Research Article
BibTex RIS Cite

A Comparative Study of Artificial Neural Networks and Naïve Bayes Techniques for the Classification of Radar Targets

Year 2020, Volume: 9 Issue: 4, 1779 - 1788, 25.12.2020
https://doi.org/10.17798/bitlisfen.676973

Abstract

The classification of radar targets is one of the most important study topics, especially in the defense and automotive industries. However, in most of the studies in the literature, raw radar signals are used. Raw radar signals may be subject to ambient noise and signal modulation effects. This may make it difficult to classify radar targets. In this study, instead of using raw data, Fourier-based features extracted from Radar Cross-sectional Area have been used. These extracted features are then input to two types of classifiers, ie, Naive Bayes (NB) and Artificial Neural Networks (ANN) for the classification of radar targets. In addition, both classifiers were trained with different algorithms and their performances were compared. In the ANN-based classifiers, the best accuracy was found that 96.69% with using Bayesian regularization and back propagation training function. On the other hand, the best accuracy with the NB classifier was achieved at 93.95% using Epanechnikov Kernel Distribution. The result presented here demonstrates that Fourier transform based feature extraction can be used effectively in radar target classification applications.

References

  • World Health Organization. 2018. Global Status Report on Road Safety. https://www.who.int/violence_injury_prevention/road_safety_status/2018/en. (Accessed: 21.09.2019).
  • Capobianco S., Facheris L., Cuccoli F., Marinai S. 2017. Vehicle Classification Based on Convolutional Networks Applied to FMCW Radar Signals, 1st European Conference on Traffic Minning Application to Police Activities, 25-26 October, Rome, Italy.
  • Choi Y., Choi I., Chae D. 2018. Decision-Level Fusion Scheme of SVM and Naive Bayes Classifier for Radar Target Recognition, 2018 International Symposium on Antennas and Propagation, 23-26 October, Busan, South Korea.
  • Nanzer J.A., Rogers R.L. 2009. Bayesian Classification of Humans and Vehicles Using Micro-Doppler Signals from a Scanning-Beam Radar, IEEE Microwave and Wireless Components Letters, 19 (5): 338 -340.
  • Severino J.V.B., Zimmer A., Brandmeier T., Freire R.Z. 2019. Pedestrian Recognition Using Micro Doppler Effects of Radar Signals Based on Machine learning and Multi-objective Optimization, Expert Systems with Applications, 136 (1): 304-315.
  • Kim B.K., Kang H.S., Park S.O. 2016. Drone Classification Using Convolutional Neural Networks with Merged Doppler Images, IEEE Geoscience and Remote Sensing Letters, 14 (1): 38-42.
  • Zaied S., Toumi A., Khenchaf A. 2018. Target Classification Using Convolutional Deep Learning and Auto-encoder Models, 4th International Conference on Advance Technologies for Signal and Image Processing, 21-24 March, Sousse, Tunisia.
  • Zhou Y., Wang H., Xu F., Jin Y. 2016. Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks, IEEE Geoscience and Remote Sensing Letters, 13 (12): 1935-1939.
  • Kouemou G., Opitz F. 2007. Hidden Markov Models in Radar Target Classification, 2007 IET International Conference on Radar Systems, 15-18 October, Edinburgh, UK.
  • Leung H., Wu J. 2000. Bayesian and Dempster-Shafer Target Identification for Radar Surveillance, IEEE Transactions on Aerospace and Electronic Systems, 36 (2): 432-447.
  • Haykin S.S. 2009. Neural Networks and Learning Machines, 3rd ed., Prentice Hall, 936s. New York.
  • Moller M.F. 1993. A Scaled Conjugate Gradient Algorithm for Fast Supervising Learning, Neural Networks, 6 (4): 525-533.
  • Hagan M.T., Menhaj M.B. 1994. Training Feed-Forward Networks with the Marquardt Algorithm, IEEE Transactions on Neural Networks, 5 (6): 989-993.
  • Foresee F.D., Hagan M.T. 1997. Gauss-Newton Approximation to Bayesian Learning, International Conference on Neural Networks, 12 June, Houston, USA.
  • Papoulis A. 1991. Probability Random Variables and Stochastic Processes, 3rd ed., McGraw-Hill, 678s. New York.
  • John G.H., Langley P. 1995. Estimating Continuous Distributions in Bayesian Classifiers, 11th Conference on Uncertainty in Artificial Intelligence, 18-20 August, Montreal, Canada.
  • IEEE Aerospace and Electronic Systems Society. 2017. IEEE Standard for Radar Definitions. https://ieeexplore.ieee.org/document/8048479. (Accessed: 25.09.2019).
  • Knott E.F. 2012. Radar Cross Section Measurements, Springer Science and Business Media, 564s. New York.
  • Mahafza B.R. 2013. Radar Systems Analysis and Design Using Matlab. CRC Press, 772s. Florida.

