access icon free Learning using privileged information for HRRP-based radar target recognition

© The Institution of Engineering and Technology
Received 04/11/2016, Accepted 12/09/2017, Revised 31/08/2017, Published 15/09/2017

A novel machine learning method named extended support vector data description with negative examples (ESVDD-neg) is developed to classify the fast Fourier transform-magnitude feature of complex high-resolution range profile (HRRP), motivated by the problem of radar automatic target recognition. The proposed method not only inherits the close non-linear boundary advantage of support vector data description with negative examples model but also incorporates a new learning paradigm named learning using privileged information into the model. It leads to the appealing application with no assumptions regarding the distribution of data and needs less training samples and prior information. Besides, the second order central moment is selected as privileged information for better recognition performance, weakening the effect of translation sensitivity, and the normalisation contributes to eliminating the amplitude sensitivity. Hence, there will be a remarkable improvement of recognition accuracy not only with small training dataset but also under the condition of low signal-to-noise ratio. Numerical experiments based on two publicly UCI datasets and HRRPs of four aircrafts demonstrate the feasibility and superiority of the proposed method. The noise robust ESVDD-neg is ideal for HRRP-based radar target recognition.

Inspec keywords: radar computing; radar target recognition; signal classification; fast Fourier transforms; radar signal processing; learning (artificial intelligence)

Other keywords: fast Fourier transform-magnitude feature classification; close nonlinear boundary advantage; HRRP-based radar target recognition; extended support vector data description-with-negative examples; translation sensitivity; low signal-to-noise ratio; learning paradigm; complex high-resolution range profile; ESVDD-neg; UCI datasets; radar automatic target recognition problem; machine learning method

Subjects: Integral transforms in numerical analysis; Signal processing and detection; Knowledge engineering techniques; Electrical engineering computing; Radar equipment, systems and applications; Integral transforms in numerical analysis; Digital signal processing

