한국빅데이터학회지 (The Journal of Bigdata)

  • 제8권2호
  • /
  • Pages.15-25
  • /
  • 2023
  • /
  • 2508-1829(pISSN)
  • /
  • 2713-6361(eISSN)
한국빅데이터학회 (Korea Bigdata Society)
권호 표지
DOI QR코드

DOI QR Code

온라인 시계열 자료를 위한 익스트림 러닝머신 적용의 최근 동향

Recent Trends in the Application of Extreme Learning Machines for Online Time Series Data

  • 윤여창 (우석대학교 정보보안학과)
  • 투고 : 2023.10.16
  • 심사 : 2023.12.06
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

익스트림 러닝머신은 다양한 방식의 예측 분야에서 주요 분석 방법을 제공하고 있다. 시계열 자료의 복잡한 패턴을 학습하고 잡음이 포함되어 있는 데이터이거나 비선형인 경우에도 최적의 학습을 통하여 정확한 예측을 할 수 있다. 이 연구에서는 온라인 시계열 자료를 분석하는 도구로서 주로 연구되고 있는 기계학습 모형들의 최근 동향들을 기존 알고리즘을 이용한 응용 특성들과 함께 제시한다. 지속적이고 폭발적으로 발생하는 대규모 온라인 데이터를 효율적으로 학습시키기 위해서는 다양하게 진화 가능한 속성에서도 잘 수행될 수 있는 학습 기술이 필요하다. 따라서 이 연구를 통하여 시계열 예측 분야에서 빅데이터가 적용되는 최신 기계 학습 모형에 대한 포괄적인 개요를 살펴보고, 빅데이터에 대한 기계 학습의 주요 과제 중 하나인 온라인 데이터를 학습하는 최신 모형들의 일반적인 특성과 온라인 시계열 자료를 얼마나 효율적으로 학습하고 예측에 활용할 수 있는지에 대하여 논의하고 그 대안을 제시한다.

Extreme learning machines (ELMs) are a major analytical method in various prediction fields. ELMs can accurately predict even if the data contains noise or is nonlinear by learning the complex patterns of time series data through optimal learning. This study presents the recent trends of machine learning models that are mainly studied as tools for analyzing online time series data, along with the application characteristics using existing algorithms. In order to efficiently learn large-scale online data that is continuously and explosively generated, it is necessary to have a learning technology that can perform well even in properties that can evolve in various ways. Therefore, this study examines a comprehensive overview of the latest machine learning models applied to big data in the field of time series prediction, discusses the general characteristics of the latest models that learn online data, which is one of the major challenges of machine learning for big data, and how efficiently they can learn and use online time series data for prediction, and proposes alternatives.

