Improved chaotic initialization of particle swarm applied to feature selection

H Djellali, N Ghoualmi - 2019 International Conference on …, 2019 - ieeexplore.ieee.org
Particle Swarm PSO and reduced PSO algorithm. The first initialization method is chaotic
initialization with … for PSO algorithm, the second initialization method called reduced size PSO (…

Models for short-term wind power forecasting based on improved artificial neural network using particle swarm optimization and genetic algorithms

DT Viet, VV Phuong, MQ Duong, QT Tran - Energies, 2020 - mdpi.com
… v 2 i init is the initial velocity of the ith particle of the PSO2 algorithm; … Specifically, the
particle swarm optimization algorithm was used to train the artificial neural networks (PSO-ANN …

Improved cooperative artificial neural networkparticle swarm optimization approach for solar photovoltaic systems using maximum power point tracking

A Ibnelouad, A El Kari, H Ayad… - … Transactions on …, 2020 - Wiley Online Library
… of the proposed approach ANN-PSO, in the two phases of ANN (training and testing)
optimized by PSO algorithm approach, for the most robust and efficient approach model structure, …

Particle swarm optimization of deep neural networks architectures for image classification

FEF Junior, GG Yen - Swarm and Evolutionary Computation, 2019 - Elsevier
… The parameters used in the proposed psoCNN can be grouped in three categories: particle
swarm optimization, CNN architecture initialization, and CNN training. The parameters used …

[HTML][HTML] IntelliSwAS: Optimizing deep neural network architectures using a particle swarm-based approach

SC Nistor, G Czibula - Expert Systems with Applications, 2022 - Elsevier
… This proves the stability of our model, as its performance is due to the architecture and
training and not random causes like the initialization of the learnable parameters. …

Swarm intelligence based approach for efficient training of regressive neural networks

GM Lozito, A Salvini - Neural Computing and Applications, 2020 - Springer
… to train neural networks, are prone to local minima entrapment, and for this reason, a strategy
to initialize the training … This algorithm is an evolution of the well-known particle swarm

Improved binary particle swarm optimization for feature selection with new initialization and search space reduction strategies

AD Li, B Xue, M Zhang - Applied Soft Computing, 2021 - Elsevier
… Thus, we propose a novel initialization method for ISBPSO using MI. … is randomly divided
into a training set (70%) and a test set (30%). The training set is fed to a FS method to obtain a …

Particle swarm optimization-based deep neural network for digital modulation recognition

W Shi, D Liu, X Cheng, Y Li, Y Zhao - IEEE Access, 2019 - ieeexplore.ieee.org
… and initialize fine… method and traditional method to perform modulation recognition. Although
time complexity is high in the case of large training datasets or particle quantity, the method

Particle swarm optimization with probability sequence for global optimization

HT Rauf, U Shoaib, MI Lali, M Alhaisoni, MN Irfan… - IEEE …, 2020 - ieeexplore.ieee.org
… , a new approach to initialize population is proposed using … at random locations for swarm
initialization. The proposed … [16], for the training of neural networks and to solve non-linear …

Large-scale feedforward neural network optimization by a self-adaptive strategy and parameter based particle swarm optimization

Y Xue, T Tang, AX Liu - IEEE Access, 2019 - ieeexplore.ieee.org
… mixed initialization as in [30]. In this initialization method, most particles are initialized with a
… its application in training of feedforward neural networks,’’ Knowl.-Based Syst., vol. 143, pp. …