References

    1. 1)
      • 19. Cha, M., Kim, J.S., Baek, J.: ‘Density weighted support vector data description’, Expert Syst. Appl., 2014, 41, (7), pp. 3343–3350.
    2. 2)
      • 26. Cui, M., Prasad, S.: ‘Sparse representation-based classification: orthogonal least squares or orthogonal matching pursuit ?’, Pattern Recognit. Lett., 2016, 84, pp. 120–126.
    3. 3)
      • 5. Du, L., He, H., Zhao, L., et al: ‘Noise robust radar HRRP target recognition based on scatterer matching algorithm’, IEEE Sens. J., 2016, 16, (6), pp. 1743–1753.
    4. 4)
      • 11. Cao, J., Zhang, L., Wang, B., et al: ‘A fast gene selection method for multi-cancer classification using multiple support vector data description’, J. Biomed. Inf., 2015, 53, pp. 381–389.
    5. 5)
      • 20. Vapnik, V., Vashist, A.: ‘A new learning paradigm: learning using privileged information’, Neural Netw., 2009, 22, (5-6), pp. 544–557.
    6. 6)
      • 21. Lapin, M., Heinb, M., Schiele, B.: ‘Learning using privileged information: SVM+ and weighted SVM’, Neural Netw., 2014, 53, pp. 95–108.
    7. 7)
      • 13. Jo, Q.H., Chang, J.H., Shin, J.W., et al: ‘Statistical model-based voice activity detection using support vector machine’, IET Signal Process., 2008, 3, pp. 205–210.
    8. 8)
      • 24. Feyereisl, J., Aickelin, U.: ‘Privileged information for data clustering’, Inf. Sci., 2012, 194, pp. 4–23.
    9. 9)
      • 25. Zhang, W.: ‘Support vector data description using privileged information’, Electron. Lett., 2015, 51, (14), pp. 1075–1076.
    10. 10)
      • 18. Forghani, Y., Sadoghi Yazdi, H., Effati, S.: ‘An extension to fuzzy support vector data description (FSVDD*)’, Pattern Anal. Appl., 2012, 15, (3), pp. 237–247.
    11. 11)
      • 30. Manikandan, J., Venkataramani, B.: ‘Evaluation of multiclass support vector machine classifiers using optimum threshold-based pruning technique’, IET Signal Process., 2011, 5, pp. 506–513.
    12. 12)
      • 27. Shrivastava, A., Patel, V.M., Chelappa, R.: ‘Multiple kernel learning for sparse representation-based classification’, IEEE Trans. Image Process., 2014, 23, (7), pp. 3013–3024.
    13. 13)
      • 22. Vapnik, V., Izmailov, R.: ‘Learning using privileged information: similarity control and knowledge transfer’, J. Mach. Learn. Res., 2015, 16, pp. 2023–2049.
    14. 14)
      • 15. Tax, D.M.J., Duin, R.P.W.: ‘Support vector data description’, Mach. Learn., 2004, 54, pp. 45–66.
    15. 15)
      • 10. Liu, Y., Liu, Y., Chen, Y.: ‘Fast support vector data descriptions for novelty detection’, IEEE Trans. Neural Netw., 2010, 21, (8), pp. 1296–1313.
    16. 16)
      • 12. Lei, L., Xiao-Dan, W., Xi, L., et al: ‘Hierarchical error-correcting output codes based on SVDD’, Pattern Anal. Appl., 2016, 19, pp. 163–171.
    17. 17)
      • 1. Du, L., Liu, H., Wang, P., et al: ‘Noise robust radar HRRP target recognition based on multitask factor analysis with small training data size’, IEEE Trans. Signal Process., 2012, 60, (7), pp. 3546–3559.
    18. 18)
      • 28. Mu, T., Nandi, A.K.: ‘Multiclass classification based on extended support vector data description’, IEEE Trans. Syst. Man Cybern. B, 2009, 39, (5), pp. 1206–1216.
    19. 19)
      • 16. Wang, Z., Zhao, Z., Weng, S., et al: ‘Solving one-class problem with outlier examples by SVM’, Neurocomputing, 2015, 149, pp. 100–105.
    20. 20)
      • 17. Huang, G., Chen, H., Zhou, Z., et al: ‘Two-class support vector data description’, Pattern Recognit., 2011, 44, (2), pp. 320–329.
    21. 21)
      • 3. Zhai, S., Jiang, T.: ‘Sparse representation-based feature extraction combined with support vector machine for sense-through-foliage target detection and recognition’, IET Signal Process., 2014, 8, (5), pp. 458–466.
    22. 22)
      • 7. Liu, J., Fang, N., Xie, Y.J., et al: ‘Multi-scale feature-based fuzzy-support vector machine classification using radar range profiles’, IET Radar Sonar Navig., 2016, 10, (2), pp. 370–378.
    23. 23)
      • 9. Chen, G., Zhang, X., Wang, Z.J., et al: ‘Robust support vector data description for outlier detection with noise or uncertain data’, Knowl.-Based Syst., 2015, 90, pp. 129–137.
    24. 24)
      • 23. Wang, S., Zhu, Y., Yue, L., et al: ‘Emotion recognition with the help of privileged information’, IEEE Trans. Auton. Ment. Dev., 2015, 7, (3), pp. 189–200.
    25. 25)
      • 6. Pan, M., Du, L., Wang, P., et al: ‘Noise-robust modification method for Gaussian-based models with application to radar HRRP recognition’, IEEE Geosci. Remote Sensing, 2013, 10, (3), pp. 558–562.
    26. 26)
      • 4. Shi, L., Wang, P., Liu, H., et al: ‘Radar HRRP statistical recognition with local factor analysis by automatic Bayesian ying-Yang harmony learning’, IEEE Trans. Signal Process., 2011, 59, (2), pp. 610–617.
    27. 27)
      • 8. Guo, S.M., Chen, L.C., Tsai, J.S.H.: ‘A boundary method for outlier detection based on support vector domain description’, Pattern Recognit., 2009, 42, (1), pp. 77–83.
    28. 28)
      • 29. Tomar, D., Agarwal, S.: ‘A comparison on multi-class classification methods based on least squares twin support vector machine’, Knowl.-Based Syst., 2015, 81, pp. 131–147.
    29. 29)
      • 14. Tax, D.M.J., Duin, R.P.W.: ‘Support vector domain description’, Pattern Recognit. Lett., 1999, 20, pp. 1191–1199.
    30. 30)
      • 2. Li, Y., Zhang, L., Liu, B., et al: ‘Stepped-frequency inverse synthetic aperture radar imaging based on adjacent pulse correlation integration and coherent processing’, IET Signal Process., 2011, 5, (7), pp. 632–642.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2016.0625
Loading

Related content

content/journals/10.1049/iet-spr.2016.0625
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading