Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Nadiya Shvai"'
Publikováno v:
IET Intelligent Transport Systems, Vol 17, Iss 1, Pp 243-254 (2023)
Abstract One of the main challenges in developing machine learning (ML) applications is the lack of labeled and balanced datasets. In the literature, different techniques tackle this problem via augmentation, rendering, and over‐sampling. Still, th
Externí odkaz:
https://doaj.org/article/d08435c536c64032897442d4a66525ad
Publikováno v:
IET Intelligent Transport Systems. 17:243-254
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a3ec2f8d81228d44aea06c9ff617a5b
https://doi.org/10.1049/itr2.12251
https://doi.org/10.1049/itr2.12251
Publikováno v:
Metaheuristics ISBN: 9783031265037
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd821818c8b707bc707e4e22c6db7594
https://doi.org/10.1007/978-3-031-26504-4_16
https://doi.org/10.1007/978-3-031-26504-4_16
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25a72f37c2871aa2083648a61f226d3f
https://doi.org/10.1145/3520304.3528819
https://doi.org/10.1145/3520304.3528819
Publikováno v:
Linear Algebra and its Applications. 614:455-499
We give new proofs of several known results about perturbations of matrix pencils. In particular, we give a direct and constructive proof of Andrzej Pokrzywa's theorem (1983), in which the closure of the orbit of each Kronecker canonical matrix penci
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8ffd191fa5788c8e230af8c4926ff3bf
https://doi.org/10.1016/j.laa.2020.12.009
https://doi.org/10.1016/j.laa.2020.12.009
Publikováno v:
Expert Systems with Applications. 213:118947
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::592bd897752b0ccc8042844a9650fa5d
https://doi.org/10.1016/j.eswa.2022.118947
https://doi.org/10.1016/j.eswa.2022.118947
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 21:1288-1297
In this paper, a real-world problem of the vehicle-type classification for automatic toll collection (ATC) is considered. This problem is very challenging because any loss of accuracy even of the order of 1% quickly turns into a significant economic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf543e7b45e72372f27385df2f335c62
https://doi.org/10.1109/tits.2019.2906821
https://doi.org/10.1109/tits.2019.2906821
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::025e4eaa67924534ef07577fde14b08e
https://doi.org/10.1109/icip42928.2021.9506188
https://doi.org/10.1109/icip42928.2021.9506188
Publikováno v:
GECCO Companion
This paper introduces Hyper-FDA: the application of the meta-heuristic "Fractal Decomposition Algorithm" (FDA) to the optimization of the hyperparameters of deep neural network architectures. FDA is a metaheuristic that was recently proposed to solve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df6a6a1e03cd22b5864e17590167bb53
https://doi.org/10.1145/3377929.3390056
https://doi.org/10.1145/3377929.3390056