Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Methodology for Air Target Dynamic Targeting Applying Machine Learning

기계학습을 활용한 항공표적 긴급표적처리 발전방안 연구

  • Kang, Junghyun (Department of Industrial Engineering, Hannam University) ;
  • Yim, Dongsoon (Department of Industrial Engineering, Hannam University) ;
  • Choi, Bongwan (Department of Industrial Engineering, Hannam University)
  • Received : 2019.03.29
  • Accepted : 2019.06.07
  • Published : 2019.08.05
Download PDF
⟨ Previous Next ⟩

Abstract

In order to prepare for the future warfare environment, which requires a faster operational tempo, it is necessary to utilize the fourth industrial revolution technology in the field of military operations. This study propose a methodology, 'machine learning based dynamic targeting', which can contribute to reduce required man-hour for dynamic targeting. Specifically, a decision tree algorithm is considered to apply to dynamic targeting process. The algorithm learns target prioritization patterns from JIPTL(Joint Integrated Prioritized Target List) which is the result of the deliberate targeting, and then learned algorithm rapidly(almost real-time) determines priorities for new targets that occur during ATO(Air Tasking Order) execution. An experiment is performed with artificially generated data to demonstrate the applicability of the methodology.

Keywords

GSGGBW_2019_v22n4_555_f0001.png 이미지

Fig. 1. Air tasking cycle

GSGGBW_2019_v22n4_555_f0002.png 이미지

Fig. 2. Joint targeting cycle

GSGGBW_2019_v22n4_555_f0003.png 이미지

Fig. 3. Target process in phase 5

GSGGBW_2019_v22n4_555_f0004.png 이미지

Fig. 4. Machine learning based dynamic targeting

GSGGBW_2019_v22n4_555_f0005.png 이미지

Fig. 5. Experiment flow chart

GSGGBW_2019_v22n4_555_f0006.png 이미지

Fig. 6. Example of survey data

GSGGBW_2019_v22n4_555_f0007.png 이미지

Fig. 7. Learned decision tree

Table 1. Multiple ATO cycle man-hour

GSGGBW_2019_v22n4_555_t0001.png 이미지

Table 2. Data attributes of JIPTL

GSGGBW_2019_v22n4_555_t0002.png 이미지

Table 3. Target category, count, ratio of the gulf war

GSGGBW_2019_v22n4_555_t0003.png 이미지

Table 4. Target priority class

GSGGBW_2019_v22n4_555_t0004.png 이미지

Table 5. Daily strikes by AIF categories

GSGGBW_2019_v22n4_555_t0005.png 이미지

Table 6. Data pre-processing method

GSGGBW_2019_v22n4_555_t0006.png 이미지

Table 7. Pre-processing of experimental dataset

GSGGBW_2019_v22n4_555_t0007.png 이미지

Table 8. Form of pre-processed data

GSGGBW_2019_v22n4_555_t0008.png 이미지

Table 9. Terminal nodes

GSGGBW_2019_v22n4_555_t0009.png 이미지

Table 11. Result of the performance test(confusion matrix and statistics)

GSGGBW_2019_v22n4_555_t0010.png 이미지

Table 10. Decision nodes and p-value

GSGGBW_2019_v22n4_555_t0011.png 이미지

References

  1. E. A. Cohen, et. al., "Volume I Planning and Command and Control, Gulf War Air Power Survey," Washington, D. C., 1993.
  2. E. A. Cohen, et. al., "Volume V A Statistical Compendium and Chronology, Gulf War Air Power Survey," Washington, D. C., 1993.
  3. J. A. Winnefeld, P. Niblack, D. J. Johnson, "A League of Airmen U.S. Air Power in the Gulf War," Santa Monica, CA: RAND, 1994.
  4. U.S. Joint Chiefs of Staff, "DOD Dictionaty of Military and Associated Terms," 2018.
  5. U.S. Joint Chiefs of Staff, "Joint Publication 3-60 Joint Targeting," 2013.
  6. Y. Park, et. al., "Introduction to Military Suidies," Seoul: Planet Media, pp. 129-187, 2014.
  7. B. J. Zacherl, "Weapon-Target Pairing; Revising an Air Tasking Order in Real-Time," Unpublished Master's Thesis, CA: Naval Postgraduate School, 2006.
  8. D. Aberdeen, O. Pacovsky and A. Slater, "The Learning Behind Gmail Priority Inbox," LCCC: NIPS 2010 Workshop on Learning on Cores, Clusters and Clouds, 2010.
  9. J. Kang, D. Yim and B. Choi, “A Study on the Application of Machine Learning Algorithms to Dynamic Targeting of Real-Time Air Targets,” Journal of Military Science and Technology Studies, Vol. 11, No. 2, pp. 21-30, 2018.
  10. K. Conner, P. Lambertson and M. Roberson, "Analyzing the Air Operations Center(AOC) Air Tasking Order(ATO) Process Using Theory of Constraints(TOC)," Unpublished Master's Thesis, Air Force Institute of Technology, 2005.
  11. O. A. S. Ibrahim and D. Landa-Silva, "ES-Rank: Evolution Strategy Learning to Rank Approach," SAC 2017 Proceedings of the Symposium on Applied Computing, pp. 944-950, 2017.
  12. S. D. MacArthur, C. E. Brodley and C. Shyu, "Relevance Feedback Decision Trees in Content- Based Image Retrieval," Proceedings of the IEEE Workshop on Content-Based Access of Image and Video Libraries, 2000.
  13. T. Liu, “Learning to Rank for Information Retrieval,” Foundations and Trends in Information Retrieval, Vol. 3, No. 3, pp. 225-331, 2009. https://doi.org/10.1561/1500000016
  14. T. Hothorn, K. Hornik and A. Zeileis, "Ctree: Conditional Inference Trees," The Comprehensive R Archive Network, pp. 1-35, 2015.
  15. Wikipedia, "Decision Tree Learning," 2018, https://en.wikipedia.org/wiki/Decision_tree_learning(accessed Nov 11, 2018).
  16. Office of Geomatics: Coordinate Systems Analysis, "Global Area Reference System(GARS)," 2018, http://earth-info.nga.mil/GandG/coordsys/grids/gars.html (accessed Nov 11, 2018).
  17. Wikipedia, "Machine Learning," 2018, https://en.wikipedia.org/wiki/Machine_learning(accessed Nov 11, 2018).