Journals / Politeknik Dergisi / 2002 / Cilt: 5 - Sayı: 2

Feature extraction method based on power spektrum of AR model and artificial neural network for target classification in the pulse radars

Darbeli radarlarda hedef sınıflama için AR modelinin güç spektrumu ve yapay sinir ağı temelli özellik çıkarma yöntemi

Pages
121–127
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In this way, an automatic and intelligent classification is realised.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, we present an efficient method for feature extraction, which is the most important stage of pattern recognition.
📊
Key Findings & Data:This method makes classification using 512 features obtained from power spectrum of AR models of measured pulse radar signals.
💡
Conclusion & Impact:In this way, an automatic and intelligent classification is realised.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

In this study, we present an efficient method for feature extraction, which is the most important stage of pattern recognition. We develop a new feature extraction procedure based on power spectrum of AR models and artificial neural network for target classification in the pulse radars. This method makes classification using 512 features obtained from power spectrum of AR models of measured pulse radar signals. Efficiency and reliability of the method is high because the features are obtained in the frequency domain and the number of the features is high. Structure of classification is set up based on artificial neural network of feed forward and the back propagation-learning algorithm. In this way, an automatic and intelligent classification is realised.

Özet

Bu çalışmada, örüntü tanımanın en önemli kısmı olan özellik çıkarma için geliştirilmiş etkili bir yöntem sunulmuştur. Darbeli radarlarda hedef sınıflama için AR modelinin güç spektrumu ve yapay sinir ağı temelli, yeni bir özellik çıkarma yöntemi geliştirilmiştir. Bu yöntemle ölçülen darbeli radar işaretlerinin AR modeli güç spektrumundan elde edilen 512 adet özellik kullanılarak sınıflama yapılmaktadır. Özelliklerin frekans bölgesinden elde edilmesi ve özellik sayısının fazla oluşu yöntemin güvenirliğini ve etkinliğini yükseltmektedir. Sınıflama yapısı ileri beslemeli ve geri yayınım öğrenme algoritmalı yapay sinir ağı üzerine kurulmuştur. Böylelikle akıllı ve otomatik bir sınıflama gerçekleşmesi sağlanmıştır.

🔖

Cite This Article

TÜRKOĞLU, İ., ARSLAN, A. (2002). Feature extraction method based on power spektrum of AR model and artificial neural network for target classification in the pulse radars. Politeknik Dergisi, Cilt: 5 - Sayı: 2, 121–127. https://ajindex.com/articles/307282

References (14)

  1. Ahern J., Delisle G. Y., etc. Radar, Lab-Volt Ltd., vol. I, Canada, 1989
  2. Madrid J.J. M., Corredera J. R. C, Vela G. M., A neural network approach to Dopplerbased target classification, Radar 92. International Conference, pp. 450-453, Brighton, England, 1992
  3. Swiatnicki Z., Semklo R., The artificial intelligence tools utilization in radar signal processing, 12th International Conference on Microwaves and Radar (MIKON '98), vol. 3, pp. 799 -803, Krakow, Poland, 1998
  4. Jakubiak A., Arabas J., Grabczak K., etc., Radar clutter classification using Kohonen neural network, Radar 97 (Conf. Publ. No.449), pp. 1-8-5 -188, Edinburgh, UK, 1997
  5. Tang B., Jiang W., Ke Y., Radar signal classification by projection onto wavelet packet subspaces, CIE International Conference of Radar Proceedings, pp. 124— 126, Beijing, China, 1996
  6. Beastall W. D., Recognition of radar signals by neural network, First IEE International Conference on Artificial Neural Networks, (Conf. Publ. No. 313), pp. 139-142, London, UK, 1989
  7. Application of pattern recognition techniques for early warning radar, Nasa Technical Reports, AD-A299735, Mar 29, 1995
  8. Guangyi C., Applications of wavelet transforms in pattern recognition and denoising, Concordia University (Canada), 1999
  9. Sowelam S.M., Tewfik A.H., Waveform selection in radar target classification, IEEE Transactions on Information Theory, vol. 46, pp. 1014-1029,2000 10. Kempen L.V., Sahli H., Nyssen E., etc., Signal processing and pattern recognition methods for radar AP mine detection and identification, Second International Conference on the Detection of Abandoned Land Mines, (Conf. Publ. No. 458), pp. 8 1 - 85, Edinburg, UK, 1998
  10. Noone G.P., A neural approach to automatic pulse repetition interval modulation recognition, Information Decision and Control, IDC 99 Proceedings, pp.213-218, Adelaide, Australia 1999
  11. Zyweck A., Bogner R.E., Radar target recognition using range profiles, IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-94., vol. 2, pp. 11/373 -11/376, Adelaide, Australia, 1994
  12. Roome S.J.,Classification of radar signals in modulation domain, Electronics Letters, vol. 28, pp.704-705, 1992
  13. Liu J., Gao S., Luo Z.Q., etc., The minimum description length criterion applied to emitter number detection and pulse classification, Statistical Signal and Array Processing, Proceedings., Ninth IEEE SP Workshop on, p. 172 -175, Portland, Oregon, Usa, 1998
  14. Richards