TOWARDS VISUAL DATA MINING

François Poulet

2004

Abstract

In this paper, we present our work in a new data mining approach called Visual Data Mining (VDM). This new approach tries to involve the user (being the data expert not a data mining or analysis specialist) more intensively in the data mining process and to increase the part of the visualisation in this process. The visualisation part can be increased with cooperative tools: the visualisation is used as a pre- or post-processing step of usual (automatic) data mining algorithms, or the visualisation tools can be used instead of the usual automatic algorithms. All these topics are addressed in this paper with an evaluation of the algorithms presented and a discussion of the interactive algorithms compared with automatic ones. All this work must be improved in order to allow the data specialists to efficiently use these kinds of algorithms to solve their problems.

Paper Citation

in Harvard Style

Poulet F. (2004). TOWARDS VISUAL DATA MINING . In Proceedings of the Sixth International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 972-8865-00-7, pages 349-356. DOI: 10.5220/0002639703490356

in Bibtex Style

@conference{iceis04,
author={François Poulet},
title={TOWARDS VISUAL DATA MINING},
booktitle={Proceedings of the Sixth International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2004},
pages={349-356},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002639703490356},
isbn={972-8865-00-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Sixth International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - TOWARDS VISUAL DATA MINING
SN - 972-8865-00-7
AU - Poulet F.
PY - 2004
SP - 349
EP - 356
DO - 10.5220/0002639703490356