Fuzzification of Euclidean Space Approach in Machine Learning Techniques

Euclidian calculations represent a cornerstone in many machine learning techniques such as the Fuzzy C-Means (FCM) and Support Vector Machine (SVM) techniques. The FCM technique calculates the Euclidian distance between different data points, and the SVM technique calculates the dot product of two points in the Euclidian space. These calculations do not consider the degree of relevance of the selected features to the target class labels. This paper proposed a modification in the Euclidian space calculation for the FCM and SVM techniques based on the ranking of features extracted from evaluating the features. The authors consider the ranking as a membership value of this feature in Fuzzification of Euclidian calculations rather than using the crisp concept of feature selection, which selects some features and ignores others. Experimental results proved that applying the fuzzy value of memberships to Euclidian calculations in the FCM and SVM techniques has better accuracy than the ordinary calculating method and just ignoring the unselected features.