A parallel evolving algorithm for flexible neural tree
Parallel Computing
Swarm optimization and Flexible Neural Tree for microarray data classification
Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology
Hi-index | 0.00 |
The paper introduces that cement decomposing furnace plays an important role in the pre-decomposing system. To make clear the complex relation among its related factors and control its production process better, the paper presents a method of making use of flexible neural tree (FNT) to construct its production process model. The FNT model’s structure and parameters are optimized by probabilistic incremental program evolution (PIPE) and simulation annealing (SA) respectively. The paper gives a detailed description of the process of constructing the FNT model, and tests the performance of the optimized model. The result demonstrates that the put forward method is effective for solving the problem. At last, comparing with other methods, the distinct advantage is that it is capable of handing the task automatically. The successful application of the method in cement decomposing production process will opens up a new research direction for cement industry production process modeling, it even has a great influence on the whole fluid industry.