Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Konstantinos Makantasis"'
Autor:
Ioannis Georgoulas, Eftychios Protopapadakis, Konstantinos Makantasis, Dylan Seychell, Anastasios Doulamis, Nikolaos Doulamis
Publikováno v:
IEEE Access, Vol 11, Pp 124819-124832 (2023)
Hyperspectral data classification is one of the fundamental problems in remote sensing. Several algorithms based on supervised machine learning have been proposed to address it. The performance, however, of the proposed algorithms is inherently depen
Externí odkaz:
https://doaj.org/article/9df9e7a8f16e429f91e204b0dec9bbae
Autor:
Konstantinos Makantasis, Alexandros Georgogiannis, Athanasios Voulodimos, Ioannis Georgoulas, Anastasios Doulamis, Nikolaos Doulamis
Publikováno v:
IEEE Access, Vol 9, Pp 58609-58620 (2021)
An increasing number of emerging applications in data science and engineering are based on multidimensional and structurally rich data. The irregularities, however, of high-dimensional data often compromise the effectiveness of standard machine learn
Externí odkaz:
https://doaj.org/article/2a6eefc9a37545c8b561cea888e1e7c5
Autor:
Ioannis N. Tzortzis, Agapi Davradou, Ioannis Rallis, Maria Kaselimi, Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis
Publikováno v:
Diagnostics, Vol 12, Iss 10, p 2389 (2022)
In this study, we propose a tensor-based learning model to efficiently detect abnormalities on digital mammograms. Due to the fact that the availability of medical data is limited and often restricted by GDPR (general data protection regulation) comp
Externí odkaz:
https://doaj.org/article/ac7b6742ef524e7fa2c3e072671dca9f
How can we reliably transfer affect models trained in controlled laboratory conditions (in-vitro) to uncontrolled real-world settings (in-vivo)? The information gap between in-vitro and in-vivo applications defines a core challenge of affective compu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7df514315565356ff135cb12e02ce8ae
https://zenodo.org/record/7879192
https://zenodo.org/record/7879192
Affect modeling is viewed, traditionally, as the process of mapping measurable affect manifestations from multiple modalities of user input to affect labels. That mapping is usually inferred through end-to-end (manifestation-to-affect) machine learni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::233e03f73c9bc8ee49c9a50ca16691be
https://zenodo.org/record/7879155
https://zenodo.org/record/7879155
Publikováno v:
IEEE Conference on Games
Self-supervised learning (SSL) techniques have been widely used to learn compact and informative representations from high-dimensional complex data. In many computer vision tasks, such as image classification, such methods achieve state-of-the-art re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a7cc60eb153a6812aef7fe1335e126d
https://zenodo.org/record/7879268
https://zenodo.org/record/7879268
Publikováno v:
GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference
Stochastic gradient descent (SGD) is a premium optimization method for training neural networks, especially for learning objectively defined labels such as image objects and events. When a neural network is instead faced with subjectively defined lab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f7c5c85f4f629d54b6f1660d584ebb9
https://zenodo.org/record/7879220
https://zenodo.org/record/7879220
Autor:
Ioannis N. Tzortzis, Ioannis Rallis, Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis, Athanasios Voulodimos
Publikováno v:
29th IEEE International Conference on Image Processing (IEEE ICIP)
In Cultural Heritage, hyperspectral images are commonly used since they provide extended information regarding the optical properties of materials. Thus, the processing of such high-dimensional data becomes challenging from the perspective of machine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9a0443053ad9a837e228f6ebc907722
Publikováno v:
Advances in Visual Computing ISBN: 9783031207129
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::62df117a05a9700b763c8f85153cf40b
https://doi.org/10.1007/978-3-031-20713-6_25
https://doi.org/10.1007/978-3-031-20713-6_25
Publikováno v:
IET Intelligent Transport Systems. 14:13-24
In this work the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0939597c76de63ae1cf50be9e4c5c580
https://doi.org/10.1049/iet-its.2019.0249
https://doi.org/10.1049/iet-its.2019.0249