G
Gerasimos Mileounis
Researcher at National and Kapodistrian University of Athens
Publications - 18
Citations - 337
Gerasimos Mileounis is an academic researcher from National and Kapodistrian University of Athens. The author has contributed to research in topics: Volterra series & Greedy algorithm. The author has an hindex of 7, co-authored 18 publications receiving 298 citations. Previous affiliations of Gerasimos Mileounis include Accenture.
Papers
More filters
Journal ArticleDOI
Adaptive algorithms for sparse system identification
TL;DR: Efficient algorithms are developed based on Kalman filtering and Expectation-Maximization based on sparse Volterra models and incorporate the effect of power amplifiers to identify sparse linear and nonlinear systems.
Journal ArticleDOI
An Adaptive Greedy Algorithm With Application to Nonlinear Communications
TL;DR: Two existing powerful greedy schemes developed in the literature are converted into an adaptive algorithm which is applied to estimation of a class of nonlinear communication systems.
Journal ArticleDOI
Empirical Volterra-Series Modeling of Commercial Light-Emitting Diodes
TL;DR: A reverse-engineering approach is presented that is based on Volterra expansions of the electro-optical characteristic function of LEDs, enabling the introduction of a realistic empirical model for commercial devices.
Journal ArticleDOI
Input-output identification of nonlinear channels using PSK, QAM and OFDM inputs
TL;DR: Nonparametric identification of baseband and passband complex Volterra systems excited by communication inputs (phase shift keying, PSK; quadrature amplitude modulation, QAM and OFDM) is considered and an order recursive algorithm is presented for the latter case, that does not require a priori knowledge of the systems order.
Journal ArticleDOI
Blind Identification of Second Order Volterra Systems With Complex Random Inputs Using Higher Order Cumulants
TL;DR: In this correspondence, closed-form expressions for the blind identification of linear-quadratic Volterra systems are established and Cumulant-based formulas are developed demonstrating that the system is uniquely identifiable.