dPCA-HMM을 이용한 전투기 조종사 모델링 연구

국문 초록 (Abstract)

전투기 조종사 모델링은 국방 M&S(Modeling & Simulation)를 활용한 전쟁 모의 및 전투 실험의 기초 기술로 국방 M&S의 중요성이 대두됨에 따라 연구의 필요성이 높아지고 있다. 특히, 최근 전투 로그의 축적으로 통계적 학습 기법을 활용한 모델링의 적용이 가능해졌으며 전투 로그의 시계열적 특성을 반영할 수 있는 HMM(Hidden Markov Model)이 적합하다. 하지만 HMM은 이산형 혹은 연속형 중 한 형태의 변수만을 통해 학습되므로 이형 변수로 구성된 전투 로그에 적용을 위해서는 형변환 과정이 필요하다. 따라서 본 논문에서는 형변환을 위한 dPCA(Discrete Principal Component Analysis)와 HMM을 접목한 dPCA-HMM 기반 조종사 모델링 방법을 제안한다. 국방과학연구소 관급 시뮬레이터로부터 생성된 전투 로그를 이용한 비교 실험을 통해 제안하는 방법론의 성능을 평가하였으며, 만족스러운 성능을 나타내었다.

다국어 초록 (Multilingual Abstract)

Modeling of fighter pilots, which is a fundamental technology for war games using defense M&S (Modeling & Simulation) becomes one of the prominent research issues as the importance of defense M&S increases. Especially, the recent accumulation of combat logs makes it possible to adopt statistical learning methods to pilot modeling, and an HMM (Hidden Markov Model) which is able to utilize the sequential characteristic of combat logs is suitable for the modeling. However, since an HMM works only by using one type of features, discrete or continuous, to apply an HMM to heterogeneous features, type integration is required. Therefore, we propose a dPCA-HMM method, where dPCA (Discrete Principal Component Analysis) is combined with an HMM for the type integration. From experiments conducted on combat logs acquired from a simulator furnished by agency for defense development, the performance of the proposed model is evaluated and was satisfactory.

목차 (Table of Contents)

• ABSTRACT
• 초록
• Ⅰ. 서론
• Ⅱ. 본론
• Ⅲ. 실험
• IV. 결론
• References

참고문헌 (Reference)

1 장대수, "퍼지로직을 이용한 무인항공기의 충돌 회피" 한국항공우주학회 34 (34): 55-62, 2006

2 김지환, "소형 고정익기의 신호기반 조종면 고장진단 알고리즘" 한국항공우주학회 40 (40): 1040-1047, 2012

3 원대연, "다수 표적 탐지를 위한 Track-Before-Detect 알고리듬 연구" 한국항공우주학회 39 (39): 848-857, 2011

4 Jeong, S., "Required technology for implementing defense M&S" 20 (20): 35-41, 2014

5 Jolliffe, I., "Principal component analysis" John Wiley & Sons, Ltd 2005

6 Lowe, C. D., "Predicting pilot intent and aircraft trajectory in uncontrolled airspace" Massachusetts Institute of Technology 2014

7 Kiseleva, J., "Predicting Current User Intent with Contextual Markov Models" 391-398, 2013

8 Lai, C., "Performance analysis of speech recognition software" 2002

9 Schenk, J., "Novel VQ designs for discrete HMM on-line handwritten whiteboard note recognition" 5096 : 234-243, 2008

10 Baek, J., "Multi-Interval Discretization of Continuous Valued Attributes for Constructing Incremental Decision Tree" 27 (27): 394-, 2001

11 Mori, R., "Modeling of Pilot Landing Approach Control Using Stochastic Switched Linear Regression Model" 47 (47): 1554-1558, 2010

12 Dempster, A. P., "Maximum likelihood from incomplete data via the EM algorithm" 39 (39): 1-38, 1977

13 Quinlan, J. R., "Learning decision tree classifiers" 28 (28): 71-72, 1996

14 Andersson, M., "Improving situation awareness using aerial-mission recognition and temporal information" 2004

15 Choi, Y., "Hypo-vigilance Detection for UCAV Operators Based on a Hidden Markov Model" 2014

16 Trevo, K., "Human adaptive mechatronics methods for mobile working machines" 2010

17 Kim, E., "Human Activity Recognition and Pattern" 9 (9): 48-53, 2010

18 Hayashi, M., "Hidden Markov Models to identify pilot instrument scanning and attention patterns" 3 : 2889-2896, 2003

19 Filmer, D., "Estimating wealth effects without expenditure Data-Or tears: An application to educational enrollments in states of india" 38 (38): 115-132, 2001

20 Krzanowski, W. J., "Discrimination and classification using both binary and continuous variables" 70 (70): 782-790, 1975

21 Antwarg, L., "Attribute-Driven Hidden Markov Model Trees for Intention Prediction" 42 (42): 1103-1119, 2012

22 Rabiner, L., "A tutorial on hidden Markov models and selected applications in speech recognition" 77 (77): 257-286, 1989