Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Eva Weigl"'
Autor:
Parastoo Kheiroddin, Patricia Schöberl, Michael Althammer, Ezgi Cibali, Thea Würfel, Hannah Wein, Birgit Kulawik, Heike Buntrock-Döpke, Eva Weigl, Silvia Gran, Magdalena Gründl, Jana Langguth, Benedikt Lampl, Guido Judex, Jakob Niggel, Philipp Pagel, Thomas Schratzenstaller, Wulf Schneider-Brachert, Susanne Gastiger, Mona Bodenschatz, Maike Konrad, Artem Levchuk, Cornelius Roth, David Schöner, Florian Schneebauer, René Rohrmanstorfer, Marcus P. Dekens, Susanne Brandstetter, Johannes Zuber, Daniel Wallerstorfer, Andreas Burkovski, Andreas Ambrosch, Thomas Wagner, Michael Kabesch
Publikováno v:
Frontiers in Pediatrics, Vol 9 (2021)
Background: Opening schools and keeping children safe from SARS-CoV-2 infections at the same time is urgently needed to protect children from direct and indirect consequences of the COVID-19 pandemic. To achieve this goal, a safe, efficient, and cost
Externí odkaz:
https://doaj.org/article/118cb8ca56754fc8805e0cdf7b6b3077
Publikováno v:
Information Sciences. :127-151
In classification-based stream mining, drift detection is essential in order to (i) inform operators when unintended system changes occur and (ii) make classifier updates more flexible when changes are intentional. Current detection approaches usuall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfea07c453089a626b99ea3be3019e77
https://doi.org/10.1016/j.ins.2016.03.034
https://doi.org/10.1016/j.ins.2016.03.034
Publikováno v:
Machine Vision and Applications. 27:103-127
Classification of detected events is a central component in state-of-the-art surface inspection systems that still relies on manual parametrization. While machine-learned classifiers promise supreme accuracy, their reliability depends on complete and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3432dd9dfe9a0530194ed06b9ef35996
https://doi.org/10.1007/s00138-015-0731-9
https://doi.org/10.1007/s00138-015-0731-9
Publikováno v:
Applied Soft Computing. 35:558-582
Graphical abstractDisplay Omitted HighlightsEvolving fuzzy classifiers being able to integrate new event types in visual inspection on-line and on-the-fly.Class decomposition strategy for fast and stable integration of new classes.Generalized fuzzy r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::500a45bf5d2bef8ed96f1618e2ea0656
https://doi.org/10.1016/j.asoc.2015.06.038
https://doi.org/10.1016/j.asoc.2015.06.038
Publikováno v:
EAIS
Drift detection is an important issue in classification-based stream mining in order to be able to inform the operators in case of unintended changes in the system. Usually, current detection approaches rely on the assumption to have fully supervised
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cf9011c74e136aac8c98026710b8f88f
https://doi.org/10.1109/eais.2015.7368802
https://doi.org/10.1109/eais.2015.7368802
Publikováno v:
FUZZ-IEEE
In this paper, we propose a fast and economic strategy for the integration of new classes on the fly into evolving fuzzy classifiers (EFC) during data stream mining processes. Fastness addresses the assurance that a newly arising class in the stream
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5444c461e813cc978c3b28bafabb6e3b
https://doi.org/10.1109/fuzz-ieee.2015.7337846
https://doi.org/10.1109/fuzz-ieee.2015.7337846
Publikováno v:
Twelfth International Conference on Quality Control by Artificial Vision 2015.
While composite materials are increasingly used in modern industry, the quality control in terms of vision-based surface inspection remains a challenging task. Due to the often complex and three-dimensional structures, a manual inspection of these co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::803cfb569a8a95c90a2a718c6a99ae33
https://doi.org/10.1117/12.2182750
https://doi.org/10.1117/12.2182750
Publikováno v:
ICMLA
In this paper, we are dealing with the automatic inclusion of new event types in visual inspection systems. Within the context of image classification for recognizing "OK" and "not OK" parts, a certain event can be directly associated with a class, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0663cecc58034ad112254ca6a22bd8b
https://doi.org/10.1109/icmla.2014.85
https://doi.org/10.1109/icmla.2014.85