On the Spectral Clustering for Dynamic Data

Abstract

Abstract. Spectral clustering has shown to be a powerful technique for grouping and/or rank data as well as a proper alternative for unlabeled problems. Particularly, it is a suitable alternative when dealing with pattern recognition problems involving highly hardly separable classes. Due to its versatility, applicability and feasibility, this clustering technique results appealing for many applications. Nevertheless, conventional spectral clustering approaches lack the ability to process dynamic or time-varying data. Within a spectral framework, this work presents an overview of clustering techniques as well as their extensions to dynamic data analysis.

Spatial-Spectral Fuzzy K-Means Clustering for Remote Sensing Image Segmentation

“…As we know it, k-means clustering algorithm is hard, with overlapping data, the application of k-Means technique do not often result in high precision. Spectral clustering has shown to be a powerful technique for grouping and/or ranking data as well as a proper alternative for unlabeled problems, so, D.H. Peluffo-Ord´o˜nez et al [10] has an overview of clustering techniques based on spectral clustering problem of dynamic data analysis. Chang-an Liu and his team [11] improved spectral clustering algorithm (ISC) by applying the hill-climbing techniques to find the cluster centroids and reduce computing costs by merging the pixels have the same gray level.…”