A Method to Obtain Parameters of One-Column Jansen–Rit Model Using Genetic Algorithm and Spectral Characteristics
| Autor: | Szczepan Paszkiel, Adam Łysiak |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
biofeedback
Rit model Mean squared error Feature vector Jansen–Rit model model parameters estimation EEG classification 01 natural sciences Signal lcsh:Technology one-column model lcsh:Chemistry 03 medical and health sciences 0302 clinical medicine 0103 physical sciences Range (statistics) genetic algorithm EEG frequency features General Materials Science 010301 acoustics Instrumentation lcsh:QH301-705.5 neural mass model Mathematics Fluid Flow and Transfer Processes Quantitative Biology::Neurons and Cognition Noise (signal processing) lcsh:T Jansen model Process Chemistry and Technology EEG modeling General Engineering Ranging lcsh:QC1-999 Computer Science Applications Nonlinear system Amplitude lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 lcsh:Engineering (General). Civil engineering (General) Algorithm 030217 neurology & neurosurgery lcsh:Physics |
| Zdroj: | Applied Sciences Volume 11 Issue 2 Applied Sciences, Vol 11, Iss 677, p 677 (2021) |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app11020677 |
| Popis: | In this paper, a method of obtaining parameters of one-column Jansen&ndash Rit model was proposed. Methods present in literature are focused on obtaining parameters in an on-line manner, producing a set of parameters for every point in time. The method described in this paper can provide one set of parameters for a whole, arbitrarily long signal. The procedure consists of obtaining specific frequency features, then minimizing mean square error of those features between the measured signal and the modeled signal, using genetic algorithm. This method produces an 8-element vector, which can be treated as an EEG signal feature vector specific for a person. The parameters which were being obtained are maximum postsynaptic potential amplitude, maximum inhibitory potential amplitude, ratio of the number of connections between particular neuron populations, the shape of a nonlinear function transforming the average membrane potential into the firing rate and the input noise range. The method shows high reproducibility (intraclass correlation coefficient for particular parameters ranging from 0.676 to 0.978) and accuracy (ranging from 0.662 to 0.863). It was additionally verified using EEG signal obtained for a single participant. This signal was measured using Emotiv EPOC+ NeuroHeadset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|