E. Paterakis

Papers

Total Citations

H-Index

About

E. Paterakis is a researcher whose work bridges computational intelligence and nonlinear system identification, with a focus on parameter estimation for complex dynamical systems. Their key research areas include neural networks, genetic algorithms, and hybrid optimization techniques for structured system modeling. Paterakis’s major contribution is the development of a hybrid neural-genetic multimodel parameter estimation algorithm, introduced in their most-cited 1998 paper (32 citations). This algorithm integrates a recurrent incremental credit assignment (ICRA) neural network with genetic algorithms to enhance the identification of nonlinear dynamic systems, offering a robust approach to handling multimodel structures. A related work from the same year (4 citations) further explores genetic algorithms in parameter estimation, underscoring their commitment to advancing computational methods in control and systems engineering. While citation counts are modest, Paterakis’s work is notable for pioneering early hybrid AI techniques that combine learning and evolutionary strategies, laying groundwork for later developments in adaptive system identification. Their research remains relevant for students and engineers tackling nonlinear dynamics in fields like robotics, process control, and signal processing.