Programming and Computer Software

, Volume 45, Issue 8, pp 600–610 | Cite as

Hybrid Model for Efficient Anomaly Detection in Short-timescale GWAC Light Curves and Similar Datasets

  • Y. Sun
  • Z. Zhao
  • X. Ma
  • Z. DuEmail author


Early warning during sky survey provides a crucial opportunity to detect low-mass, free-floating planets. In particular, to search short-timescale microlensing (ML) events from high-cadence and wide- field survey in real time, a hybrid method which combines ARIMA (Autoregressive Integrated Moving Average) with LSTM (Long-Short Time Memory) and GRU (Gated Recurrent Unit) recurrent neural networks (RNN) is presented to monitor all observed light curves and identify ML events at their early stages. Experimental results show that the hybrid models perform better in accuracy and less time consuming of adjusting parameters. ARIMA+LSTM and ARIMA+GRU can achieve improvement in accuracy by 14.5% and 13.2%, respectively. In the case of abnormal detection of light curves, GRU can achieve almost the same result as LSTM with less time by 8%. The hybrid models are also applied to MIT-BIH Arrhythmia Databases ECG dataset which has the similar abnormal pattern to ML. The experimental results from both data sets show that the hybrid model can save up to 40% of researchers' time in model adjusting and optimization to achieve 90% accuracy.



This research is supported in part by Key Research and Development Program of China (no. 2016YFB1000602), ”the Key Laboratory of Space Astronomy and Technology, National Astronomical Observatories, Chinese Academy of Sciences, Beijing ,100012, China,” National Natural Science Foundation of China (nos. 61440057, 61272087, 61363019 and 61073008, 11690023), MOE research center for online education foundation (no. 2016ZD302).


  1. 1.
    Mayer-Schönberger, V. and Cukier, K., Big Data: a Revolution That Will Transform How We Live, Work and Think, Boston: Houghton Mifflin Harcourt, 2013.Google Scholar
  2. 2.
    Siami-Namini, S. and Siami-Namin, A., Forecasting economics and financial time series: ARIMA vs. LSTM, 2018. Scholar
  3. 3.
    Jenkins, G. and Box, G.E.P., Time Series Analysis, Forecasting and Control, San Francisco: Holden-Day, 1970.zbMATHGoogle Scholar
  4. 4.
    Zhang, G.P., “Time series forecasting using a hybrid arima and neural network model, Neurocomputing, 2003, vol. 50, p. 159175.Google Scholar
  5. 5.
    Konar, A. and Bhattacharya, D., Time-Series Prediction and Applications, Ch. 1: An Introduction to Time-Series Prediction, New York: Springer-Verlag, 2017.Google Scholar
  6. 6.
    Hochreiter, S. and Schmidhuber, J., “Long short-term memory, Neural Comput., 1997, vol. 9, no. 8, pp. 1735–1780.CrossRefGoogle Scholar
  7. 7.
    Graves, A. and Schmidhuber, J., Framewise phoneme classification with bidirectional LSTM and other neural network architectures, Neural Networks, 2005, vol. 18, nos. 5–6, pp. 602–610.CrossRefGoogle Scholar
  8. 8.
    Wan, M., Wu, C., Wang, J., et al., Publ. Astron. Soc. Pac., 2016, vol. 128, p. 114501.CrossRefGoogle Scholar
  9. 9.
    Udalski, A., Acta Astron., 2003, vol. 53, p. 291.Google Scholar
  10. 10.
    Udalski, A., Szymanski, M.K., and Szymanski, G., Acta Astron., 2015, vol. 65, p. 1.Google Scholar
  11. 11.
    Feng, T., Du, Z., Sun, Y., et al., in Proc. 6th IEEE Int. Congress on Big Data, Honolulu, 2017.Google Scholar
  12. 12.
    Lipton, Z.C., Berkowitz, J., and Elkan, C., A critical review of recurrent neural networks for sequence learning, 2015. arXiv 1506.00019.Google Scholar
  13. 13.
    Farmer, J.D. and Sidorowich, J.J., “Predicting chaotic time series, Phys. Rev. Lett., 1987, vol. 59, p. 845.MathSciNetCrossRefGoogle Scholar
  14. 14.
    Cho, K., van Merrienboer, B., Bahdanau, D., and Bengio, Y., “On the properties of neural machine translation: encoder-decoder approaches, Proc. 8th Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8), Doha, 2014. arXiv: 1409.1259Google Scholar
  15. 15. Scholar
  16. 16.
    Meng Wan, An Application Research of Column store MonetDB database on GWAC Large-Scale Astronomical Data Management Chaoyang: Natl. Astron. Obs., Chin. Acad. Sci., 2016.Google Scholar
  17. 17. Scholar
  18. 18. Scholar
  19. 19.
    MIT-BIHArrhythmiaDatabase. Scholar
  20. 20.
    Rajpurkar, P., Hannun, A.Y., Haghpanahi, M., Bourn, C., and Ng, A.Y., Cardiologist-level arrhythmia detection with convolutional neural networks, 2017. arXiv:1707.01836Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2019

Authors and Affiliations

  1. 1.Tsinghua University, Department of Computer Science and Technology Qinghua W Rd Haidian, BeijingChina

Personalised recommendations