An Improved Deep Clustering Model for Underwater Acoustical Targets



Hand-craft features and clustering algorithms constitute the main parts of the unsupervised clustering system. Performance of the clustering deteriorates when the assumed probabilistic distribution of the data differs from the true one. This paper introduces a novel method that combines systematically the deep Boltzmann machine (DBM) with the Dirichlet process based Gaussian mixture model (DP-GMM) to bypass the problem of distribution mismatch. DBM is firstly used to extract the deep complex data features. By tactfully designing the distributions of different layers in DBM to make them compatible to that of the DP-GMM, we build a distribution consistent clustering system. The system is then jointly optimized by Markov chain Monte Carlo method with succinct updating formulations. The experimental results on two real databases of underwater acoustical target show the effectiveness and the robustness of the proposed clustering method.


Data clustering Deep Boltzmann machine Dirichlet process Gaussian mixture model Passive sonar target 



This work is supported by the National Natural Science Foundation of China under Grants 61501375, 11774291 and 11374241 and by the Fundamental Research Funds for the Central Universities under Grant 3102016ZY006.


  1. 1.
    Arthur D, Vassilvitskii S (2007) k-means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms. Society for Industrial and Applied Mathematics, pp 1027–1035Google Scholar
  2. 2.
    Bachem O, Lucic M, Hassani SH, Krause A (2016) Approximate k-means++ in sublinear time. In: AAAI, pp 1459–1467Google Scholar
  3. 3.
    Biernacki C, Celeux G, Govaert G (2000) Assessing a mixture model for clustering with the integrated completed likelihood. IEEE Trans Pattern Anal Mach Intell 22(7):719–725CrossRefGoogle Scholar
  4. 4.
    Bishop CM et al (2006) Pattern recognition and machine learning. Springer, New York, pp 4–12MATHGoogle Scholar
  5. 5.
    Celebi ME, Kingravi HA, Vela PA (2013) A comparative study of efficient initialization methods for the k-means clustering algorithm. Expert Syst Appl 40(1):200–210CrossRefGoogle Scholar
  6. 6.
    Chandran C, Kamal S, Mujeeb A, Supriya M et al (2015) Novel class detection of underwater targets using self-organizing neural networks. In: Underwater technology (UT), 2015 IEEE. IEEE, pp 1–5Google Scholar
  7. 7.
    Cipli G, Sattar F, Driessen PF (2015) Multi-class acoustic event classification of hydrophone data. In: Communications, computers and signal processing (PACRIM), 2015 IEEE Pacific Rim conference on. IEEE, pp 473–478Google Scholar
  8. 8.
    Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11(Feb):625–660MathSciNetMATHGoogle Scholar
  9. 9.
    Hinton G (2010) A practical guide to training restricted boltzmann machines. Momentum 9(1):926Google Scholar
  10. 10.
    Hong C, Yu J, Tao D, Wang M (2015) Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. IEEE Trans Ind Electron 62(6):3742–3751Google Scholar
  11. 11.
    Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670MathSciNetCrossRefGoogle Scholar
  12. 12.
    Jian L, Yang H, Zhong L, Ying X (2014) Underwater target recognition based on line spectrum and support vector machine. In: International conference on mechatronics, control and electronic engineering (MCE2014). Atlantis Press, pp 79–84Google Scholar
  13. 13.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  14. 14.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  15. 15.
    Neal RM (2000) Markov chain sampling methods for Dirichlet process mixture models. J Comput Graph Stat 9(2):249–265MathSciNetGoogle Scholar
  16. 16.
    Rand WM (1971) Objective criteria for the evaluation of clustering methods. J Am Stat Assoc 66(336):846–850CrossRefGoogle Scholar
  17. 17.
    Rasmussen CE (1999) The infinite Gaussian mixture model. NIPS 12:554–560Google Scholar
  18. 18.
    Salakhutdinov R, Hinton G (2012) An efficient learning procedure for deep Boltzmann machines. Neural Comput 24(8):1967–2006MathSciNetCrossRefMATHGoogle Scholar
  19. 19.
    Salakhutdinov R, Hinton GE (2009) Deep Boltzmann machines. Artif Intell Stat 1:448–455MATHGoogle Scholar
  20. 20.
    Salakhutdinov R, Tenenbaum JB, Torralba A (2013) Learning with hierarchical-deep models. IEEE Trans Pattern Anal Mach Intell 35(8):1958–1971CrossRefGoogle Scholar
  21. 21.
    Su Y (2017) Robust video face recognition under pose variation. Neural Process Lett 1–15.
  22. 22.
    Wang L, Zhao L, Bi G, Wan C, Zhang L, Zhang H (2016) Novel wideband DOA estimation based on sparse Bayesian learning with Dirichlet process priors. IEEE Trans Signal Process 64(2):275–289MathSciNetCrossRefGoogle Scholar
  23. 23.
    Yao X, Han J, Cheng G, Qian X, Guo L (2016) Semantic annotation of high-resolution satellite images via weakly supervised learning. IEEE Trans Geosci Remote Sens 54(6):3660–3671CrossRefGoogle Scholar
  24. 24.
    Yu J, Yang X, Gao F, Tao D (2016) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans Cybern 47(12):4014–4024Google Scholar
  25. 25.
    Yu J, Zhang B, Kuang Z, Lin D, Fan J (2017) iPrivacy: image privacy protection by identifying sensitive objects via deep multi-task learning. IEEE Trans Inf Forensics Secur 12(5):1005–1016CrossRefGoogle Scholar
  26. 26.
    Zhang D, Han J, Han J, Shao L (2016) Cosaliency detection based on intrasaliency prior transfer and deep intersaliency mining. IEEE Trans Neural Netw Learn Syst 27(6):1163–1176MathSciNetCrossRefGoogle Scholar
  27. 27.
    Zhang D, Han J, Li C, Wang J, Li X (2016) Detection of co-salient objects by looking deep and wide. Int J Comput Vis 120(2):215–232MathSciNetCrossRefGoogle Scholar
  28. 28.
    Zhang D, Han J, Jiang L, Ye S, Chang X (2017) Revealing event saliency in unconstrained video collection. IEEE Trans Image Process 26(4):1746–1758MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Qiang Wang
    • 1
  • Lu Wang
    • 1
  • Xiangyang Zeng
    • 1
  • Lifan Zhao
    • 2
  1. 1.The School of Marine Science and TechnologyNorthwestern Polytechnical UniversityXi’anChina
  2. 2.The School of Electrical and Electronic EngineeringNanyang Technological UniversitySingaporeSingapore

Personalised recommendations