Multidimensional Systems and Signal Processing

, Volume 30, Issue 1, pp 391–411 | Cite as

Collaborative linear dynamical system identification by scarce relevant/irrelevant observations

  • Behzad Bakhtiari
  • Hadi Sadoghi YazdiEmail author


In the current paper, linear dynamical system identification by relevant and irrelevant multi-sensor observations is presented. In common system identification methods, it is presumed that observations are related to the system. However, the present study assumes that there are multi-sensor observations, whose sensors may give relevant information related to the system while some others do not. Furthermore, whether or not the sensor data is related or unrelated is unknown. Especially in large dimensions, the scarce observations of sensors pose a problem for estimating parameters. For this scenario, the current work will show that common methods are not appropriate. Therefore, to solve the problem of scarce relevant/irrelevant observations, the collaborative identification method is presented, in which relevant sensors collaborate with each other and, as a result, the estimation of parameters is more accurate. The results of synthetic and real dataset experiments indicate that the proposed model’s performance is superior to common methods.


Linear dynamical system identification State-space model parameter estimation Multi-sensor multi-dimensional observations Unreliable observations Scarce observations Relevant/irrelevant observations 


  1. Carmi, A., Gurfil, P., & Kanevsky, D. (2010). Methods for sparse signal recovery using kalman filtering with embedded pseudo-measurement norms and quasi-norms. IEEE Transactions on Signal Processing, 58(4), 2405–2409. Scholar
  2. Charles, A., Asif, M. S., Romberg, J., & Rozell, C. (2011). Sparsity penalties in dynamical system estimation. In 2011 45th annual conference on information sciences and systems, March 2325, 2011 (pp. 1–6).
  3. Chen, F., Agüero, J. C., Gilson, M., Garnier, H., & Liu, T. (2017). EM-based identification of continuous-time ARMA models from irregularly sampled data. Automatica, 77, 293–301. Scholar
  4. Cheng, J., Fang, M., & Wang, Y. (2017). Subspace identification for closed-loop 2-D separable-in-denominator systems. Multidimensional Systems and Signal Processing, 28(4), 1499–1521. Scholar
  5. Choong, M. K., Charbit, M., & Yan, H. (2009). Autoregressive-model-based missing value estimation for DNA microarray time series data. IEEE Transactions on Information Technology in Biomedicine, 13(1), 131–137. Scholar
  6. Ding, F. (2014). State filtering and parameter estimation for state space systems with scarce measurements. Signal Processing, 104, 369–380. Scholar
  7. Ding, F., & Ding, J. (2010). Least-squares parameter estimation for systems with irregularly missing data. International Journal of Adaptive Control and Signal Processing, 24(7), 540–553.MathSciNetzbMATHGoogle Scholar
  8. Ding, J., Han, L., & Chen, X. (2010). Time series AR modeling with missing observations based on the polynomial transformation. Mathematical and Computer Modelling, 51(5), 527–536. Scholar
  9. Ding, F., Liu, G., & Liu, X. P. (2011). Parameter estimation with scarce measurements. Automatica, 47(8), 1646–1655. Scholar
  10. Ding, F., Wang, X., Mao, L., & Xu, L. (2017). Joint state and multi-innovation parameter estimation for time-delay linear systems and its convergence based on the Kalman filtering. Digital Signal Processing, 62, 211–223.CrossRefGoogle Scholar
  11. Ding, F., Wang, F., Xu, L., Hayat, T., & Alsaedi, A. (2016). Parameter estimation for pseudo-linear systems using the auxiliary model and the decomposition technique. IET Control Theory and Applications, 11(3), 390–400.MathSciNetCrossRefGoogle Scholar
  12. Ghahramani, Z., & Hinton, G. E. (1996). Parameter estimation for linear dynamical systems. Technical report CRG-TR-96-2, University of Toronto, Dept. of Computer Science.Google Scholar
  13. Ghanem, B., & Ahuja, N. (2010). Sparse coding of linear dynamical systems with an application to dynamic texture recognition. In 2010 20th international conference on pattern recognition, August 2326 2010 (pp. 987–990).
  14. Gibson, S., & Ninness, B. (2005). Robust maximum-likelihood estimation of multivariable dynamic systems. Automatica, 41(10), 1667–1682. Scholar
  15. Huang, W.-B., Sun, F., Cao, L.-L., & Harandi, M. (2016). Analyzing linear dynamical systems: From modeling to coding and learning.
  16. Ko, J., & Fox, D. (2009). GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models. Autonomous Robots, 27(1), 75–90. Scholar
  17. Liang, J., Wang, Z., & Liu, X. (2014). Robust state estimation for two-dimensional stochastic time-delay systems with missing measurements and sensor saturation. Multidimensional Systems and Signal Processing, 25(1), 157–177. Scholar
