Title | ||
---|---|---|
Hierarchical Mahalanobis Distance Clustering Based Technique for Prognostics in Applications Generating Big Data |
Abstract | ||
---|---|---|
In this paper, a Mahalanobis Distance (MD) based hierarchical clustering technique is proposed for prognostics in applications generating Big Data. This technique is shown to have the ability to overcome certain challenges concerning Big Data analysis. In this technique, Mahalanobis Taguchi Strategy is utilized to organize the MD values into a tree and hierarchical clustering approach is then applied to obtain an overall MD value. This overall MD value is trended over time for prediction. Simulation results are presented to demonstrate the efficiency of the proposed technique. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/SSCI.2015.82 | 2015 IEEE Symposium Series on Computational Intelligence |
Keywords | Field | DocType |
hierarchical Mahalanobis distance clustering based technique,MD based hierarchical clustering technique,Big Data analysis,Mahalanobis Taguchi strategy | Hierarchical clustering,Data mining,Prognostics,Computer science,Signal-to-noise ratio,Mahalanobis distance,Taguchi methods,Cluster analysis,Big data | Conference |
ISBN | Citations | PageRank |
978-1-4799-7560-0 | 0 | 0.34 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
r krishnan | 1 | 0 | 0.34 |
Sarangapani Jagannathan | 2 | 1136 | 94.89 |