Cluster Validity Through Graph-based Boundary Analysis
نویسندگان
چکیده
Gaining confidence that a clustering algorithm has produced meaningful results and not an accident of its usually heuristic optimization is central to data mining. This is the issue of cluster validity. We propose here a method by which proximity graphs are used to effectively detect border points and measure the margin between clusters. With analysis of boundary situation, we design a framework and relevant working principles to evaluate the separation and compactness in the clustering results. The method can obtain an insight into the internal structure in clustering result.
منابع مشابه
On the Relation Between Low Density Separation, Spectral Clustering and Graph Cuts
One of the intuitions underlying many graph-based methods for clustering and semi-supervised learning, is that class or cluster boundaries pass through areas of low probability density. In this paper we provide some formal analysis of that notion for a probability distribution. We introduce a notion of weighted boundary volume, which measures the length of the class/cluster boundary weighted by...
متن کاملShot boundary detection in videos using Graph Cut Sets
The Shot Boundary Detection (SBD) is an early step for most of the video applications involving understanding, indexing, characterization, or categorization of video. The SBD is temporal video segmentation and it has been an active topic of research in the area of content based video analysis. The research efforts have resulted in a variety of algorithms. The major methods that have been used f...
متن کاملA Learnable Spectral Memory Graph for Recognition and Segmentation
Image segmentation is often treated as an unsupervised task. Segmentation by human, in contrast, relies heavily on memory to produce an object-like clustering, through a mechanism of controlled hallucination. This paper presents a learning algorithm for memory-driven object segmentation and recognition. We propose a general spectral graph learning algorithm based on gradient descent in the spac...
متن کاملModified Dunn’s cluster validity index based on graph theory
Clustering methods serve as common tools for efficient data analysis in many fields of science. The essential, yet often neglected, step in the cluster analysis is validation of the clustering results. This paper presents a novel cluster validity index, which is the modification of the well-known Dunn’s index. Our proposal is based on its generalization considering the shortest paths between da...
متن کاملHighly Coherent Pattern Identification Using Graph-based Clustering
This paper presents an enhanced graph based parameter independent clustering technique. The algorithm produces highly coherent clusters in terms of visual representation and cluster validity measures. The technique finds highly coherent patterns of genes having high biological relevance. The method was tested on four real life datasets and the results compared with those of other similar algori...
متن کامل