Abstract
The paper addresses the Karhunen-Loeve series representation in the tessarine domain. Based on augmented statistics, a tessarine widely linear Karhunen-Loeve expansion is defined. Then, the impact of T-properness on this representation
is analyzed, leading to a T-proper Karhunen-Loeve expansion that means a dimensionality reduction. Furthermore, this series representation serves as a versatile simulation tool, valid for both stationary and non-stationary, Gaussian and non-Gaussian random signals. Finally, the applicability of the simulation technique proposed is examined numerically.
is analyzed, leading to a T-proper Karhunen-Loeve expansion that means a dimensionality reduction. Furthermore, this series representation serves as a versatile simulation tool, valid for both stationary and non-stationary, Gaussian and non-Gaussian random signals. Finally, the applicability of the simulation technique proposed is examined numerically.
Original language | English |
---|---|
Title of host publication | 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP) |
Publisher | IEEE |
Number of pages | 6 |
ISBN (Electronic) | 979-8-3503-7225-0 |
ISBN (Print) | 979-8-3503-7226-7 |
DOIs | |
Publication status | Published - 4 Nov 2024 |