Evolving neural networks through augmenting topologies
Evolutionary Computation
Evolutionary ensembles with negative correlation learning
IEEE Transactions on Evolutionary Computation
Cooperative coevolution of artificial neural network ensembles for pattern classification
IEEE Transactions on Evolutionary Computation
Making use of population information in evolutionary artificialneural networks
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Fast neural network ensemble learning via negative-correlation data correction
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Prediction and diagnosis of nuclear accidents is one of the most important tasks for nuclear safety. Since accurate diagnosis of nuclear accident is a very important issue for avoidance of disastrous outcomes, it is more desirable to make a decision by combining the results of various expert classifiers rather than by depending on the results of only one classifier. To deal with such challenging problem, the idea of using ensemble classifiers to predict and diagnose accidents is proposed in this paper. Ensembles improve both the efficiency in learning the model and the accuracy in performing classification. Ensemble classifier has substantial advantage over single classifier in prediction accuracy, and the ensemble framework is effective for a variety of classification models. A new method to design and evolve neural network ensembles NNEs based on speciation is used classify reactor data. The main advantage of this method is that, it completely evolves NNEs by combining the evolution of neural networks and the configuration of the ensemble in one evolutionary phase. After forming the ensemble, several accident diagnoses were performed. The results indicate that ensemble able to diagnose the accidents accurately with high rate.