Satellite time series data classification method based on trend symbolic aggregation approximation

被引：0
作者：
Ruan H. [1 ]
Liu L. [2 ]
Hu X. [1 ]
机构：
[1] School of Automation Science and Electrical Engineering, Beihang University, Beijing
[2] Beijing Electro-Mechanical Engineering Institute, Beijing
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2021年 / 47卷 / 02期
基金：
中国国家自然科学基金;
关键词：
Anomaly detection; Satellite telemetry data; Symbolic representation; Time series; Time series classification;
D O I：
10.13700/j.bh.1001-5965.2020.0332
中图分类号：
学科分类号：
摘要：
As the main symbolic representation method widely used in time series data mining, the Symbolic Aggregation Approximation (SAX) uses the mean value of segments as the symbolic representation. Since it is impossible to distinguish different time series that have different trends but the same mean value, it may lead to incorrect classification. This paper presents an improved symbol representation-Trend Symbol Aggregation Approximation (TrSAX), which integrates SAX and least squares method to describe the mean and slope value of the time series, and constructs the BOTS classifier. In addition, this paper analyzes the angle sequence, rotation speed sequence, and current sequence in the satellite analog telemetry time series data, and selects three datasets similar to these three sequences from the UCR public dataset for classification experiment verification. They are compared with the 1-NN classification methods using SAX, two improved SAX, classic Euclidean Distance (ED) and Dynamic Time Warping (DTW). The results show that the classification error rate of the proposed BOTS classification method is significantly lower than the other five classification methods. © 2021, Editorial Board of JBUAA. All right reserved.
引用
收藏
页码：333 / 341
页数：8
相关论文
共 21 条
  • [1] YANG H M, PAN Z S, BAI W., Review of time series prediction methods, Computer Science, 46, 1, pp. 21-28, (2019)
  • [2] SHI X T, PANG J Y, ZHANG X, Et al., Satellite big data analysis based on bagging extreme learning machine, Chinese Journal of Scientific Instrument, 39, 12, pp. 81-91, (2018)
  • [3] PENG X Y, PANG J Y, PENG Y, Et al., Review on anomaly detection of spacecraft telemetry data, Chinese Journal of Scientific Instrument, 37, 9, pp. 1929-1945, (2016)
  • [4] YANG T, CHEN B, GAO Y, Et al., Data mining-based fault detection and prediction methods for in-orbit satellite, IEEE International Conference on Measurement, Information and Control, pp. 805-808, (2013)
  • [5] ZHAO G, LI Y J., Spacecraft fault diagnosis method based on time series data mining, Journal of Spacecraft TT & C Technology, 29, 3, pp. 1-5, (2010)
  • [6] BAO J P, YANG K, ZHOU J., Node level parallel and optimization method of satellite time serial data mining, Journal of Beijing University of Aeronautics and Astronautics, 44, 12, pp. 2470-2478, (2018)
  • [7] ZHANG G, ZHAI J W, YANG H F., Research on telemetry data tendency prognosis for navigation satellite, Spacecraft Engineering, 3, 3, pp. 74-81, (2017)
  • [8] WAN Y, SI Y W., A hidden semi-Markov model for chart pattern matching in financial time series, Soft Computing, 22, 3, pp. 1-20, (2017)
  • [9] MUEEN A, KEOGH E, YOUNG N E., Logical-Shapelets: An expressive primitive for time series classification, ACM Sigkdd International Conference on Knowledge Discovery & Data Mining, pp. 1154-1162, (2011)
  • [10] GAO Z K, CAI Q, YANG Y X, Et al., Multiscale limited penetrable horizontal visibility graph for analyzing nonlinear time series, Scientific Reports, 6, 1, (2016)
123