Esperanza García-Gonzalo

Dr. Esperanza García-Gonzalo

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2015 in Reliability Engineering & System Safety
Verified
Journal Article
Closed access
PNP.J. García Nieto
P.J. García Nieto
EGEsperanza García-Gonzalo
Esperanza García-Gonzalo
FLF. Sánchez Lasheras
F. Sánchez Lasheras
FJF.J. de Cos Juez
F.J. de Cos Juez

1 April 2018 in Science of The Total Environment
Verified
Journal Article
Closed access
PNPaulino José García Nieto
Paulino José García Nieto
FLF. Sánchez Lasheras
F. Sánchez Lasheras
EGEsperanza García-Gonzalo
Esperanza García-Gonzalo
FJF.J. de Cos Juez
F.J. de Cos Juez

1 May 2010 in Journal of Applied Geophysics
Verified
Journal Article
Closed access
JFJ.L. Fernández-Martínez
J.L. Fernández-Martínez
EGEsperanza García-Gonzalo
Esperanza García-Gonzalo
JÁJosé P. Fernández Álvarez
José P. Fernández Álvarez
HKHeidi A. Kuzma
Heidi A. Kuzma
CPCésar O. Menéndez Pérez
César O. Menéndez Pérez

23 December 2010 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
JFJ.L. Fernández-Martínez
J.L. Fernández-Martínez
EGEsperanza García-Gonzalo
Esperanza García-Gonzalo
Particle swarm optimization (PSO) can be interpreted physically as a particular discretization of a stochastic damped mass-spring system. Knowledge of this analogy has been crucial to derive the PSO continuous model and to introduce different PSO family members including the generalized PSO (GPSO) algorithm, which is the generalization of PSO for any time discretization step. In this paper, we present the stochastic analysis of the linear continuous and generalized PSO models for the case of a stochastic center of attraction. Analysis of the GPSO second order trajectories is performed and clarifies the roles of the PSO parameters and that of the cost function through the algorithm execution: while the PSO parameters mainly control the eigenvalues of the dynamical systems involved, the mean trajectory of the center of attraction and its covariance functions with the trajectories and their derivatives (or the trajectories in the near past) act as forcing terms to update first and second order trajectories. The similarity between the oscillation center dynamics observed for different kinds of benchmark functions might explain the PSO success for a broad range of optimization problems. Finally, a comparison between real simulations and the linear continuous PSO and GPSO models is shown. As expected, the GPSO tends to the continuous PSO when time step approaches zero. Both models account fairly well for the dynamics (first and second order moments) observed in real runs. This analysis constitutes so far the most realistic attempt to better understand and approach the real PSO dynamics from a stochastic point of view.

2 October 2009 in Swarm Intelligence
Verified
Journal Article
Open access
PDF file
JFJ.L. Fernández-Martínez
J.L. Fernández-Martínez
JLJ. L.
J. L.
EGEsperanza García-Gonzalo
Esperanza García-Gonzalo
The PSO algorithm can be physically interpreted as a stochastic damped mass-spring system: the so-called PSO continuous model. Furthermore, PSO corresponds to a particular discretization of the PSO continuous model. In this paper, we introduce a delayed version of the PSO continuous model, where the center of attraction might be delayed with respect to the particle trajectories. Based on this mechanical analogy, we derive a family of PSO versions. For each member of this family, we deduce the first and second order stability regions and the corresponding spectral radius. As expected, the PSO-family algorithms approach the PSO continuous model (damped-mass-spring system) as the size of the time step goes to zero. All the family members are linearly isomorphic when they are derived using the same delay parameter. If the delay parameter is different, the algorithms have corresponding stability regions of any order, but they differ in their respective force terms. All the PSO versions perform fairly well in a very broad area of the parameter space (inertia weight and local and global accelerations) that is close to the border of the second order stability regions and also to the median lines of the first order stability regions where no temporal correlation between trajectories exists. In addition, these regions are fairly similar for different benchmark functions. When the number of parameters of the cost function increases, these regions move towards higher inertia weight values (w=1) and lower total mean accelerations where the temporal covariance between trajectories is positive. Finally, the comparison between different PSO versions results in the conclusion that the centered version (CC-PSO) and PSO have the best convergence rates. Conversely, the centered-progressive version (CP-PSO) has the greatest exploratory capabilities. These features have to do with the way these algorithms update the velocities and positions of particles in the swarm. Knowledge of their respective dynamics can be used to propose a family of simple and stable algorithms, including hybrid versions.

1 September 2019 in Journal of Computational and Applied Mathematics
Verified
Journal Article
Closed access
PNPaulino José García Nieto
Paulino José García Nieto
EGEsperanza García-Gonzalo
Esperanza García-Gonzalo
Fernando Sanchez LasherasFernando Sanchez Lasheras
Fernando Sanchez Lasheras
JPJ.P. Paredes–Sánchez
J.P. Paredes–Sánchez
PFPedro Riesgo Fernández
Pedro Riesgo Fernández