Data Dimensionality Reduction Framework for Data Mining

The database built by TERAPERS project contains a considerable volume of data about the personal or familial anamnesis, and regarding the process of personalized therapy of dyslalia. This data can be the starting point of data mining processes that could provide useful information for the design and adaptation of different therapies to obtain the maximum efficiency. Because data dimensionality affects the performances of data mining tasks, this paper presents two supervised feature selection methods to be used in the frame of an information system. These methods were validated by experiments in the classification of Romanian patients with speech disorders. Obtained results will be used to implement Logo-DM, which is intended to be a data mining system aiming to optimize the personalized therapy of dyslalia.