To access the full text documents, please follow this link: http://hdl.handle.net/2099.1/11323

Advanced Statistical Machine Learning Methods for the Analysis of Neurophysiologic Data with Medical Application
Amengual Roig, Julià Lluís
Vellido Alcacena, Alfredo; Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics
Transcranial magnetic stimulation procedures use a magnetic field to carry a short-lasting electricalcurrent pulse into the brain, where it stimulates neurons, particularly in superficial regionsof the cerebral cortex. It is a powerfull tool to calculate several parameters related to the intracorticalexcitability and inhibition of the motor cortex. The cortical silent period (CSP), evokedby magnetic stimulation, corresponds to the suppression of muscle activity for a short period aftera muscle response to a magnetic stimulation. The duration of the CSP is paramount to assessintracortical inhibition, and it is known to be correlated with the prognosis of stroke patients’motor ability. Current mechanisms to estimate the duration of the CSP are mostly based on theanalysis of raw electromyographical (EMG) signal and they are very sensitive to the presence ofnoise.This master thesis is devoted to the analysis of the EMG signal of stroke patients under rehabilitation.The use of advanced statistical machine learning techniques that behave robustly inthe presence of noise for this analysis allows us to accurately estimate signal parameters suchas the CSP. The research reported in this thesis provides us with a first evidence about theirapplicability in other areas of neuroscience.
2011-03-11
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
Cerebral embolism and thrombosis
Brain stimulation
Electromiography
Stroke
Variational Bayesian Generative
Topograp of Variability
Silent Periohic Mapping
Embòlia i trombosi cerebral
Cervell -- Estimulació
Open Access
Research/Master Thesis
Universitat Politècnica de Catalunya
         

Show full item record

 

Coordination

 

Supporters