키워드

참고문헌

  1. Han M, Zhang R, Qiu T, Xu M and Ren W, "Multivariate Chaotic Time Series Prediction Based on Improved Grey Relational Analysis," IEEE Transactions on Systems, Man, and Cybernetics: Systems, pp. 1-11, 2017.
  2. O'Reilly C, Moessner K and Nati M, "Univariate and Multivariate Time Series Manifold Learning," Knowledge-Based Systems, 133, pp. 1-16, 2017. https://doi.org/10.1016/j.knosys.2017.05.026
  3. Wilson S, "Data representation for time series data mining: Time domain approaches," Wiley Interdisciplinary Reviews: Computational Statistics, 9(1), p. e1392, 2016.
  4. Gooijer JD and Hyndman R, "25 years of time series forecasting," International Journal of Forecasting, 22(3), pp. 443-473, 2006. https://doi.org/10.1016/j.ijforecast.2006.01.001
  5. Yi BK and Faloutsos C, "Fast Time Sequence Indexing for Arbitrary Lp Norms ," Proceedings of the VLDB, Cairo, Egypt, 2000.
  6. Lin J, Keogh E, Wei L and Lonardi S, "Experiencing SAX: A novel symbolic representation of time series," Data Mining and Knowledge Discovery, 15(2), 2007.
  7. Fayyad UM and Irani KB, "Multi-Interval Discretization of continuous-valued Attributes for Classification Learning," Proc. 13th Int'l Joint Conference of Artificial Intelligence, pp.1022-1027, 1993.
  8. George K and Mutalik P, "A Multiple Model Approach to Time-Series Prediction Using an Online Sequential Learning Algorithm," IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(5), pp. 1-15, 2019. https://doi.org/10.1109/TSMC.2017.2712184
  9. Rosenblatt F, "The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain," Psychological Review, 65(6), pp. 386-408, 1958. https://doi.org/10.1037/h0042519
  10. Huang G, Zhu Q and Siew C, "Extreme learning machine: A new learning scheme of feedforward neural networks," IEEE International Joint Conference on Neural Networks, 2004.
  11. Tang J, Deng C and Huang G, Extreme Learning Machine for Multilayer Perceptron, IEEE Transactions on Neural Networks and Learning Systems, 27(4), 2016.
  12. Kuo J, Principle J and Vries BD, "Prediction of chaotic time series using recurrent neural networks," Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop, 1992.
  13. Li Q and Lin RC, "new approach for chaotic time series prediction using recurrent neural network," Mathematical Problems in Engineering, 2016.
  14. Qinghai L, Lin RH, "A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network," Mathematical Problems in Engineering, 2016.
  15. Ho S, Xie M and Goh T, "A comparative study of neural network and Box-Jenkins ARIMA modeling in time series," Computers & Industrial Engineering, 42(2-4), pp. 371-375, 2002. https://doi.org/10.1016/S0360-8352(02)00036-0
  16. Gers F, Eck D and Schmidhuber J, "Applying LSTM to Time Series Predictable Through Time-Window Approaches," Perspectives in Neural Computing, pp. 193-200, 2002.
  17. Hou X, Wang K, Zhang J and Wei Z, "An Enriched Time-Series Forecasting Framework for Long-Short Portfolio Strategy," IEEE Access, 8, 2020.
  18. Markowska-Kaczmar U and Kosturek M, "Extreme learning machine versus classical feedforward network," Neural Computing & Applications, 33(22), pp. 15121-15144, 2021. https://doi.org/10.1007/s00521-021-06402-y
  19. Huang G, Wang D and Lan Y, "Extreme learning machines: A survey," International Journal of Machine Learning and Cybernetics, 2(2), pp. 107-122, 2011. https://doi.org/10.1007/s13042-011-0019-y
  20. Ahmad I, Basheri M, Iqbal M and Rahim A, "Performance Comparison of Support Vector Machine, Random Forest, and Extreme Learning Machine for Intrusion Detection," IEEE Access, 6, 2018.
  21. Wang Z, Li M, Wang H, Jiang H, Yao Y, Zhang H, Xin J, "Breast Cancer Detection Using Extreme Learning Machine Based on Feature Fusion with CNN Deep Features," IEEE Access, 7, 2019.
  22. Smith M, Neural Networks for Statistical Modeling, Van Nostrand Reinhold, 1996.
  23. Bharath, YK, Griffiths' Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks, Automatic Control and Computer Sciences; New York, 56(2), pp. 160-165, 2022. https://doi.org/10.3103/S0146411622020031
  24. Rajendra V and Motupalli R, "Analys is on the Estimators to the OSELM Model," 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2022.
  25. Chang HD, Wang XJ, Gu J, Wang W, "A Review of Online Sequential Extreme Learning Machines," Journal of Physics: Conference Series, 1302(3), 2019.
  26. Sun Z, Au K and Choi T, "A Neuro-Fuzzy Inference System Through Integration of Fuzzy Logic and Extreme Learning Machines," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 37(5), 2007.
  27. Zhou X, Liu Z and Zhu C, "Online Regularized and Kernelized Extreme Learning Machines with Forgetting Mechanism," Mathematical Problems in Engineering, 2014.
  28. Li R, Zhang H, Wu Z, Li R, "Transient Electromagnetic Inversion: An ICDE-Trained Kernel Principal Component OSELM Approach," IEEE Transactions on Geoscience and Remote Sensing. 60, pp.1-14, 2022. https://doi.org/10.1109/TGRS.2021.3112192
  29. George K, Mutalik P, "A Multiple Model Approach to Time-Series Prediction Using an Online Sequential Learning Algorithm," IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(5), 2019.
  30. Scardapane S, Comminiello D, Scarpiniti M and Uncini A, "Online Sequential Extreme Learning Machine With Kernels," IEEE Transactions on Neural Networks and Learning Systems, 26(9), pp. 2214-2220, 2015. https://doi.org/10.1109/TNNLS.2014.2382094
  31. Lu J, Huang J and Lu F, "Time Series Prediction Based on Adaptive Weight Online Sequential Extreme Learning Machine," Applied Sciences, 7(3), 2017.
  32. Atsawaraungsuk S, Boonphairote W, Somsuk K, Suwannapong C, Khummanee S, "A progressive learning for structural tolerance online sequential extreme learning machine," TELKOMNIKA Telecommunication Computing Electronics and Control, 21(5), pp. 1039-1050, 2023.
  33. Matias T, Souza F, Araujo R, Goncalves N and Barreto J, "On-line sequential extreme learning machine based on recursive partial least squares," Journal of Process Control, 27, pp. 15-21, 2015. https://doi.org/10.1016/j.jprocont.2015.01.004
  34. Rong HJ, Huang GB, Sundararajan N and Saratchandran P, "Online Sequential Fuzzy Extreme Learning Machine for Function Approximation and Classification Problems, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(4), pp. 1067-1072, 2009. https://doi.org/10.1109/TSMCB.2008.2010506
  35. Chai W, Zheng Y, Lin, T, Qin J, Zhou T, "GAKELM: Genetic Algorithm Improved Kernel Extreme Learning Machine for Traffic Flow Forecasting," Mathematics, 11(16), 2023.
  36. Kale AP, Sonawane S, Wahul RM, Dudhedia MA, "Improved Genetic Optimized Feature Selection for Online Sequential Extreme Learning Machine, Ingenierie des Systemes d'Information," 27(5), pp. 843-848, 2022. https://doi.org/10.18280/isi.270519