Mean and entropy of b-spline PDF models: analysis and design

J. Zhou, H. Yue, H. Wang

Research output: Contribution to conferencePaper

Abstract

For continuous probability density functions (PDFs) approximated by the B-spline basis functions, the relationships between the B-spline weights, the entropy and the mean have been analyzed in detail. It shows the different characteristics of the entropy with and without mean constraint. A minimum entropy controller subjected to mean constraint is developed by taking the performance function as a Lyapunov function and ensuring the negativeness of its first-order derivative. Simulation examples are included to validate the analysis results and evaluate the closed-loop control performance.
Original languageEnglish
Pages1 - 6
Number of pages6
DOIs
Publication statusPublished - 2005
Event16th IFAC World Congress, 2005 - Prague, Czech Republic
Duration: 4 Jul 20058 Jul 2005

Conference

Conference16th IFAC World Congress, 2005
CountryCzech Republic
CityPrague
Period4/07/058/07/05

Keywords

  • dynamic stochastic systems
  • probability density function (PDF)
  • B-spline neural network
  • minimum entropy
  • mean constraint

Fingerprint Dive into the research topics of 'Mean and entropy of b-spline PDF models: analysis and design'. Together they form a unique fingerprint.

  • Cite this

    Zhou, J., Yue, H., & Wang, H. (2005). Mean and entropy of b-spline PDF models: analysis and design. 1 - 6. Paper presented at 16th IFAC World Congress, 2005, Prague, Czech Republic. https://doi.org/10.3182/20050703-6-CZ-1902.00368