Neural network design
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Hi-index | 0.00 |
Detection fertility and development in hatchery eggs could increase efficiency in commercial hatcheries. A new algorithm named simulated annealing particle swarm optimization algorithm (SAPSO) is proposed, and it is used to optimize topology structure of multi-layer feedback forward neural network for classification of hatching eggs. Trained and tested by a great deal of samples, a reasonable neural network model is obtained. Its performance is measured in terms of two parameters: short computing time and accuracy in the classification process.