Title | ||
---|---|---|
A mixture of experts committee machine to design compensators for intensity modulated radiation therapy |
Abstract | ||
---|---|---|
This paper presents a new algorithm to produce a near optimal mixture of experts model (MEM) architecture for a continuous mapping. The MEM is applied to a new method incorporating photon scatter for designing compensators for intensity modulated radiation therapy. The algorithm utilizes the fuzzy C-means clustering algorithm to partition data before training commences. A reduction in the size of training sets also allows the Levenberg-Marquardt algorithm to be implemented. As a result, both training time and validation error are reduced. A 71% reduction in prediction error compared with that of a single neural network is achieved. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1016/j.patcog.2006.03.018 | Pattern Recognition |
Keywords | Field | DocType |
experts committee machine,training commences,experts model,validation error,levenberg-marquardt algorithm,continuous mapping,intensity modulated radiation therapy,training time,new method,new algorithm,fuzzy c-means,prediction error,compensators,neural networks,levenberg marquardt,radiation therapy,neural network | Photon,Mean squared prediction error,Pattern recognition,Committee machine,Fuzzy logic,Mixture of experts,Artificial intelligence,Artificial neural network,Cluster analysis,Intensity-modulated radiation therapy,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
39 | 9 | Pattern Recognition |
Citations | PageRank | References |
9 | 0.46 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
J. H. Goodband | 1 | 9 | 0.46 |
O. C. L. Haas | 2 | 9 | 1.14 |
J. A. Mills | 3 | 9 | 0.46 |