Algorithms for clustering data
Algorithms for clustering data
A Validity Measure for Fuzzy Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence
Self-organizing maps
ACM Computing Surveys (CSUR)
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition with Fuzzy Objective Function Algorithms
Pattern Recognition with Fuzzy Objective Function Algorithms
Fundamentals of Computer Alori
Fundamentals of Computer Alori
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance Evaluation of Some Clustering Algorithms and Validity Indices
IEEE Transactions on Pattern Analysis and Machine Intelligence
A large database of graphs and its use for benchmarking graph isomorphism algorithms
Pattern Recognition Letters - Special issue: Graph-based representations in pattern recognition
Validation indices for graph clustering
Pattern Recognition Letters - Special issue: Graph-based representations in pattern recognition
On clusterings-good, bad and spectral
FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science
Combining experts for anchorperson shot detection in news videos
Pattern Analysis & Applications
Graph-Theoretical Methods for Detecting and Describing Gestalt Clusters
IEEE Transactions on Computers
Assessing the performance of a graph-based clustering algorithm
GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Clustering NGN user behavior for anomaly detection
Information Security Tech. Report
| Hi-index | 0.00 |
Among all the different clustering approaches proposed so far, graph-based algorithms are particularly suited for dealing with data that does not come from a Gaussian or a spherical distribution. They can be used for detecting clusters of any size and shape without the need of specifying the actual number of clusters; moreover, they can be profitably used in cluster detection problems. Despite of the fact that graph-based methods are gaining more and more popularity in different scientific areas, the choice of an appropriate algorithm for a given application is still the most crucial task. In this paper, we then present a detailed performance evaluation of five different graph-based clustering approaches on a database of synthetically generated graphs. The main findings of such an analysis were that algorithms based on the Minimum Spanning Tree perform better than other approaches. Four of the algorithms selected for comparison have been chosen from the open literature. While these algorithms do not require the setting of the number of clusters, they need, however, some parameters to be provided by the user. So, as the fifth algorithm under comparison, we propose an approach that overcomes this limitation, proving to be an effective solution in real applications where a completely unsupervised method for cluster detection is desirable. This was confirmed by a further comparative analysis carried out on four datasets coming from the UCI Machine Learning Repository.