Abstract
FCM (fuzzy c-means algorithm) based on Euclidean
distance function converges to a local minimum of the objective
function, which can only be used to detect spherical structural
clusters. The added fuzzy covariance matrices in their distance
measure were not directly derived from the objective function. In
this paper, an improved Normalized Clustering Algorithm Based
on Mahalanobis distance by taking a new threshold value and a
new convergent process is proposed.