scholarly journals Analysis and classification of collective behavior using generative modeling and nonlinear manifold learning

2013 ◽  
Vol 336 ◽  
pp. 185-199 ◽  
Author(s):  
Sachit Butail ◽  
Erik M. Bollt ◽  
Maurizio Porfiri
Author(s):  
S. Rajintha. A. S. Gunawardena ◽  
Fei He ◽  
Ptolemaios Sarrigiannis ◽  
Daniel J. Blackburn

AbstractIn this work, nonlinear temporal features from multi-channel EEGs are used for the classification of Alzheimer’s disease patients from healthy individuals. This was achieved by temporal manifold learning using Gaussian Process Latent Variable Models (GPLVM) as a nonlinear dimensionality reduction technique. Classification of the extracted features was undertaken using a nonlinear Support Vector Machine. Comparisons were made against the linear counterpart, Principle Component Analysis while exploring the effect of the time window or EEG epoch length used. It was demonstrated that temporal manifold learning using GPLVM is better in extracting features that attain high separability and prediction accuracy. This work aims to set the significance of using GPLVM temporal manifold learning for EEG feature extraction in the classification of Alzheimer’s disease.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 207112-207133
Author(s):  
Lorenzo Manoni ◽  
Claudio Turchetti ◽  
Laura Falaschetti

Author(s):  
Katherine R. Gray ◽  
Paul Aljabar ◽  
Rolf A. Heckemann ◽  
Alexander Hammers ◽  
Daniel Rueckert

2020 ◽  
Vol 31 (1) ◽  
Author(s):  
Camila Cristina Fonseca Bicalho ◽  
Israel Teoldo da Costa ◽  
Franco Noce ◽  
Varley Teoldo Costa

The aimed of the study were: (a) to construct a reference table for burnout in soccer athletes of the U-20 category and (b) to verify the individual oscillations in the perception of these athletes in relation to burnout over three periods of the sports season. The 53 sub-20 soccer athletes participated. The Atlhete Burnout Questionnaire, brazilian version, was applied to athletes during training, competition and vacation periods of the sports season. A reference table was built for under-20 soccer athletes for each assessed period. Fluctuations were found in the average values of the total burnout frequency of the athletes during the 3 periods: training (=1.35 ± 0.13 and =2.11 ± 0.19), competition (=1.26 ± 0.13 and =2.27 ± 0.24) and vacation (=1.27 ± 0.14 and = 2.18 ± 0.28) Based on this table and the individual classification of each athlete, it was observed that 32 athletes presented fluctuations in the perception of burnout during the sports season and 21 athletes did not show fluctuations in feelings of burnout during the three evaluation periods. The period with the highest number of athletes (n = 17) with a high level of burnout was the training period. It is concluded that it is not possible to establish a single and collective behavior regarding the fluctuations of burnout levels in athletes of the U-20 category during a sports season, and that the category reference table contributes to a greater accuracy of the burnout evaluation in every season.


2006 ◽  
pp. 43-60
Author(s):  
Richard T. LaPiere
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document