Pulse component modification detection in spino cerebellar ataxia 2 using ICA

Authors:
Rodolfo V. García;Fernando Rojas;Jesús Gonz´lez;Luis Velázquez;Roberto Rodríguez;Roberto Becerra;Olga Valenzuela
Affiliations:
Network Department, University of Holguín, Cuba;Dept. of Computer Architecture and Technology, University of Granada, Spain;Dept. of Computer Architecture and Technology, University of Granada, Spain;Centre for the Research and Rehabilitation of Hereditary Ataxias, Holguín, Cuba;Centre for the Research and Rehabilitation of Hereditary Ataxias, Holguín, Cuba;Network Department, University of Holguín, Cuba;Dept. of Applied Mathematics, University of Granada
Venue:
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
Year:
2011

Citing 1
Cited 0

An information-maximization approach to blind separation and blind deconvolution

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Anomalies in the oculomotor system are well known symptoms in patients with severe Spino Cerebellar Ataxia 2 form of autosomal dominant cerebellar ataxias (ADCA), including the main parameters used to describe saccadic movements. Also a combination of a pulse and step components constitutes an accepted model of the saccadic generation system, In the present work, Independent Component Analysis (ICA) is used to separate both components, revealing a significant difference in the time of the pulse component to reach its maximum value. This result suggests its use in order to obtain a classification tool to diagnose this disease. Five electro-oculographic records of patients of SCA2 ataxia and five control subjects were processed with the ICA based algorithm with this objective.