한국정보처리학회:학술대회논문집 (Annual Conference of KIPS)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

해양 통신 시스템에서의 결측 데이터 문제와 진보된 데이터 대체 방법

Challenges of Missing Data in Maritime Communication Systems and Advanced Data Imputation Methods

  • 신하 쉬르티카 (국민대학교 금융정보보안학과) ;
  • 염선호 (국민대학교 금융정보보안학과) ;
  • 박수현 (국민대학교 컴퓨터공학과)
  • Shrutika Sinha (Dept. of Financial Information Security, Kookmin University) ;
  • Sun-Ho Yum (Dept. of Financial Information Security, Kookmin University) ;
  • Soo-Hyun Park (School of Computer Science, Kookmin University)
  • 발행 : 2024.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A robust and efficient communication network is crucial for ensuring the smooth operation, efficiency, and utmost safety of various maritime activities. Throughout the vast expanse of history, the highly significant maritime industry has heavily relied upon an extensive range of diverse communication methods. Accurate network performance is critical in maritime environments, where data loss due to signal interruptions, equipment failures, and other domain-specific factors frequently occur. This paper evaluates traditional and advanced data imputation techniques to assess their impact on the predictive accuracy of machine learning models used for network switching decisions in maritime settings. Results show that advanced deep learning techniques, like Autoencoder-based imputation can improve performance over traditional methods.

키워드

과제정보

이 논문은 2024 년도 해양경찰청 재원으로 해양수산과학기술진흥원의 지원을 받아 수행된 연구임(RS-2021-KS211488, 해양사고 신속대응 군집수색 자율수중로봇시스템 개발)

참고문헌

  1. A. Jain, H. Patel, L. Nagalapatti, N. Gupta, S. Mehta, S. C. Guttula, S. Mujumdar, S. Afzal, R. S. Mittal, and V. Munigala, "Overview and importance of data quality for machine learning tasks," Proc. 26th ACM SIGKDD Int. Conf. Knowledge Discovery Data Mining, 2020. doi: 10.1145/3394486.3406477.
  2. R. W. Liu, J. Nie, S. Garg, Z. Xiong, Y. Zhang, and M. S. Hossain, "Data-driven trajectory quality improvement for promoting intelligent vessel traffic services in 6G-enabled maritime IoT systems," IEEE Internet Things J., vol. 8, pp. 5374-5385, 2021. doi: 10.1109/JIOT.2020.3028743.
  3. Z. Peng, J. Wang, D. Wang, and Q. Han, "An overview of recent advances in coordinated control of multiple autonomous surface vehicles," IEEE Trans. Ind. Informat., vol. 17, pp. 732-745, 2021. doi: 10.1109/TII.2020.3004343.
  4. G. Wang, M. Ma, L. Jiang, F. Chen, and L. Xu, "Multiple imputation of maritime search and rescue data at multiple missing patterns," PLoS ONE, vol. 16, 2021. doi: 10.1371/journal.pone.0252129.
  5. Y.-y. Chen, Y. Lv, and F.-y. Wang, "Traffic flow imputation using parallel data and generative adversarial networks," IEEE Trans. Intell. Transp. Syst., vol. 21, pp. 1624-1630, 2020. doi: 10.1109/TITS.2019.2910295.
  6. K. Yau, A. R. Syed, W. Hashim, J. Qadir, C. Wu, and N. Hassan, "Maritime networking: Bringing internet to the sea," IEEE Access, vol. 7, pp. 48236-48255, 2019. doi: 10.1109/ACCESS.2019.2909921.
  7. S. Goksu and O. Arslan, "Quantitative analysis of dynamic risk factors for shipping operations," J. ETA Marit. Sci., vol. 8, no. 2, 2020. doi: 10.5505/jems.2020.63308.
  8. P. Bithas, E. T. Michailidis, N. Nomikos, D. Vouyioukas, and A. Kanatas, "A survey on machine-learning techniques for UAV-based communications," Sensors (Basel, Switzerland), vol. 19, 2019. doi: 10.3390/s19235170.
  9. S. Sinha, G. P. Reddy, and S.-H. Park, "Channel selection using machine learning," 2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Osaka, Japan, 2024, pp. 164-168. doi: 10.1109/ICAIIC60209.2024.10463321.
  10. G. P. Reddy, S. Sinha, and S.-H. Park, "Analysis of research trends in maritime communication," Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 6, 2024. doi: 10.14569/ijacsa.2024.0150670.
  11. S. Sinha, S. Y. Kwon, and S. H. Park, "A survey of deep/machine learning in maritime communications," 2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN), Paris, France, 2023, pp. 856-860. doi: 10.1109/ICUFN57995.2023.10199678.
  12. T. Bolton and L. Zanna, "Applications of deep learning to ocean data inference and subgrid parameterization," J. Adv. Model. Earth Syst., vol. 11, pp. 376-399, 2019. doi: 10.1029/2018MS001472.