Notice of RetractionRecognition of stratiform/cumuliform cloud based on G-K fuzzy clustering and SVM

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

By now, there are many recognition methods. Support vector machine (SVM) is one of main methods. For SVM, the training time was long and it was hard to implement large-scale samples´ training, so the training model of SVM and the recognition to the testing are influenced directly. In order to solve these problems, this paper provided an optimized algorithm based on Gustafson-Kessel (G-K) fuzzy clustering of training sample set, and it studied the automatic recognition of stratiform /cumuliform cloud. In the paper, the cloud areas were extracted, and the data were refined with clustering. Finally, the stratiform /cumuliform clouds were identified with SVM. The experiments showed that the training sample scale was reduced by six and the training time of SVM was reduced from 31ms to 16ms after Gustafson-Kessel clustering. The recognition rate was greatly increased from 78% to 86% with the optimized algorithm.