Stacked Autoencoders for the P300 Component Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43931861" target="_blank" >RIV/49777513:23520/17:43931861 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.3389/fnins.2017.00302" target="_blank" >http://dx.doi.org/10.3389/fnins.2017.00302</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3389/fnins.2017.00302" target="_blank" >10.3389/fnins.2017.00302</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Stacked Autoencoders for the P300 Component Detection

Popis výsledku v původním jazyce

Using a combination of unsupervised pre-training and subsequent fine-tuning, deep neural networks have become one of the most reliable classification methods. The aim of the experiments subsequently presented was to verify if deep learning-based models can also perform well for single trial P300 classification with possible application to P300-based brain-computer interfaces. The P300 data used were recorded in the EEG/ERP laboratory at the Department of Computer Science and Engineering, University of West Bohemia, and are publicly available. Stacked autoencoders were implemented and compared with some of the currently most reliable state-of-the-art methods, such as LDA and multi-layer perceptron. The parameters of stacked autoencoders were optimized empirically. Subsequently, fine-tuning using backpropagation was performed. The architecture of the neural network was 209-130-100-50-20-2. The classifiers were trained on a dataset merged from four subjects and subsequently tested on different 11 subjects without further training. The trained SAE achieved 69.2% accuracy that was higher (p &lt; 0.01) than the accuracy of MLP (64.9%) and LDA (65.9%). The recall of 58.8% was slightly higher when compared with MLP (56.2%) and LDA (58.4%).

Název v anglickém jazyce

Stacked Autoencoders for the P300 Component Detection

Popis výsledku anglicky

Using a combination of unsupervised pre-training and subsequent fine-tuning, deep neural networks have become one of the most reliable classification methods. The aim of the experiments subsequently presented was to verify if deep learning-based models can also perform well for single trial P300 classification with possible application to P300-based brain-computer interfaces. The P300 data used were recorded in the EEG/ERP laboratory at the Department of Computer Science and Engineering, University of West Bohemia, and are publicly available. Stacked autoencoders were implemented and compared with some of the currently most reliable state-of-the-art methods, such as LDA and multi-layer perceptron. The parameters of stacked autoencoders were optimized empirically. Subsequently, fine-tuning using backpropagation was performed. The architecture of the neural network was 209-130-100-50-20-2. The classifiers were trained on a dataset merged from four subjects and subsequently tested on different 11 subjects without further training. The trained SAE achieved 69.2% accuracy that was higher (p &lt; 0.01) than the accuracy of MLP (64.9%) and LDA (65.9%). The recall of 58.8% was slightly higher when compared with MLP (56.2%) and LDA (58.4%).

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Frontiers in Neuroscience

ISSN

1662-453X

e-ISSN

—

Svazek periodika

11

Číslo periodika v rámci svazku

302

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

9

Strana od-do

1-9

Kód UT WoS článku

000406529900001

EID výsledku v databázi Scopus

2-s2.0-85020069785