FSR MARINE TARGET CLASSIFICATION WITH DATA MINING APPROACH

Dorina Kabakchieva, Hristo Kabakchiev, Vera Behar, Ivan Garvanov

2013

Abstract

The purpose of this paper is to present the research results from a study focused on the possibilities for implementing data mining approach for classification of radar detected marine targets. The study is based on experimental data collected by researchers from Birmingham University with Bistatic Forward Scattering Radar. The data is further processed by using a CA CFAR approach for radar detection and target specific estimation, proposed by Sofia University team. Rough estimation of the target parameters in time domain in implemented, based on the hypothesis that the number of detected samples received from the target defines the target projection (length) and the energy reflected from the target. The classification models for predicting the class of the detected marine targets, achieved with selected algorithms in data mining software WEKA, for two values of the predicted variable (the marine target class), are described in the paper. The results from the evaluation of the models are compared with the results received in our previous paper, concerning classifiers achieved for predicted target variable with three values. The proposed hypothesis that the decreased number of values for the predicted variable will lead to achieving classifiers with better quality is validated.

References

  1. Chapman, P., et al. (2000). CRISP-DM 1.0: Step-by-step data mining guide. 2000 SPSS Inc. CRISPWP-0800. Available at: http://www.crisp-dm.org/CRISPWP0800.pdf.
  2. Cherniakov, M, Gashinova, M, Cheng, H, Antoniou, M, Sizov, V, Daniel, L.Y. (2007). Ultra wideband forward scattering radar: Concept and prospective. Proceedings of Int. Conf. Radar 2007, 1-5, (2007).
  3. Cherniakov, M., Raja Abdullah, R.S.A., Jancovic, P., Salous, M. (2005). Forward Scattering Micro Sensor for Vehicle Classification. Proceedings of the IEEE International Radar Conference, Washington DC, US, pp. 184-189, 2005.
  4. Galati, G. (edit.), 1993. Advanced radar techniques and systems, IEE Radar, Sonar, Navigation and Avionics Series 4, Peter Peregrinus Ltd.
  5. Ibrahim, N.K.,. Raja Abdullah, R.S.A, Saripan, M.I. (2009). Artificial Neural Network Approach in Radar Target Classification. Journal of Computer Science 5 (1): pp.23-32, 2009, ISSN 1549-3636.
  6. Kabakchiev, C., Garvanov, I., Cherniakov, M., Gashinova, M., Behar, V., Kabakchiev, A., 2011. CFAR Detection and Paramiter Estimation of Moving Marine Targets using Forward Scattering Radar, Proc. of Int. Radar Simp. IRS'11, Leipzig, Germany, (2011).
  7. Kabakchiev, C., Garvanov, I., Cherniakov, M., Gashinova, M., Kabakchiev, A., Kiovtorov, V., Vladimirova, M., Daskalov,P, 2011. CFAR BI Detector for Mariner Targets in Time Domain for Bistatic Forward Scattering Radar, Pros. of Int. SPS-2011, Jachranka, Poland, 2011.
  8. Kabakchiev, H., Kabakchieva, D., Cherniakov, M., Gashinova, M., Behar, V., Garvanov, I., 2011. Maritime Target Detection, Estimation and Classification in Bistatic Ultra Wideband Forward Scattering Radar. Conference Proceedings of the International Radar Symposium (IRS 2011), 7-9 September 2011, Leipzig, Germany, pp.79-84.
  9. Kabakchieva, D. (2013). Study of Data Mining Classification Models. PhD. Thesis, Institute of Information and Communication Technologies (IICT), Bulgarian Academy of Sciences (BAS), 2013. Available at: http://www.iict.bas.bg/konkursi/2013/D_Kabakchieva/ Dorina%20Kabakchieva%20avtoreferat.pdf
  10. Raja Syamsul Azmir Bin Raja Abdulla (2005). Forward Scattering Radar for Vehicle Classification. PhD Thesis, July 2005, The University of Birmingham, UK.
  11. Rashid, N, Antoniou, M, Jancovic, P, Sizov, V, Abdullah, R, Cherniakov, M, 2008. Automatic Target Classification in a Low Frequency FSR Network, Proc. of EuRAD conf. 2008, pp. 68-71.
  12. Witten, I., Frank, E., 2005. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Publishers, Elsevier Inc.
Download


Paper Citation


in Harvard Style

Kabakchieva D., Kabakchiev H., Behar V. and Garvanov I. (2013). FSR MARINE TARGET CLASSIFICATION WITH DATA MINING APPROACH . In Proceedings of the Second International Conference on Telecommunications and Remote Sensing - Volume 1: ICTRS, ISBN 978-989-8565-57-0, pages 145-152. DOI: 10.5220/0004786501450152


in Bibtex Style

@conference{ictrs13,
author={Dorina Kabakchieva and Hristo Kabakchiev and Vera Behar and Ivan Garvanov},
title={FSR MARINE TARGET CLASSIFICATION WITH DATA MINING APPROACH},
booktitle={Proceedings of the Second International Conference on Telecommunications and Remote Sensing - Volume 1: ICTRS,},
year={2013},
pages={145-152},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004786501450152},
isbn={978-989-8565-57-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Telecommunications and Remote Sensing - Volume 1: ICTRS,
TI - FSR MARINE TARGET CLASSIFICATION WITH DATA MINING APPROACH
SN - 978-989-8565-57-0
AU - Kabakchieva D.
AU - Kabakchiev H.
AU - Behar V.
AU - Garvanov I.
PY - 2013
SP - 145
EP - 152
DO - 10.5220/0004786501450152