Data Clustering Method Using Efficient Fuzzifier Values Derivation

Abstract

The Type-2 fuzzy set (T2 FS) is widely used for efficient control uncertainties, such as noise sensitivity in the fuzzy set. In addition, unsupervised machine learning requires a clustering parameter value in advance, and may affect clustering performance according to prior information such as the number and size of clusters. In this case, the fuzzifier value m to be applied is the most important factor in improving the accuracy of data. Therefore, in this paper, we intend to perform clustering to automatically acquire the determination of m 1 and m 2 values that depended on existing repeated experiments. To this end, in order to increase efficiency on deriving appropriate fuzzifier value, we used the Interval type-2 possibilistic fuzzy C-means (IT2PFCM), clustering method to classify a given pattern. In Efficient IT2PFCM method, used for clustering, we propose an algorithm that derives suitable fuzzifier values for each data. These values also extract information from each data point through the histogram approach and Gaussian Curve Fitting method. Using the extracted information, two adaptive fuzzifier value m 1 and m 2 are determined. Obtained values apply the new lowest and highest membership values. In addition, it is possible to form an appropriate fuzzy area on each cluster by only taking advantage of the characteristics of IT2PFCM, which reduces uncertainty. This doesn't only improve the accuracy of clustering of measured sensor data, but can also be used without additional procedures such as data labeling or the provision of prior information. It is also efficient at monitoring numerous sensors, managing and verifying sensor data collected in real time such as smart cities. Eventually, in this study, the proposed method is to improve IT2PFCM performance on accurate and quick clustering of large amount of complex data such as Internet of Things (IoT).