Abstract
Techniques are described herein for providing a coclustering algorithm that iteratively applies Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering with Jaccard distance to discover clusters of entities along with corresponding clusters of features. The algorithm provides a stable alternative to the existing coclustering algorithms that can discover distinct coclusters of different compactness beyond a threshold that can be controlled by the user. The algorithm may be used to discover patterns of syslog messages predictive of certain network device failures and simultaneously cluster the devices that encounter each of these patterns.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Das, Debasish; Nucci, Antonio; and Pandya, Jaykishan, "STABLE COCLUSTERING BY ITERATIVE DENSITY-BASED SPATIAL CLUSTERING OF APPLICATIONS WITH NOISE", Technical Disclosure Commons, (November 20, 2018)
https://www.tdcommons.org/dpubs_series/1690