Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of Line-shaped Echo Detection Method using Naive Bayesian Classifier

나이브 베이지안 분류기를 이용한 선에코 탐지 방법에 대한 연구

  • 이한수 (부산대학교 전자전기컴퓨터공학과) ;
  • 김성신 (부산대학교 전기공학과)
  • Received : 2014.03.09
  • Accepted : 2014.05.24
  • Published : 2014.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

There are many types of advanced devices for weather prediction process such as weather radar, satellite, radiosonde, and other weather observation devices. Among them, the weather radar is an essential device for weather forecasting because the radar has many advantages like wide observation area, high spatial and time resolution, and so on. In order to analyze the weather radar observation result, we should know the inside structure and data. Some non-precipitation echoes exist inside of the observed radar data. And these echoes affect decreased accuracy of weather forecasting. Therefore, this paper suggests a method that could remove line-shaped non-precipitation echo from raw radar data. The line-shaped echoes are distinguished from the raw radar data and extracted their own features. These extracted data pairs are used as learning data for naive bayesian classifier. After the learning process, the constructed naive bayesian classifier is applied to real case that includes not only line-shaped echo but also other precipitation echoes. From the experiments, we confirm that the conclusion that suggested naive bayesian classifier could distinguish line-shaped echo effectively.

기상 레이더, 인공위성, 라디오존데 등 날씨 예보를 수행하기 위해 많은 종류의 첨단 장비들이 사용되고 있다. 이들 중에서 지상에 설치된 기상 레이더는 넓은 탐지영역, 높은 시간 및 공간 분해능 등과 같은 많은 장점을 가지고 있기 때문에 기상예보 과정에서 필수적인 장비이다. 이러한 기상 레이더 데이터의 내부에는 기상현상 이외에도 여러 가지 외부 요인에 의해 발생하는 비기상현상이 관측되는데, 이는 기상 예보의 정확도를 감소시키는 원인이 된다. 본 논문에서는 기상 레이더 데이터를 이용한 연구를 통하여 비기상현상이 레이더에 관측되어 에코 형태로 나타난 것들 중에서 선 모양으로 발생하는 비기상에코를 제거하는 방법을 제안한다. 원시 레이더 데이터에서 선에코를 구분하여 그 특성을 추출한 후, 이들을 바탕으로 데이터 페어를 구성하여 나이브 베이지안 분류기를 학습시켰다. 그리고 학습된 나이브 베이지안 분류기를 선에코와 기상에 코가 혼재된 사례에 적용하였다. 실제 사례를 바탕으로 한 실험을 통해서 제안한 나이브 베이지안 분류기가 효과적으로 선에코를 식별할 수 있음을 확인하였다.

Keywords

References

  1. Hye-Young Han, Bok-Haeng Heo, Sung-Hwa Jung, GyuWon Lee, Cheol-Hwan You, Jong-Ho Lee, "Elimination of Chaff Echoes in Reflectivity Composite from an Operational Weather Radar Network using Infrared Satellite Data," Atmosphere. Korean Meteorological Society, vol. 21, no. 3, pp. 285-301, 2011.
  2. Lakshmanan Valliappa, Angela Fritz, Travis Smith, Kurt Hondl, Gregory Stumpf, "An Automated Technique to Quality Control Radar Reflectivity Data," Journal of Applied Meteorology and Climatology, vol. 46, pp. 288-305, 2007. https://doi.org/10.1175/JAM2460.1
  3. M. Steiner, J. Smith, "Use of three-dimensional reflectivity structure for automated detection and removal of non-precipitating echoes in radar data," Journal of Atmospheric and Oceanic Technology, vol. 19, pp. 673-686, 2002. https://doi.org/10.1175/1520-0426(2002)019<0673:UOTDRS>2.0.CO;2
  4. Zhou Jiao, Gao Yuchun, "A Study on Removal of Radial Interference Echo with Weather Radar," 2010 International Conference on Multimedia Technology, pp. 1-5, 2010.
  5. Hansoo Lee, Ji Chul Park, Jong Guen Kim, Sungshin Kim, "Line-shaped non-precipitation echo detection using fuzzy inference system," IFSA World Congress and NAFIPS Annual Meeting, pp. 1074-1079, 2013.
  6. N. Friedman, D. Geiger and M. Goldszmidt, "Bayesian network classifiers," Machine learning, vol. 29, no. 2-3, pp. 131-163, 1997. https://doi.org/10.1023/A:1007465528199
  7. N. Friedman, and M. Goldszmidt. "Building classifiers using Bayesian networks." Proceedings of the national conference on artificial intelligence. pp. 1277-1284, 1996.
  8. C. Y. Hong, J. H. Park, T. S. Yoon, and J. B. Park, "A study on the bayesian recurrent neural network for time series prediction," Journal of Control, Automation,and Systems Engineering (in Korean), vol. 10, no. 12,pp. 1295-1304, Dec. 2004. https://doi.org/10.5302/J.ICROS.2004.10.12.1295
  9. D. Heckerman, "Bayesian networks for data mining," Data Mining and Knowledge Discovery, vol. 1, no. 1, pp. 79-119, Mar. 1997. https://doi.org/10.1023/A:1009730122752
  10. R. E. Neapolitan, Learning Bayesian Networks, Pearson Prentice Hall, New Jersey, 2004.
  11. C.A. Ratanamahatana and D. Gunopulos, "Feature selection for the naive bayseian classifier using decision tree," Applied Artificial Intelligence, vol. 17, no. 5-6, pp. 475-487, 2003. https://doi.org/10.1080/713827175
  12. J. Chen, H. Huang, S. Tian, Y. Qu, "Feature selection for text classification with Naive Bayes," Expert Systems with Applications, vol. 36, no. 3, pp. 5432-5435, 2009. https://doi.org/10.1016/j.eswa.2008.06.054
  13. R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Machine learning: An artificial Intelligence Approach, vol. 2, Morgan Kaufmann, Portland, 1986.
  14. Keon Myung Lee, Won Jae Kim, Seok Jung Yun, "A Clinical Nomogram Construction Method Using Genetic Algorithm and Naive Bayesian Technique," Journal of The Korean Institute of Intelligent Systems, vol. 19, no. 6, pp. 796-801, 2009. https://doi.org/10.5391/JKIIS.2009.19.6.796
  15. Bomin Choi, Myung-Mook Han, "A Study of Threat Evaluation using Learning Bayesian Network on Air Defense," Journal of The Korean Institute of Intelligent Systems, vol. 22, no. 6, pp. 715-721, 2012. https://doi.org/10.5391/JKIIS.2012.22.6.715
  16. Song Ko, Daewon Kim, Bo-Yeong Kang, "A Matrix-Based Genetic Algorithm for Structure Learning of Bayesian Networks," International Journal of Fuzzy Logic and Intelligent Systems, vol. 11, no. 3, pp. 135-142, 2011. https://doi.org/10.5391/IJFIS.2011.11.3.135

Cited by

  1. Analysis and Detection Method for Line-shaped Echoes using Support Vector Machine vol.24, pp.6, 2014, https://doi.org/10.5391/JKIIS.2014.24.6.665
  2. A Study on Fuzzy Logic based Clustering Method for Radar Data Analysis vol.25, pp.3, 2015, https://doi.org/10.5391/JKIIS.2015.25.3.217