  18. Liu, Q., & Ding, F. (2017). The data filtering based generalized stochastic gradient parameter estimation algorithms for multivariate output-error autoregressive systems using the auxiliary model. Multidimensional Systems and Signal Processing. Scholar
  19. Liu, Z., & Hauskrecht, M. (2015). A regularized linear dynamical system framework for multivariate time series analysis. Paper presented at the proceedings of the twenty-ninth AAAI conference on artificial intelligence, Austin, Texas.Google Scholar
  20. Luttinen, J. (2013). Fast variational Bayesian linear state-space model. Paper presented at the proceedings of the European conference on machine learning and knowledge discovery in databases—Volume 8188, Prague, Czech Republic.Google Scholar
  21. Luttinen, J., Ilin, A., & Karhunen, J. (2009). Bayesian robust PCA for incomplete data. In T. Adali, C. Jutten, J. M. T. Romano, & A. K. Barros (Eds.), Independent component analysis and signal separation: 8th international conference, ICA 2009, Paraty, Brazil, March 1518, 2009. Proceedings (pp. 66–73). Berlin: Springer.Google Scholar
  22. Ma, P., Ding, F., Alsaedi, A., & Hayat, T. (2017). Recursive least squares identification methods for multivariate pseudo-linear systems using the data filtering. Multidimensional Systems and Signal Processing. Scholar
  23. Oliveira, P., & Gomes, L. (2009). Interpolation of signals with missing data using principal component analysis. Multidimensional Systems and Signal Processing, 21(1), 25. Scholar
  24. Peñarrocha, I., Sanchis, R., & Albertos, P. (2012). Estimation in multisensor networked systems with scarce measurements and time varying delays. Systems and Control Letters, 61(4), 555–562.MathSciNetCrossRefzbMATHGoogle Scholar
  25. Pereira, S. S., López-Valcarce, R., & Pagès-Zamora, A. (2013). A diffusion-based EM algorithm for distributed estimation in unreliable sensor networks. IEEE Signal Processing Letters, 20(6), 595–598. Scholar
  26. Robinson, G. A., & Smith, G. A. (2000). A comparison between the EM and subspace identification algorithms for time-invariant linear dynamical systems. Cambridge: Cambridge University.Google Scholar
  27. Roweis, S., & Ghahramani, Z. (1999). A unifying review of linear Gaussian models. Neural Computation, 11(2), 305–345. Scholar
  28. Shumway, R. H., & Stoffer, D. S. (1982). An approach to time series smoothing and forecasting using the em algorithm. Journal of Time Series Analysis, 3(4), 253–264. Scholar
  29. Siddiqi, S. M., Boots, B., & Gordon, G. J. (2007). A constraint generation approach to learning stable linear dynamical systems. Paper presented at the proceedings of the 20th international conference on neural information processing systems, Vancouver, British Columbia, Canada.Google Scholar
  30. Svensson, A., & Schön, T. B. (2017). A flexible state–space model for learning nonlinear dynamical systems. Automatica, 80, 189–199.MathSciNetCrossRefzbMATHGoogle Scholar
  31. Tutunji, T. A. (2016). Parametric system identification using neural networks. Applied Soft Computing, 47, 251–261.CrossRefGoogle Scholar
  32. van Overschee, P., & de Moor, B. L. (2012). Subspace identification for linear systems: Theory—Implementation—Applications. Berlin: Springer.zbMATHGoogle Scholar
  33. Wang, X., & Ding, F. (2015). Recursive parameter and state estimation for an input nonlinear state space system using the hierarchical identification principle. Signal Processing, 117, 208–218.CrossRefGoogle Scholar
  34. Wang, Y., & Ding, F. (2016). Recursive parameter estimation algorithms and convergence for a class of nonlinear systems with colored noise. Circuits, Systems, and Signal Processing, 35(10), 3461–3481.MathSciNetCrossRefzbMATHGoogle Scholar
  35. Wen, F., & Xu, Y. (2017). HOSVD based multidimensional parameter estimation for massive MIMO system from incomplete channel measurements. Multidimensional Systems and Signal Processing. Scholar
  36. Yazidi, A., Oommen, B. J., & Olsen, M. G. (2015). On distinguishing between reliable and unreliable sensors without a knowledge of the ground truth. Paper presented at the international conference on web intelligence and intelligent agent technology, Singapore, 2015.Google Scholar
  37. Zhang, X., Ding, F., Alsaadi, F. E., & Hayat, T. (2017). Recursive parameter identification of the dynamical models for bilinear state space systems. Nonlinear Dynamics, 89(4), 2415–2429. Scholar
  38. Zitao, L., Hauskrecht, M. (2016). Learning linear dynamical systems from multivariate time series a matrix factorization based framework. In Proceedings of the 2016 SIAM international conference on data mining. Society for Industrial and Applied Mathematics.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer EngineeringFerdowsi University of MashhadMashhadIran

Personalised recommendations