00082 "ae3029ab37e06a00bafcfcfbbff716

81

Adaptive Hierarchical Bayesian Kalman Filtering

There is also a flattening of the expected value of the weighting curve in the area corresponding to the case where the design models and truth models are nearly equal. This indicates that rejection of competing models will be morę difficult in this area. This indicates that we do not need dense sampling across the rangę of gains. This fact was corroborated by the performance comparison which indicated that, due to the weighted averaging of the various filter element estimates, an adaptive filter with only 5 discrete elements was nearly identical in performance to the truth model.

References

Box, G. E. P., and Jenkins, G. M. (1970). Time Series Analysis Forecasting and Control. Holden-Day, San Francisco.

Crowder, S. V. (1986). “Kalman Filtering and Statistical Process Control.” Unpublished Ph. D. Dissertation, Iowa State University.

Duncan, D. B., and Horn, S. D. (1972). “Linear Dynamie Recursive Estimation from the Viewpoint of Regression Analysis.” Journal of the American Statistical Association, 42, 224-241.

Harrison, P. J. (1967). “Exponential Smoothing and Short-Term Sales Forecasting.” Management Science, 13,821-842.

Harrison, P. J., and Stevens, C. F. (1971). A Bayesian Approach to Short-Term Forecasting. Operational Research Quarterly, 22, 341-362.

Harrison, P. J., and Stevens, C. F. (1976). "Bayesian Forecasting." Journal of the Royal Statistical Society, B, 205-228.

Ho, Y. C., and Lee, R. C. K. (1964). "A Bayesian Approach to Problems in Stochastic Estimation and Control." IEEE Transactions on Automatic Control, AC-9.

Hunter, J. S. (1986). "The Exponentially Weighted Moving Average." Journal of Quality Technology, 18, 203-210.

Kalman, R. E. (1960). "A New Approach to Linear Filtering and Prediction Problems." Transactions ASME Journal of Basic Engineering, 82, 34-35.