Abstract
A least-squares (LS) based algorithm for noisy autoregressive signals is recently proposed, which needs neither to prefilter noisy data nor to perform parameter extraction. In this paper, a more computationally efficient procedure for estimating the measurement noise variance is developed, and then an efficient implementation of the algorithm is presented. It is shown that this better way of implementation can considerably reduce the computational requirement of the LS based algorithm.
| Original language | English |
|---|---|
| Pages (from-to) | V-21-V-24 |
| Journal | Proceedings - IEEE International Symposium on Circuits and Systems |
| Volume | 5 |
| Publication status | Published - 1998 |
| Event | Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, ISCAS. Part 5 (of 6) - Monterey, CA, USA Duration: 31 May 1998 → 3 Jun 1998 |