Computation Cluster Validation in the Big Data Era
- Autori: Giancarlo, Raffaele; Utro, Filippo
- Anno di pubblicazione: 2017
- Tipologia: Capitolo o Saggio (Capitolo o saggio)
- OA Link: http://hdl.handle.net/10447/291370
Abstract
Data-driven class discovery, i.e., the inference of cluster structure in a dataset, is a fundamental task in Data Analysis, in particular for the Life Sciences. We provide a tutorial on the most common approaches used for that task, focusing on methodologies for the prediction of the number of clusters in a dataset. Although the methods that we present are general in terms of the data for which they can be used, we offer a case study relevant for Microarray Data Analysis