Improvements in the application of stochastic estimation algorithms--Parameter jump detection
- 1 November 1984
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 29 (11) , 962-969
- https://doi.org/10.1109/tac.1984.1103411
Abstract
The paper discusses the problem of recursive algorithms for estimating parameters which are subject to random jumps. A new method is presented which consists of detecting these parameter jumps and, should a detection occur, reinitializing the estimation gain sequence. New variables required by this method are calculated by means of diffusion approximations. Some simulation results illustrate the improved adaptation capabilities offered by the method.Keywords
This publication has 18 references indexed in Scilit:
- A measure of the tracking capability of recursive stochastic algorithms with constant gainsIEEE Transactions on Automatic Control, 1982
- Edge detection using sequential methods for change in level--Part II: Sequential detection of change in meanIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Dynamic model-based techniques for the detection of incidents on freewaysIEEE Transactions on Automatic Control, 1980
- Detecting change in a time-series (Corresp.)IEEE Transactions on Information Theory, 1980
- Maximum-likelihood estimation of a process with random transitions (failures)IEEE Transactions on Automatic Control, 1979
- Convergence of an adaptive filter algorithmInternational Journal of Control, 1978
- Analysis of recursive stochastic algorithmsIEEE Transactions on Automatic Control, 1977
- An adaptive technique for a redundant-sensor navigation systemPublished by American Institute of Aeronautics and Astronautics (AIAA) ,1972
- On Stochastic Processes Defined by Differential Equations with a Small ParameterTheory of Probability and Its Applications, 1966
- Continuous Inspection SchemesBiometrika, 1954