Training by ART-2 and Classification of Ballistic Missiles Using Hidden Markov Model

  • Upendra Kumar Singh
  • Vineet Padmanabhan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


This paper addresses the classification of different ranges of Ballistic Missiles (BM) for air defense applications using Adaptive Resonance Theory (ART-2) and Hidden Markov Model (HMM). ART-2 finds the initial clusters using unsupervised learning to be fed to HMM for classification using recursive method. The classification is based on derived parameters of specific energy, acceleration, altitude and velocity which in turn are acquired from measured data by radars. To meet the conflicting requirements of classifying short as well as long-range BM trajectories, we are proposing a formulation for partitioning the trajectory by using a moving window concept. Experimental results show that the HMM model is able to classify above 95% within time of the order of milliseconds once initial data is trained using ART2.


Hide Markov Model Adaptive Resonance Theory Hide Markov Model Model Ballistic Missile M2000 Class 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Bashir, F.I., Khokhar, A.A., Schonfeld, D.: Object trajectory-based activity classification and recognition using hidden markov models. IEEE Transactions on Image Processing 16(7), 1912–1919 (2007)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bishop, C.M.: Pattern reccognition and Machine Learning. Springer (2006)Google Scholar
  3. 3.
    Fausett, L.: Fundamentals of Neural Networks - Architectures, Algorithms and Applications. Prentice Hall (2008)Google Scholar
  4. 4.
    Fraser, A.M.: Hidden Markov Models and Dynamical Systems. Society for Industrial and Applied Mathematics (2008)Google Scholar
  5. 5.
    Carpenter, G.A., Grossberg, S.: Art 2: self-organization of stable category recognition codes for analog input patterns. Journal of Optics 26(23), 4919–4930 (1987)Google Scholar
  6. 6.
    Garcia, J., Poncha, O.P., Molina, J.M., de Miguel, G.: Trajectory classification based on machine-learning techniques over tracking data. In: 9th International Conference on Information Fusion, pp. 1–8 (2006)Google Scholar
  7. 7.
    Juang, B.H., Rabiner, L.R.: Hidden markov models for speech recognition. Technometrics 33(3), 251–272 (1991)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Mantle, P.J.: The Missile Defense Equation-Factors for decision making. American Institute of Aeronautics and Astronautics (2003)Google Scholar
  9. 9.
    Mlich, I.J., Chmelar, P.: Trajectory classification based on hidden markov models. In: 18th International Conference on Computer Graphics and Vision, pp. 101–105 (2008)Google Scholar
  10. 10.
    Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  11. 11.
    Tait, P.: Introduction to Radar Target Recognition. The Institution of Engineering and Technology (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Upendra Kumar Singh
    • 1
  • Vineet Padmanabhan
    • 2
  1. 1.PGAD, Defence Research & Development OrganisationHyderabadIndia
  2. 2.School of Computer & Information SciencesUniversity of HyderabadIndia

Personalised recommendations