A Comparative Study of Artificial Neural Networks and Naïve Bayes Techniques for the Classification of Radar Targets

Year 2020, Volume: 9 Issue: 4, 1779 - 1788, 25.12.2020
https://doi.org/10.17798/bitlisfen.676973

Abstract

Radar hedeflerinin sınıflandırılması, özellikle savunma ve otomotiv endüstrilerinde en önemli çalışma konulardan biridir. Ancak, literatürdeki çalışmaların çoğunda ham radar sinyalleri kullanılmaktadır. Ham radar sinyalleri ortamdan kaynaklı Gürültü ve sinyal modülasyon etkilerine maruz kalabilmektedir. Bu durum radar hedeflerinin sınıflandırılmasını zorlaştırabilir. Bu çalışmada, ham veri kullanmak yerine, Radar Kesit Alanından çıkarılan Fourier tabanlı özellikler kullanılmıştır. Bu çıkarılan özellikler daha sonra radar hedeflerinin sınıflandırılması için iki tür sınıflandırıcıya, yani Naive Bayes (NB) ve Yapay Sinir Ağlarına (YSA) girdi olarak verilmiştir. Ayrıca, her iki sınıflandırıcı farklı algoritmalar ile eğitilmiş ve performansları karşılaştırılmıştır. YSA tabanlı sınıflandırıcıda, en iyi doğruluk, Bayesian regülarizasyon ve geri yayılma eğitim fonksiyonu kullanılarak 96.69% olarak bulunmuştur. Diğer taraftan, NB sınıflandırıcı ile en iyi doğruluk Epanechnikov çekirdek dağılımı kullanılarak 93.95% olarak elde edilmiştir. Burada sunulan sonuç, Fourier dönüşüm temelli öznitelik çıkarımının radar hedef sınıflandırma uygulamalarında etkili bir şekilde kullanılabileceğini göstermektedir.

References

  • World Health Organization. 2018. Global Status Report on Road Safety. https://www.who.int/violence_injury_prevention/road_safety_status/2018/en. (Accessed: 21.09.2019).
  • Capobianco S., Facheris L., Cuccoli F., Marinai S. 2017. Vehicle Classification Based on Convolutional Networks Applied to FMCW Radar Signals, 1st European Conference on Traffic Minning Application to Police Activities, 25-26 October, Rome, Italy.
  • Choi Y., Choi I., Chae D. 2018. Decision-Level Fusion Scheme of SVM and Naive Bayes Classifier for Radar Target Recognition, 2018 International Symposium on Antennas and Propagation, 23-26 October, Busan, South Korea.
  • Nanzer J.A., Rogers R.L. 2009. Bayesian Classification of Humans and Vehicles Using Micro-Doppler Signals from a Scanning-Beam Radar, IEEE Microwave and Wireless Components Letters, 19 (5): 338 -340.
  • Severino J.V.B., Zimmer A., Brandmeier T., Freire R.Z. 2019. Pedestrian Recognition Using Micro Doppler Effects of Radar Signals Based on Machine learning and Multi-objective Optimization, Expert Systems with Applications, 136 (1): 304-315.
  • Kim B.K., Kang H.S., Park S.O. 2016. Drone Classification Using Convolutional Neural Networks with Merged Doppler Images, IEEE Geoscience and Remote Sensing Letters, 14 (1): 38-42.
  • Zaied S., Toumi A., Khenchaf A. 2018. Target Classification Using Convolutional Deep Learning and Auto-encoder Models, 4th International Conference on Advance Technologies for Signal and Image Processing, 21-24 March, Sousse, Tunisia.
  • Zhou Y., Wang H., Xu F., Jin Y. 2016. Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks, IEEE Geoscience and Remote Sensing Letters, 13 (12): 1935-1939.
  • Kouemou G., Opitz F. 2007. Hidden Markov Models in Radar Target Classification, 2007 IET International Conference on Radar Systems, 15-18 October, Edinburgh, UK.
  • Leung H., Wu J. 2000. Bayesian and Dempster-Shafer Target Identification for Radar Surveillance, IEEE Transactions on Aerospace and Electronic Systems, 36 (2): 432-447.
  • Haykin S.S. 2009. Neural Networks and Learning Machines, 3rd ed., Prentice Hall, 936s. New York.
  • Moller M.F. 1993. A Scaled Conjugate Gradient Algorithm for Fast Supervising Learning, Neural Networks, 6 (4): 525-533.
  • Hagan M.T., Menhaj M.B. 1994. Training Feed-Forward Networks with the Marquardt Algorithm, IEEE Transactions on Neural Networks, 5 (6): 989-993.
  • Foresee F.D., Hagan M.T. 1997. Gauss-Newton Approximation to Bayesian Learning, International Conference on Neural Networks, 12 June, Houston, USA.
  • Papoulis A. 1991. Probability Random Variables and Stochastic Processes, 3rd ed., McGraw-Hill, 678s. New York.
  • John G.H., Langley P. 1995. Estimating Continuous Distributions in Bayesian Classifiers, 11th Conference on Uncertainty in Artificial Intelligence, 18-20 August, Montreal, Canada.
  • IEEE Aerospace and Electronic Systems Society. 2017. IEEE Standard for Radar Definitions. https://ieeexplore.ieee.org/document/8048479. (Accessed: 25.09.2019).
  • Knott E.F. 2012. Radar Cross Section Measurements, Springer Science and Business Media, 564s. New York.
  • Mahafza B.R. 2013. Radar Systems Analysis and Design Using Matlab. CRC Press, 772s. Florida.
There are 19 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Araştırma Makalesi
Authors

Doğan Tunca Arık 0000-0002-2636-3016

Ömer Karal 0000-0001-8742-8189

Asaf Behzat Şahin 0000-0001-9759-8448

Publication Date December 25, 2020
Submission Date January 18, 2020
Acceptance Date September 27, 2020
Published in Issue Year 2020 Volume: 9 Issue: 4

Cite

IEEE D. T. Arık, Ö. Karal, and A. B. Şahin, “A Comparative Study of Artificial Neural Networks and Naïve Bayes Techniques for the Classification of Radar Targets”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 9, no. 4, pp. 1779–1788, 2020, doi: 10.17798/bitlisfen.676973.

Bitlis Eren University
Journal of Science Editor
Bitlis Eren University Graduate Institute
Bes Minare Mah. Ahmet Eren Bulvari, Merkez Kampus, 13000 BITLIS