Weight Optimize by Automatic Unsupervised Clustering using Computation Intelligence

Abstract

The present data used for clustering contains data record not related to processing. This may be spam or noise causing error and delay of processing. However, it is necessary to process this kind of data together but the results may be incorrect, depending on the quantity of noise. Therefore, it will be much better if data cleaning is conducted before processing system data. This paper proposes a method to develop unsupervised clustering intelligence to reduce the quantity of spam. This computational intelligence system applies the first layer of radial basis function network as an input layer of the system for incremental work. The results of system can provide level of accuracy of least related membership in any cluster which is called the data not relevant to the dataset or the data not associated with the dataset. According to an experiment, the data from UCI machine learning repository was used to test the system efficiency while classification algorithm in a program called weka3.6 was also utilized to test the system accuracy. The results from noise filtering help the data processing more precise, compared to the processing without the noise filtering.