Iterative-differential-analyzer methods are presented which allow experimental studies of prediction net works to be performed without the use of delay lines. Two classes of problems are examined in this paper:
1. Prediction of stochastic signals with no noise present.
2. Prediction and filtering of deterministic signals masked by noise. Measurement techniques are de veloped for each case, and experimental verification is included.
Get full access to this article
View all access options for this article.
References
1.
Korn, G.A., New High-Speed Analog and Analog-Digital Computing Techniques: The ASTRAC System, Electronic Industries, July 1962.
2.
Bates, M.R., et al., Analog Computer Applications in Predictor Design, Trans. IRE/PGEC, September 1957.
3.
Becker, C.L. and Wait, J.V., Two-Level Correlation of an Analog Computer , Trans. IRE/PGEC, December 1961 .
4.
Conant, B., A Hybrid Analog-Digital Statistics Computer, ACL Memo No. 45, Electrical Engineering Dept., University of Arizona, Tucson, Arizona.
5.
Zadeh, L.A. and Ragazzini, An Extension of Wiener's Theory of Prediction, J. Appl. Physics, Vol. 21, pp. 645-655, July 1950 .
6.
Chang, S.S.L. , Synthesis of Optimum Control Systems , McGraw-Hill, New York, N.Y., 1961, pp. 100-125.
