print

Measuring explainability and trustworthiness of power quality disturbances classifiers using XAI - explainable artificial intelligence

author
Machlev, Ram
Perl, Michael
Belikov, Juri
Levy, Kfir
Levron, Yoash
statement of authorship
Ram Machlev, Michael Perl, Juri Belikov, Kfir Yehuda Levy, Yoash Levron
source
IEEE transactions on industrial informatics
publisher
IEEE
journal volume number month
vol. 18, 8
year of publication
2022
pages
p. 5127−5137
url
https://doi.org/10.1109/TII.2021.3126111
subject term
sügavõpe
tehisintellekt
kvaliteet
hindamine
keyword
convolutional neural network (CNN)
deep-learning (DL)
energy
evaluation metrics
Explainable Artificial Intelligence (XAI)
power quality disturbances (PQDs)
power
ISSN
1551-3203
notes
Bibliogr.: 36 ref
scientific publication
teaduspublikatsioon
classifier
1.1
Scopus
Journal metrics at Scopus
Article at Scopus
WOS
Journal metrics at WOS
Article at WOS
category (general)
Engineering
Computer science
category (sub)
Engineering. Control and systems engineering
Computer science. Computer science applications
Engineering. Electrical and electronic engineering
Computer science. Information systems
kvartiil
Q1
TTÜ department
tarkvarateaduse instituut
language
inglise
Uurimisrühm
Nonlinear control systems group
Centre for intelligent systems
Machlev, R., Perl, M., Belikov, J., Levy, K., Levron, Y. Measuring explainability and trustworthiness of power quality disturbances classifiers using XAI - explainable artificial intelligence // IEEE transactions on industrial informatics (2022) vol. 18, 8, p. 5127−5137. https://doi.org/10.1109/TII.2021.3126111