A Blind Source Separation Algorithm for the Processing and Classification of Electro-oculogram Data

Abnormalities in the oculomotor system are well known clinical symptoms in patients of several neurodegenerative diseases, including modifications in latency, peak velocity, and deviation in saccadic movements, causing changes in the waveform of the patient response. The changes in the morphology waveform suggest a higher degree of statistic independence in sick patients when compared to healthy individuals regarding the patient response to the visual saccadic stimulus modeled by means of digital generated saccade waveforms. The electro-oculogram records of six patients diagnosed with ataxia SCA2 (a neurodegenerative hereditary disease) and six healthy subjects used as control were processed to extract saccades. We propose the application of a blind source separation algorithm (or independent component analysis algorithm) in order to find significant differences in the obtained estimations between healthy and sick subjects. These results point out the validity of independent component analysis based techniques as an adequate tool in order to evaluate saccadic waveform changes in patients of ataxia SCA-2.

[1]  Andreas Stainer-Hochgatterer,et al.  EOG Pattern Recognition Trial for a Human Computer Interface , 2007, HCI.

[2]  Oleg V. Komogortsev,et al.  Eye movement prediction by Kalman filter with integrated linear horizontal oculomotor plant mechanical model , 2008, ETRA.

[3]  K. Müller,et al.  Automatic sleep stage classification using two-channel electro-oculography , 2007, Journal of Neuroscience Methods.

[4]  L J Schut,et al.  Abnormal ocular motor function predicts clinical diagnosis of familial ataxia , 1987, Neurology.

[5]  A Dürr,et al.  Eye movement abnormalities correlate with genotype in autosomal dominant cerebellar ataxia type I , 1998, Annals of neurology.

[6]  Sadık Kara,et al.  Classification of electro-oculogram signals using artificial neural network , 2006, Expert Syst. Appl..

[7]  A. Funase,et al.  Single trial analysis on saccade-related EEG signal , 2007, 2007 3rd International IEEE/EMBS Conference on Neural Engineering.

[8]  T. Yokota,et al.  Unusual blink reflex with four components in a patient with periodic ataxia , 2004, Journal of Neurology.

[9]  C.G. Puntonet,et al.  Adaptive and heuristic approaches for nonlinear source separation , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[10]  Dinesh Kumar,et al.  Classification of EOG for human computer interface , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[11]  Carlos G. Puntonet,et al.  Post-nonlinear blind source separation using methaheuristics , 2003 .

[12]  M. Almaguer,et al.  Psychological Aspects of Presymptomatic Diagnosis of Spinocerebellar Ataxia Type 2 in Cuba , 2007, Public Health Genomics.

[13]  Hubert Kimmig,et al.  Eye movement abnormalities in spinocerebellar ataxia type 17 (SCA17) , 2007, Neurology.

[14]  Ahmet Alkan,et al.  Classification of EEG Recordings by Using Fast Independent Component Analysis and Artificial Neural Network , 2008, Journal of Medical Systems.

[15]  Jörg B. Schulz,et al.  Fixation instability and oculomotor abnormalities in Friedreich's ataxia , 1995, Journal of Neurology.

[16]  Terrence J. Sejnowski,et al.  Complex Independent Component Analysis of Frequency-Domain Electroencephalographic Data , 2003, Neural Networks.

[17]  Shirley Hansen,et al.  Dominantly inherited olivopontocerebellar atrophy from eastern Cuba Clinical, neuropathological, and biochemical findings , 1989, Journal of the Neurological Sciences.

[18]  N Hironaga,et al.  Monitoring of eye movement and its use for artifact elimination , 2004 .

[19]  Nicola Vanello,et al.  Independent component analysis applied to the removal of motion artifacts from electrocardiographic signals , 2008, Medical & Biological Engineering & Computing.

[20]  I Sobue,et al.  [Analysis of the abnormal ocular movements in spinocerebellar degenerations and the influence of the thyrotropin releasing hormone (author's transl)]. , 1980, Rinsho shinkeigaku = Clinical neurology.

[21]  J. Dichgans,et al.  Autosomal dominant cerebellar ataxia type I: oculomotor abnormalities in families with SCA1, SCA2, and SCA3 , 1999, Journal of Neurology.

[22]  Elizabeth L Irving,et al.  Horizontal saccade dynamics across the human life span. , 2006, Investigative ophthalmology & visual science.

[23]  Jean-Francois Cardoso,et al.  Source separation using higher order moments , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[24]  Wolfgang Heide,et al.  Slow saccades and other eye movement disorders in spinocerebellar atrophy type 1 , 1997, Journal of Neurology.

[25]  César Sánchez,et al.  Convolutive Blind Source Separation Algorithms Applied to the Electrocardiogram of Atrial Fibrillation: Study of Performance , 2007, IEEE Transactions on Biomedical Engineering.

[26]  Luis E. Almaguer Mederos,et al.  Electrophysiological features in patients and presymptomatic relatives with spinocerebellar ataxia type 2. , 2007, Journal of the neurological sciences.

[27]  A.K. Barros,et al.  ECG Data Compression by Independent Component Analysis , 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

[28]  Khosrow Behbehani,et al.  EOG and EMG: Two Important Switches in Automatic Sleep Stage Classification , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[29]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .