad Naufal Mansor
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 206)

Abstract

Crime rate in Malaysia is almost in awareness stage. The centre for Public Policy Studies Malaysia reports that the ratio of police to population is 3.6 officers to 1,000 citizens in Malaysia. This lack of manpower sources ratios alone are not a comprehensive afford of crime fighting capabilities. Thus, dealing with these circumstances, we present a comprehensive study to determine bandit behavior with PCA and different neural network algorithm such as Elman Neural Network (ELMNN), Feed Forward Neural Network (FFNN) and Cascade-Forward Neural Network (CFNN). This system provided a good justification as a monitoring supplementary tool for the Malaysian police arm forced.

Keywords

Crime rate Principal Component analysis Elman Neural Network Feed Forward Neural Network and Probabilistic Neural Network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Global Peace Index Vision of Humanity website, http://www.Visionofhumanity.org/gpi/results/rankings.php (accessed December 6, 2012)
  2. 2.
    RRT Country Advice 2010, Country Advice MYS35845 (January 11, 2010) Google Scholar
  3. 3.
    Royal Malaysian Police website, http://polismalaysia.brinkster.net/Royal%20Malaysian%20Police%20Force%20-%20About.asp (accessed December 6, 2012)
  4. 4.
    Center for Public Policy Studies Malaysia website, Policy Fact Sheet Polic, http://www.cpps.org.my/downloads/factsheets/Police%20factsheet.pdf (accessed January 4, 2010)
  5. 5.
    NationMaster.com website, Statistics Tab, Crime statistic – police per capita by country, http://www.nationmaster.com/graph/cri_pol_percap-crime-police-per-capita (accessed December 17, 2009)
  6. 6.
    International Association of Chiefs of Police website, Research Center Directorate Perspectives Police Officer to Population Ratios Bureau of Justice Statistics Data, http://www.theiacp.org/LinkClick.aspx?fileticket=LF7xdWl1tPk%3D&tabid=87(accessed December 21, 2009)
  7. 7.
    Cheriyadat, A.: Why principal component analysis is not an appropriate feature extraction method for hyperspectral data, vol. 6, pp. 3420–3422 (2003)Google Scholar
  8. 8.
    Park, M.S.: PCA-based Feature Extraction using Class Information, vol. 1, pp. 341–345 (2005)Google Scholar
  9. 9.
    Zhang, J., Zhang, X.-D., Ha, S.-W.: A Novel Approach Using PCA and SVM for Face Detection, vol. 3, pp. 29–33 (2008)Google Scholar
  10. 10.
    Jasmina, N., Milomir, M., Alempije, V.: Classification Accuracy of Neural Networks with PCA in Emotion Recognition. Theory and Applications of Mathematics & Computer Science, 11–161 (2011)Google Scholar
  11. 11.
    Eleyan, A., Demirel, H.O.: Face Recognition System Based on PCA and Feedforward Neural Networks. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 935–942. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Chitaliya, N.G.: Feature Extraction Using Wavelet-PCA and Neural Network for Application of Object Classification & Face Recognition, vol. 1, pp. 510–514 (2010)Google Scholar
  13. 13.
    Franco, L., Treves, A.: A neural network facial expression recognition system using unsupervised local processing, pp. 628–632 (2001)Google Scholar
  14. 14.
    Latha, P., Ganesan, L., Annadurai, S.: Face Recognition using Neural Networks. An International Journal (SPIJ) 3, 153–160 (2008)Google Scholar
  15. 15.
    Mansor, M.N., Yaacob, S., Hariharan, M., Basah, S.N., bin Ahmad Jamil, S.H.-F.S., Khidir, M.L.M., Rejab, M.N., Ibrahim, K.M.Y.K., bin Ahmad Jamil, A.H.-F.S., Junoh, A.K.: PCA - Based Feature Extraction for Preterm Birth Monitoring. Progress in process tomography & instrumentation system Series 8. Universiti Teknologi Malaysia (2012) ISBN 978-967-354-186-7Google Scholar
  16. 16.
    Mansor, M.N., Yaacob, S., Hariharan, M., Basah, S.N., bin Ahmad Jamil, S.H.-F.S., Khidir, M.L.M., Rejab, M.N., Ibrahim, K.M.Y.K., bin Ahmad Jamil, A.H.-F.S., Junoh, A.K.: PCA- Based Feature Extraction and k-NN algorithm for Early Jaundice Detection. Journal of Soft Computing and Software Engineering (2012) ISSN: 2251-7545Google Scholar
  17. 17.
    Mansor, M.N., Yaacob, S., Hariharan, M., Basah, S.N., bin Ahmad Jamil, S.H.-F.S., Khidir, M.L.M., Rejab, M.N., Ibrahim, K.M.Y.K., bin Ahmad Jamil, A.H.-F.S., Junoh, A.K.: PCA- Based Feature Extraction and LDA algorithm for Preterm Birth Monitoring. Journal of Soft Computing and Software Engineering (2012) ISSN: 2251-7545Google Scholar
  18. 18.
    Junoh, A.K., Mansor, M.N., Yaacob, S., Mukhtar, A.Z., Fauzi, S.F., Abu, M.S., Ahmad, W.Z.A.W., Jaafar, W.N.W.: Smart Surveillance System Detection Using PCA- Based Feature Extraction. Applied Mechanics and Materials Journal (2012) ISSN: 1660-9336Google Scholar
  19. 19.
    Werbos, P.J.: Generalization of backpropagation with application to a recurrent gas market model. Neural Networks 1 (1988)Google Scholar
  20. 20.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  21. 21.
    Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing 45, 2673–2681 (1997)CrossRefGoogle Scholar
  22. 22.
    Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18, 602–610 (2005)CrossRefGoogle Scholar
  23. 23.
    Schmidhuber, J.: Learning complex, extended sequences using the principle of history compression. Neural Computation 4(2), 234–242 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Institute of Engineering Mathematics (IMK)University Malaysia perlisKangarMalaysia
  2. 2.Intelligent Signal Processing Group (ISP)University Malaysia perlisKangarMalaysia

Personalised recommendations