Active Learning Approach for EEG Classification using Neural Networks: A review
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F19%3A00336838" target="_blank" >RIV/68407700:21460/19:00336838 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/EHB47216.2019.8970017" target="_blank" >https://doi.org/10.1109/EHB47216.2019.8970017</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/EHB47216.2019.8970017" target="_blank" >10.1109/EHB47216.2019.8970017</a>
Alternative languages
Result language
angličtina
Original language name
Active Learning Approach for EEG Classification using Neural Networks: A review
Original language description
Labelling of electroencephalography (EEG) recordings for further classification and analysis can be time consuming for a physician (expert), especially for long term monitoring (e.g. sleep stages). Active learning approach using machine learning classifiers seems to be a promising method for semi-automated label acquisition with expert in the loop as it can radically decrease the necessary training set needed for neural network to learn. A critical review of current state-of-the-art in active learning approach for EEG classification by neural networks is the goal of this paper. Studies using active learning in EEG address detection of specific graphoelements (artifacts, VEPs, epileptic spikes) or stages (sleep stages, drowsiness) or they optimized brain computer interface (BCI). Amount of the training set in the studies is reduced compared to a common classifier used as a golden standard (reduction differs from 40% to 80% of the set size).
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20601 - Medical engineering
Result continuities
Project
<a href="/en/project/GA17-20480S" target="_blank" >GA17-20480S: Temporal context in analysis of long-term non-stationary multidimensional signal</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
IEEE E-HEALTH AND BIOENGINEERING EHB 2019
ISBN
978-1-7281-2603-6
ISSN
—
e-ISSN
2575-5145
Number of pages
4
Pages from-to
—
Publisher name
Gr. T. Popa University of Medicine and Pharmacy
Place of publication
Iasi
Event location
Iasi
Event date
Nov 21, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000558648300147