Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Optimal experimental design in the context of canonical expansions

In a wide variety of engineering applications, the mathematical model cannot be fully identified. Therefore, one would like to construct robust operators (filters, classifiers, controllers etc.) that perform optimally relative to incomplete knowledge. Improving model identification through determining unknown parameters can enhance the performance of robust operators. One would like to perform the experiment that provides the most information relative to the engineering objective. The authors present an experimental design framework for parameter estimation in signal processing when the random process model is in the form of canonical expansions. The proposed experimental design is based on the concept of the mean objective cost of uncertainty, which quantifies model uncertainty by taking into account the performance degradation of the designed operator owing to the presence of uncertainty. They provide the general framework for experimental design in the context of canonical expansions and solve it for two major signal processing problems: optimal linear filtering and signal detection.

References

    1. 1)
      • 15. Mohsenizadeh, D., Dehghannasiri, R., Dougherty, E.: ‘Optimal objective-based experimental design for uncertain dynamical gene networks with experimental error’, IEEE/ACM Trans. Comput. Biol. Bioinf., 2016, 10.1109/TCBB.2016.2602873.
    2. 2)
      • 10. Chen, H., Varshney, P.K.: ‘Theory of the stochastic resonance effect in signal detection—Part II: variable detectors’, IEEE Trans. Signal Process., 2008, 56, (10), pp. 50315041.
    3. 3)
      • 14. Dehghannasiri, R., Yoon, B.-J., Dougherty, E.: ‘Optimal experimental design for gene regulatory networks in the presence of uncertainty’, IEEE/ACM Trans. Comput. Biol. Bioinf., 2015, 12, (4), pp. 938950.
    4. 4)
      • 3. Poor, H.V.: ‘On robust Wiener filtering’, IEEE Trans. Autom. Control, 1980, 25, (3), pp. 531536.
    5. 5)
      • 9. Likas, A.C., Galatsanos, N.P.: ‘A variational approach for Bayesian blind image deconvolution’, IEEE Trans. Signal Process., 2004, 52, (8), pp. 22222233.
    6. 6)
      • 2. Kassam, S.A., Lim, T.L.: ‘Robust Wiener filters’, J. Franklin Inst., 1977, 304, (4), pp. 171185.
    7. 7)
      • 21. Tuzlukov, V.: ‘Signal detection theory’ (Springer Science & Business Media, 2001).
    8. 8)
      • 1. Kuznetsov, V.: ‘Stable detection when the signal and spectrum of normal noise are inaccurately known’, Telecommun. Radio Eng., 1976, 30, p. 31.
    9. 9)
      • 12. Dehghannasiri, R., Qian, X., Dougherty, E.: ‘Optimal experimental design in canonical expansions with applications to signal compression’. Proc. IEEE Global Conf. Signal and Information Processing, Washington D.C., USA, December 2016, pp. 9498.
    10. 10)
      • 16. Dehghannasiri, R., Xue, D., Balachandran, P.V., et al: ‘Optimal experimental design for materials discovery’, Comput. Mater. Sci., 2017, 129, pp. 311322.
    11. 11)
      • 4. Poor, V., Looze, D.P.: ‘Minimax state estimation for linear stochastic systems with noise uncertainty’, IEEE Trans. Autom. Control, 1981, 26, (4), pp. 902906.
    12. 12)
      • 6. Grigoryan, A.M., Dougherty, E.R.: ‘Bayesian robust optimal linear filters’, Signal Process.., 2001, 81, (12), pp. 25032521.
    13. 13)
      • 8. Dougherty, E.R., Chen, Y.: ‘Robust optimal granulometric bandpass filters’, Signal Process.., 2001, 81, (7), pp. 13571372.
    14. 14)
      • 22. Levy, B.C.: ‘Principles of signal detection and parameter estimation’ (Springer Science & Business Media, 2008).
    15. 15)
      • 18. Dougherty, E.R.: ‘Random processes for image and signal processing’ (SPIE Optical Engineering Press, 1999).
    16. 16)
      • 24. Thomas, J., Wong, E.: ‘On the statistical theory of optimum demodulation’, IRE Trans. Inf. Theory, 1960, 6, (4), pp. 420425.
    17. 17)
      • 19. Dalton, L., Dougherty, E.: ‘Intrinsically optimal Bayesian robust filtering’, IEEE Trans. Signal Process., 2014, 62, (3), pp. 657670.
    18. 18)
      • 7. Dalton, L.A., Dougherty, E.R.: ‘Optimal classifiers with minimum expected error within a Bayesian framework—Part I: Discrete and Gaussian models’, Pattern Recogn., 2013, 46, (5), pp. 13011314.
    19. 19)
      • 13. Yoon, B.-J., Qian, X., Dougherty, E.: ‘Quantifying the objective cost of uncertainty in complex dynamical systems’, IEEE Trans. Signal Process., 2013, 61, (9), pp. 22562266.
    20. 20)
      • 25. Dehghannasiri, R., Yoon, B.-J., Dougherty, E.: ‘Efficient experimental design for uncertainty reduction in gene regulatory networks’, BMC Bioinf., 2015, 16, (Suppl. 13), p. S2.
    21. 21)
      • 17. Pugachev, V.: ‘Theory of random functions and its applications to control problems’ (Pergamon Press; USA ed. distributed by Addison-Wesley, 1965).
    22. 22)
      • 5. Vastola, K.S., Poor, H.V.: ‘Robust Wiener-Kolmogorov theory’, IEEE Trans. Inf. Theory, 1984, 30, (2), pp. 316327.
    23. 23)
      • 20. Qian, X., Dougherty, E.R.: ‘Bayesian regression with network prior: optimal Bayesian filtering perspective’, IEEE Trans. Signal Process., 2016, 64, (23), pp. 62436253.
    24. 24)
      • 11. Dehghannasiri, R., Esfahani, M.S., Dougherty, E.: ‘Intrinsically Bayesian robust Kalman filter: an innovation process approach’, IEEE Trans. Signal Process., 2017, 65, (10), pp. 25312546.
    25. 25)
      • 23. Youla, D.C.: ‘The use of the method of maximum likelihood in estimating continuous-modulated intelligence which has been corrupted by noise’, IRE Trans. Inform. Theory, 1954, 3, (3), pp. 90105.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2017.0016
Loading

Related content

content/journals/10.1049/iet-spr.2017.0016
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address