Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Sonar Target Classification using Generalized Discriminant Analysis

일반화된 판별분석 기법을 이용한 능동소나 표적 식별

  • Kim, Dong-wook (School of Electronics Engineering, Kyungpook National University) ;
  • Kim, Tae-hwan (Agency for Defense Development) ;
  • Seok, Jong-won (Department of Information and Communication, Changwon National University) ;
  • Bae, Keun-sung (School of Electronics Engineering, Kyungpook National University)
  • Received : 2017.11.15
  • Accepted : 2017.12.05
  • Published : 2018.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Linear discriminant analysis is a statistical analysis method that is generally used for dimensionality reduction of the feature vectors or for class classification. However, in the case of a data set that cannot be linearly separated, it is possible to make a linear separation by mapping a feature vector into a higher dimensional space using a nonlinear function. This method is called generalized discriminant analysis or kernel discriminant analysis. In this paper, we carried out target classification experiments with active sonar target signals available on the Internet using both liner discriminant and generalized discriminant analysis methods. Experimental results are analyzed and compared with discussions. For 104 test data, LDA method has shown correct recognition rate of 73.08%, however, GDA method achieved 95.19% that is also better than the conventional MLP or kernel-based SVM.

선형판별분석(LDA) 기법은 특징벡터의 차원을 줄이거나 클래스 식별에 이용되는 통계적 분석 방법이다. 그러나 선형 분리가 불가능한 데이터 집합의 경우에는 비선형 함수를 이용하여 특징벡터를 고차원의 공간으로 사상(mapping) 시켜줌으로써 선형 분리가 가능하도록 만들 수 있는데, 이러한 기법을 일반화된 판별분석(GDA) 또는 커널판별분석(KDA) 기법이라고 한다. 본 연구에서는 인터넷에 공개되어 있는 능동소나 표적신호에 LDA 및 GDA 기법을 이용하여 표적식별 실험을 수행하고, 그 결과를 비교/분석하였다. 실험 결과 104개의 테스트 데이터에 대해 LDA 기법으로는 73.08% 인식률을 얻었으나 GDA 기법으로는 95.19%로 기존의 MLP 또는 커널 기반 SVM에 비해 나은 성능을 보였다.

Keywords

References

  1. R. P. Gorman, T. J. Sejnowski, "Analysis of hidden units in a layered network trained to classify sonar targets," Neural Networks, vol. 1, no 1, pp. 75-89, Jan, 1988. https://doi.org/10.1016/0893-6080(88)90023-8
  2. Jongwon Seok, "Multi-aspect Based Active Sonar Target Classification," Journal of Korea Multimedia Society, vol. 19, no. 10, pp. 1775-1781, Oct, 2016. https://doi.org/10.9717/kmms.2016.19.10.1775
  3. J. W. Seok, K. S. Bae, "Target Classification Using Features Based on Fractional Fourier Transform," IEICE Trans. Information and Systems, vol. E97-D, no. 9, pp. 2518-2521, Sep, 2014. https://doi.org/10.1587/transinf.2014EDL8003
  4. J. H. Park, C. S. Hwang, and K. S. Bae, "Analysis of target classification performances of active sonar returns depending on parameter values of SVM kernel functions," Journal of the Korea Institute of Information and Communication Engineering, vol. 17, no. 5, pp. 1083-1088, 2013. https://doi.org/10.6109/jkiice.2013.17.5.1083
  5. UCI Machine Learning Repository: Connectionist Bench (Sonar, Mines vs. Rocks) Data Set [Internet]. Available: http://archive.ics.uci.edu/ml/datasets/connectionist+bench+(sonar,+mines+vs.+rocks)/.
  6. G. Baudat, F. Anouar, "Generalized Discriminant Analysis Using a Kernel Approach," Neural Computation, vol. 12, no. 10, pp. 2385-2404, Oct, 2000. https://doi.org/10.1162/089976600300014980
  7. Kernel Fisher discriminant analysis - Wikipedia [Internet]. Available: https://en.wikipedia.org/wiki/Kernel_Fisher_discriminant_analysis, edited on 22 Jan, 2017.
  8. http://www.kernel-machines.org/software.

Cited by

  1. 온실 내 환경데이터 분석을 통한 파프리카 온실의 식별 vol.30, pp.1, 2018, https://doi.org/10.12791/ksbec.2021.30.1.019