The Optimization of Fuzzy Neural Network Based on Artificial Fish Swarm Algorithm

2013 ◽  
Author(s):  
Lei Yanmin ◽  
Feng Zhibin
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Artificial Fish Swarm Algorithm ◽  
Fuzzy Neural ◽  
Artificial Fish Swarm ◽  
Swarm Algorithm

Research on Nonlinear Approximation Model of Radial Basis Function Neural Network Trained Using Artificial Fish Swarm Algorithm with Adaptive Adjustment

2015 ◽  
Vol 713-715 ◽  
pp. 1855-1858 ◽  
Author(s):  
Xu Sheng Gan ◽  
Xue Qin Tang ◽  
Hai Long Gao
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Nonlinear Approximation ◽  
Nonlinear Function ◽  
Training Algorithm ◽  
Step Size ◽  
Artificial Fish Swarm Algorithm ◽  
Artificial Fish Swarm ◽  
Adaptive Adjustment ◽  
Swarm Algorithm

In order to improve the modeling efficiency of RBF neural network, an Artificial Fish Swarm Algorithm (AFSA) training algorithm with an adaptive mechanism is proposed. In the training algorithm, the search step size and visible domain of AFSA algorithm can be adjusted dynamically according to the convergence characteristics of artificial fish swarm, and then the improved AFSA algorithm is used to optimize the parameters of RBF neural network. The example shows that, the proposed model is a better approximation performance for the nonlinear function.

The Application in Grain Monitoring Based on Particle Swarm-Fuzzy Neural Network Algorithm

2011 ◽  
Vol 474-476 ◽  
pp. 1116-1121 ◽  
Author(s):  
Zhen Tong ◽  
Wang Jing ◽  
Yi Ming ◽  
Jian Jun Wu
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Particle Swarm ◽  
Particle Swarm Algorithm ◽  
Iterative Optimization ◽  
Network Algorithm ◽  
Temperature And Humidity ◽  
Fuzzy Neural ◽  
Neural Network Algorithm ◽  
Swarm Algorithm

In order to strengthen the administration of the barn, we need to storage environment for scientific and effective monitoring and analysis. This paper firstly filter and merge the temperature and humidity information in the environment by using fuzzy neural network, then regard the temperature and humidity as particles, calculate the fitness of the particles according to corresponding mildew rate and cost, finally the outputs of temperature and humidity curve values are obtained through iterative optimization of local and global extreme by particle swarm algorithm.

Sign in / Sign up

Export Citation Format

Share Document