|
SPEAKER: |
|
|
TITLE: |
"Signal Processing: Modeling and Parameter Estimation" |
|
DAY: |
Wednesday, October 4, 2000 |
|
TIME: |
3:30 p.m. [Coffee & cookies in BSB-202 at 3:00 p.m.] |
|
PLACE: |
BSB-108 |
Signal Processing is an area that has been the focus of extensive research in the field of engineering. Statistics plays an integral role in model formulation, and in the development of efficient estimation techniques. In this talk, we will describe two models that have been widely discussed in the literature. These models have been applied in a variety of different disciplines including medicine, radar/ sonar tracking, seismology, and communications. The models are highly nonlinear, and traditional estimation methods like maximum likelihood and least squares are numerically difficult. We will discuss some alternative methods of estimation of the model parameters using eigendecompositions of the sample covariance matrix. These eigenspace methods are high-resolution techniques that exploit the structures in these models and are computationally much more tractable then the traditional methods.
Dr Nandini Kannan is an Associate Professor in the Division of Mathematics and Statistics at the University of Texas at San Antonio. She received her Ph.D. degree in Statistics from Pennsylvania State University, University Park, in 1992. After receiving her Ph.D., she joined the faculty at San Antonio. Her research interests include Signal Processing, Multivariate Analysis, Survival Analysis, and Inference.
The references below, suggested by the speaker as useful background for this talk, have been placed on reserve at Thode Library (STATS 770: Statistics Seminar).
Kannan, N. & D. Kundu (1994). On modified EVLP and ML methods for estimating superimposed exponential signals. Signal Processing 39, 223-233.
Schmidt, R.O. (1986). Multiple emitter location and signal parameter estimation. IEEE Transactions on Antennas and Propagation AP-34, 276-280.