Home // ICCGI 2012, The Seventh International Multi-Conference on Computing in the Global Information Technology // View article

Unsupervised Information-Based Feature Selection for Speech Therapy Optimization by Data Mining Techniques

Authors:
Mirela Danubianu
Valentin Popa
Iolanda Tobolcea

Keywords: data mining, feature selection, feature relevance, feature redundancy, speech disorder therapy

Abstract:
Data mining was proven to be an efficient way to find new and useful knowledge in data. Since data dimensionality has major implications on the performance of the algorithms used, one of the data pre-processing operations refers to reducing the number of features. One way to do that is feature selection based on their relevance and redundancy analysis. This paper presents a feature selection method which is applied on data provided by TERAPERS – a computer-based speech therapy system for Romanian children suffering of dyslalia.

Pages: 206 to 211

Copyright: Copyright (c) IARIA, 2012

Publication date: June 24, 2012

Published in: conference

ISSN: 2308-4529

ISBN: 978-1-61208-202-8

Location: Venice, Italy

Dates: from June 24, 2012 to June 29, 2012