Multi-AI 모델 융합 기반 한반도 위협 실시간 분석 및 의사결정 지원 시스템 연구

오성일¹ ; 임양규²^{, *} ; 김동균³

1아이디비에스 한국지사장
2덕성여자대학교 가상현실융합학과 조교수
3몽고디비코리아 수석엔지니어

A Study on Real-time Threat Analysis and Decision Support System for the Korean Peninsula Based on Multi-AI Model Fusion

Sungil Oh¹ ; Yangkyu Lim²^{, *} ; Dongkyun Kim³

1Regional manager, IDBS Korea
2Assistant professor, Dept. of VR Convergence, Duksung Women’s University
3Principal Engineer, MongoDB Korea

Correspondence to: ^*Yangkyu Lim Dept. of VR Convergence, Duksung Women’s University 33, Samyang-ro 144-gil, Dobong-gu, Seoul, 01369, Republic of Korea Tel: +82-2-901-8717 E-mail: trumpetyk09@duksung.ac.kr

초록

한반도는 북한 핵·미사일, 중국 군사력 증강, 사이버 공격 등 다중 도메인 복합 안보 위협에 직면하고 있다. 기존 단일 영역 감시 시스템은 동시 발생 위협의 통합 분석과 신속 대응에 한계를 보여 새로운 접근법이 요구된다. 본 연구는 다중 AI 모델 융합 기반 실시간 위협 분석 시스템을 제안한다. 제안 시스템은 데이터 수집·전처리, AI 상황 분석, 의사결정 지원 계층으로 구성된 3계층 AI 아키텍처를 채택한다. GPT-5/Claude-4 Sonnet 기반 지능형 상황 분석 모듈로 4단계 위험도 분석과 시나리오별 대응 프로토콜을 제공한다. 실시간 민간 항공 데이터 성능 평가에서 KADIZ 경계 접근 탐지, 베이지안 행동 패턴 분류, 칼만 필터 예측 등 핵심 모듈의 우수한 성능을 확인하였고, 전체 시스템이 단일 모델 대비 향상된 성능을 검증하였다.

Abstract

The Korean Peninsula faces complex security threats including North Korea's nuclear/missile threats, China's military buildup, and cyber attacks. Existing single-domain surveillance systems show limitations in analyzing simultaneous threats and responding swiftly, requiring new approaches. This study proposes a real-time threat analysis system based on multi-AI model fusion. The system adopts three-layered architecture: data collection/preprocessing, AI situation analysis, and decision support layers. An intelligent situation analysis module using GPT-5/Claude-4 Sonnet analyzes four-level risk assessment and provides response protocols for scenarios. Performance evaluation using real-time civilian aviation data confirmed excellent performance of core modules including KADIZ boundary detection, Bayesian behavioral classification, and Kalman filter prediction, verifying improved system performance compared to single models.

Keywords:

Korean Peninsula Security, Threat Analysis, Real-time Analysis, Multi-AI Models, Decision Support

키워드:

한반도 안보, 위협 분석, 실시간 분석, 다중 AI 모델, 의사결정 지원

References

국방부, “국방백서 2022,” 2023.
Pollack, J. D., “North Korea's Nuclear Weapons: Implications for Regional Security and US Policy,” Brookings Institution, 2017.
Heginbotham, E., et al., “The U.S.-China Military Scorecard,” RAND Corporation, 2015.
NATO, “NATO's Multi-Domain Operations Concept,” Brussels: NATO Allied Command Transformation, 2020.
Allen, G., “Understanding AI Technology,” Center for a New American Security (CNAS), 2019.
Boyd, J. R., “A Discourse on Winning and Losing,” Air University, Maxwell AFB, 1987.
Boin, A., 't Hart, P., Stern, E., & Sundelius, B., “The Politics of Crisis Management: Public Leadership Under Pressure,” Cambridge University Press, 2016. [https://doi.org/10.1017/9781316339756]
Wu, Y., Yu, H., Du, J., Liu, B., & Yu, W., “An Aircraft Trajectory Prediction Method Based on Trajectory Clustering and a Spatiotemporal Feature Network,” Electronics, Vol. 11, No. 21, 3453, 2022. [https://doi.org/10.3390/electronics11213453]
Xu, X., Yang, R., & Fu, Y., “Situation Assessment for Air Combat Based on Novel Semi-supervised Naive Bayes,” Journal of Systems Engineering and Electronics, Vol. 29, No. 4, pp. 768-779, 2018. [https://doi.org/10.21629/JSEE.2018.04.11]
Kalman, R. E., “A New Approach to Linear Filtering and Prediction Problems,” Transactions of the ASME - Journal of Basic Engineering, Vol. 82, No. 1, pp. 35-45, 1960. [https://doi.org/10.1115/1.3662552]
Johansson, F., & Falkman, G., “A Bayesian network approach to threat evaluation with application to an air defense scenario,” Proceedings of the 11th International Conference on Information Fusion, 2008. [https://doi.org/10.1007/978-3-540-88269-5_11]
Breiman, L., “Random Forests,” Machine Learning, Vol. 45, No. 1, pp. 5-32, 2001. [https://doi.org/10.1023/A:1010933404324]
Strohmeier, M., Olive, X., Lübbe, J., Schäfer, M., & Lenders, V., “Crowdsourced air traffic data from the OpenSky Network 2019-2020,” Earth System Science Data, Vol. 13, No. 2, pp. 357-366, 2021. [https://doi.org/10.5194/essd-13-357-2021]
Strohmeier, M., Lenders, V., & Martinovic, I., “On the Security of the Automatic Dependent Surveillance-Broadcast Protocol,” IEEE Communications Surveys & Tutorials, Vol. 17, No. 2, pp. 1066-1087, 2015. [https://doi.org/10.1109/COMST.2014.2365951]
Wan, E. A., & van der Merwe, R., “The Unscented Kalman Filter for Nonlinear Estimation,” Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (AS-SPCC), pp. 153-158, 2000. [https://doi.org/10.1109/ASSPCC.2000.882463]
Salunkhe, T., Bobde, S. S., Wagh, K. P., et al., “Machine Learning-based Anomaly Detection and Prediction in Commercial Aircraft Using Autonomous Surveillance Data,” PLOS ONE, Vol. 19, No. 12, e0317914, 2024. [https://doi.org/10.1371/journal.pone.0317914]