Share Email Print
cover

Proceedings Paper

Search of hidden properties in sensor data using recurrent neural networks
Author(s): Lissette Lemus del Cueto; Nancy Lopez; Luis J. Barrios; Roberto Cruz Moreno
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Sensor data can be mined to discover a description of an implicit property in an application domain. Main problems in the sensor data domain are the huge volume of noisy data and, therefore, the difficulty to locate the relevant information. KDD is the field where these problems are being addressed. This paper proposes a feature selection approach to discover relevant features, which will characterize the unknown property. The obtained description improves the expert knowledge and makes up a base for the prediction task. The feature selection task becomes intractable when the features set is large. Recurrent neural networks have shown to be very useful to obtain the global minimum of hard problems. This paper proposes two recurrent neural network models for feature selection: the graph model and the cluster model. Experiments show the advantage of the new methods, by comparing them with heuristic methods like RELIEF-F, DTM, and the Wrapper approach. We have selected databases from the UCI Repository and experimental data from steel machining processes. The new methods provide better solutions than the heuristic methods, and solve the tradeoff between accuracy and efficiency, as well as their generalization capability, which gives a solution of the noise problem.

Paper Details

Date Published: 25 February 1999
PDF: 8 pages
Proc. SPIE 3695, Data Mining and Knowledge Discovery: Theory, Tools, and Technology, (25 February 1999); doi: 10.1117/12.339971
Show Author Affiliations
Lissette Lemus del Cueto, CSIC Instituto de Automatica Industrial (Spain)
Nancy Lopez, Univ. of Antioquia and Institute of Cybernetics, Mathematics and Physics (Cuba) (Colombia)
Luis J. Barrios, Consejo Superior de Investigaciones Cientificas (Spain)
Roberto Cruz Moreno, Institute of Nuclear Sciences and Technology (Cuba)


Published in SPIE Proceedings Vol. 3695:
Data Mining and Knowledge Discovery: Theory, Tools, and Technology
Belur V. Dasarathy, Editor(s)

© SPIE. Terms of Use
Back to Top