Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Ingeniería
Print version ISSN 0121-750X
Abstract
MEDINA SALGADO, Boris and ALVAREZ LOPEZ, Ramón. Characterization of EEG Signals Using Wavelet Packet and Fuzzy Entropy in Motor Imagination Tasks. ing. [online]. 2017, vol.22, n.2, pp.226-238. ISSN 0121-750X. https://doi.org/10.14483/udistrital.jour.reving.2017.2.a04.
Context:
Clinical rhythm analysis on advanced signal processing methods is very important in medical areas such as brain disorder diagnostic, epilepsy, sleep analysis, anesthesia analysis, and more recently in braincomputer interfaces (BCI).
Method:
Wavelet transform package is used on this work to extract brain rhythms of electroencephalographic signals (EEG) related to motor imagination tasks. We used the Competition BCI 2008 database for this characterization. Using statistical functions we obtained features that characterizes brain rhythms, which are discriminated using different classifiers; they were evaluated using a 10fold cross validation criteria.
Results:
The classification accuracy achieved 81.11 % on average, with a degree of agreement of 61 %, indicating a ”suitablec¸oncordance, as it has been reported in the literature. An analysis of relevance showed the concentration of characteristics provided in the nodes as a result of Wavelet decomposition, as well as the characteristics that more information content contribute to improve the separability decision region for the classification task.
Conclusions:
The proposed method can be used as a reference to support future studies focusing on characterizing EEG signals oriented to the imagination of left and right hand movement, considering that our results proved to compared favourably to those reported in the literature.
Keywords : BCI; EEG; Wavelet Packet; Language: Spanish.