Skip to main content

Least square support vector data description for HRRP-based radar target recognition

Abstract

A novel machine learning method named least square support vector data description (LSSVDD) is developed to classify the FFT-magnitude feature of complex high-resolution range profile (HRRP), motivated by the problem of radar automatic target recognition (RATR). The LSSVDD method not only inherits the advantage of LSSVM model, which owns low computational complexity with linear equality constraints, but also overcomes the shortcoming of poor capacity of variable targets in SVDD. Similar to the LSSVM, the distribution information within classes is found by least square method and applied for adjusting the boundary in LSSVDD, which relieves the over-fitting of SVDD. Hence, there will be a remarkable improvement in classification accuracy and generalization performance. Numerical experiments based on several publicly UCI datasets and HRRPs of four aircrafts are taken to compare the proposed method with other available approaches, and the results especially for multiple targets can demonstrate the feasibility and superiority of the proposed method. The LSSVDD is ideal for HRRP-Based radar target recognition.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2

References

  1. 1.

    Du L, Liu H, Wang P, Feng B, Pan M, Bao Z (2012) Noise robust radar HRRP target recognition based on multitask factor analysis with small training data size. IEEE T Signal Proces 60:3546–3559

    MathSciNet  Article  Google Scholar 

  2. 2.

    Wang J, Li Y, Chen K (2015) Radar high-resolution range profile recognition via geodesic weighted sparse representation. IET Radar Sonar Nav 9:75–83

    Article  Google Scholar 

  3. 3.

    Liu H, Feng B, Chen B, Du L (2016) Radar high-resolution range profiles target recognition based on stable dictionary learning. IET Radar Sonar Nav 10:228–237

    Article  Google Scholar 

  4. 4.

    Shi L, Wang P, Liu H, Xu L, Bao Z (2011) Radar HRRP statistical recognition with local factor analysis by automatic bayesian Ying-Yang harmony learning. IEEE T Signal Proces 59:610–617

    MathSciNet  Article  Google Scholar 

  5. 5.

    Du L, He H, Zhao L, Wang P (2016) Noise robust radar HRRP target recognition based on scatterer matching algorithm. IEEE Sens J 16:1743–1753

    Article  Google Scholar 

  6. 6.

    Pan M, Du L, Wang P, Liu H, Bao Z (2012) Noise-Robust Modification method for Gaussian-based models with application to radar HRRP recognition. IEEE Geosci Remote S 10:558–562

    Article  Google Scholar 

  7. 7.

    Liu J, Fang N, Xie YJ, Wang B (2016) Multi-scale feature-based fuzzy-support vector machine classification using radar range profiles. IET Radar Sonar Nav 10:370–378

    Article  Google Scholar 

  8. 8.

    Chen G, Zhang X, Wang ZJ, Montali A (2009) One-class classification for oil spill detection. Pattern Anal Applic 13: 349–366

    MathSciNet  Google Scholar 

  9. 9.

    Guo SM, Chen LC, Tsai JSH (2009) A boundary method for outlier detection based on support vector domain description. Pattern Recogn 42:77–83

    Article  MATH  Google Scholar 

  10. 10.

    Cao J, Zhang L, Wang B, Li F, Yang J (2016) A fast gene selection method for multi-cancer classification using multiple support vector data description. J Biomed Inform 53:381–389

    Article  Google Scholar 

  11. 11.

    Hejazi M, Al-Haddad S, Singh YP, Tout K (2016) Editing training data for multi-label classification with the k-nearest neighbor rule. Pattern Anal Applic 19:145–161

    MathSciNet  Article  Google Scholar 

  12. 12.

    Vapnik VN (1995) The nature of statistical learning theory. Springer, New York

    Book  MATH  Google Scholar 

  13. 13.

    Qi Z, Tian Y, Shi Y (2013) Robust twin support vector machine for pattern classification. Pattern Recogn 46:305–316

    Article  MATH  Google Scholar 

  14. 14.

    Shao Y, Chen W, Zhang J, Wang Z, Deng N (2014) An efficient weighted Lagrangian twin support vector machine for imbalanced data classification. Pattern Recogn 47:3158–3167

    Article  MATH  Google Scholar 

  15. 15.

    Tax DMJ, Duin RPW (2004) Support vector data description. Mach Learn 54:45–66

    Article  MATH  Google Scholar 

  16. 16.

    Mu T, Nandi AK (2009) Multiclass classification based on extended support vector data description. IEEE T Syst Man Cy B 39:1206–1216

    Article  Google Scholar 

  17. 17.

    Maldonado S (2015) Churn prediction via support vector classification: an empirical comparison. Intell Data Anal 19: S135–S147

    Article  Google Scholar 

  18. 18.

    Forghani Y, Sadoghi Yazdi H, Effati S (2012) An extension to fuzzy support vector data description (FSVDD*). Pattern Anal Appl 15:237–247

    MathSciNet  Article  Google Scholar 

  19. 19.

    Xiao Y, Liu B, Hao Z, Cao L (2014) A K-Farthest-Neighbor-based approach for support vector data description. Appl Intell 41:196–211

    Article  Google Scholar 

  20. 20.

    Cha M, Kim JS, Baek J (2014) Density weighted support vector data description. Expert Syst Appl 41:3343–3350

    Article  Google Scholar 

  21. 21.

    Tanveer M, Khan MA, Ho S (2016) Robust energy-based least squares twin support vector machines. Appl Intell 45:174–186

    Article  Google Scholar 

  22. 22.

    Silva DA, Silva JP, Rocha Neto AR (2015) Novel approaches using evolutionary computation for sparse least square support vector machines. Neurocomputing 168:908–916

    Article  Google Scholar 

  23. 23.

    Mall R, Suykens JAK (2015) Very sparse LSSVM reductions for large-scale data. IEEE T Neur Net Lear 26:1086–1097

    MathSciNet  Article  Google Scholar 

  24. 24.

    Tomar D, Agarwal S (2015) A comparison on multi-class classification methods based on least squares twin support vector machine. Knowl Based Syst 81:131–147

    Article  Google Scholar 

Download references

Acknowledgments

The authors gratefully acknowledge the helpful comments and suggestions of reviewers. This work was supported by National Natural Science Foundation of China (No.61372159).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yu Guo.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Guo, Y., Xiao, H. & Fu, Q. Least square support vector data description for HRRP-based radar target recognition. Appl Intell 46, 365–372 (2017). https://doi.org/10.1007/s10489-016-0836-5

Download citation

Keywords

  • Machine learning
  • Least square
  • Support vector data description
  • High-resolution range profile
  • Radar automatic target recognition