A study on feature extraction of parallel immune genetic clustering algorithm based on clustering center optimization

A method of feature extraction of parallel immune genetic clustering algorithm based on clustering center optimization is put forward which is using the characteristics of text. The different characteristics of between the features is give full consideration by this method, and the parallel and immune mechanisms genetic algorithm is used which can calculate clustering center of the feature. Comparative test results show that the method not only can reduce the dimension of the feature, but also can increase the correct rate and recall rate of classification, thus the overall performance of the classification system is enhanced, and it can be enable the system to achieve a higher level of automation and strong portability.