Advertisement

Quaternion-Valued Feedforward Neural Network Based Time Series Forecast

  • Xiaodong Li
  • Changjun Yu
  • Fulin Su
  • Aijun Liu
  • Xuguang Yang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 463)

Abstract

Currently, the quaternion-valued feedforward neural network (QFNN) has been proposed for image compression and has a more superior performance than the real-valued feedforward neural network (FNN). However, the used quaternion activation function is a split quaternion function, thus it may not preserve the cross-information within the components of the data and for time series forecast, the established model is a strictly linear model which may not be appropriate for noncircular quaternion-valued signal processing.

In this paper, a fully quaternion activation function is employed to design the QFNN and an augmented QFNN (AQFNN) is proposed. They are derived by using recent studies in the augmented quaternion statistics and the HR-calculus. With the augmented quaternion statistics, the AQFNN can process quaternion-valued noncircular signals, effectively. Simulations on both benchmark circular and noncircular quaternion-valued signals, and real-world quaternion-valued signals support the analysis.

Keywords

FNN Augmented quaternion statistics HR-calculus Noncircular 

References

  1. 1.
    Jahanchahi, C., Mandic, D.P.: A class of quaternion Kalman filters. IEEE Trans. Neural Netw. Learn. Syst. 25(3), 533–544 (2014)CrossRefGoogle Scholar
  2. 2.
    Took, C.C., Strbac, G., Aihara, K., Mandic, D.P.: Quaternion-valued short-term joint forecasting of three-dimensional wind and atmospheric parameters. Renew. Energy 36(6), 1754–1760 (2011)CrossRefGoogle Scholar
  3. 3.
    Matsui, N., Isokawa, T., Kusamichi, H., Peper, F., Nishimura, H.: Quaternion neural network with geometrical operators. J. Intell. Fuzzy Syst. 15(3, 4), 149–164 (2004)MATHGoogle Scholar
  4. 4.
    Shang, F., Hirose, A.: Quaternion neural-network-based PolSAR land classification in Poincare-sphere-parameter space. IEEE Trans. Geosci. Remote Sens. 52(9), 5693–5703 (2014)CrossRefGoogle Scholar
  5. 5.
    Took, C.C., Mandic, D.P.: Augmented second-order statistics of quaternion random signals. Signal Process. 91(2), 214–224 (2011)CrossRefGoogle Scholar
  6. 6.
    Ell, T.A., Sangwine, S.J.: Quaternion involutions and anti-involutions. Comput. Math. Appl. 53(1), 137–143 (2007)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Ujang, B.C., Took, C.C., Mandic, D.P.: Quaternion-valued nonlinear adaptive filtering. IEEE Trans. Neural Netw. 22(8), 1193–1206 (2011)CrossRefGoogle Scholar
  8. 8.
    Xu, D., Mandic, D.P.: The theory of quaternion matrix derivatives. IEEE Trans. Signal Process. 63(6), 1543–1556 (2015)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Xia, Y., Jahanchahi, C., Mandic, D.P.: Quaternion-valued echo state networks. IEEE Trans. Neural Networks Learn. Syst. 26(4), 663–673 (2015)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Xiaodong Li
    • 1
  • Changjun Yu
    • 1
  • Fulin Su
    • 1
  • Aijun Liu
    • 1
  • Xuguang Yang
    • 1
  1. 1.Harbin Institute of TechnologyWeihaiChina

Personalised recommendations