Towards Visualizing Hidden Structures - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Towards Visualizing Hidden Structures

Abstract

There is an increasing need to quickly understand the contents log data. A wide range of patterns can be computed and provide valuable information: for example existence of repeated sequences of events or periodic behaviors. However pattern mining techniques often produce many patterns that have to be examined one by one, which is time consuming for experts. On the other hand, visualization techniques are easier to understand , but cannot provide the in-depth understanding provided by pattern mining approaches. Our contribution is to propose a novel visual analytics method that allows to immediately visualize hidden structures such as repeated sets/sequences and periodicity, allowing to quickly gain a deep understanding of the log.
Fichier principal
Vignette du fichier
ICDM_phdForum.pdf (946.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01407664 , version 1 (02-12-2016)

Identifiers

  • HAL Id : hal-01407664 , version 1

Cite

Rémy Dautriche, Alexandre Termier, Renaud Blanch, Miguel Santana. Towards Visualizing Hidden Structures. International Conference on Data Mining (ICDM) / PhD Forum, 2016, Barcelone, Spain. ⟨hal-01407664⟩
246 View
200 Download

Share

Gmail Facebook X LinkedIn More