Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Iulian B. Ciocoiu"'
Publikováno v:
Sensors, Vol 24, Iss 17, p 5597 (2024)
The paper introduces a new FireAndSmoke open dataset comprising over 22,000 images and 93,000 distinct instances compiled from 1200 YouTube videos and public Internet resources. The scenes include separate and combined fire and smoke scenarios and a
Externí odkaz:
https://doaj.org/article/41ff699515d84f7fbdc2ef6549f97aa3
Autor:
Irina Pavel, Iulian B. Ciocoiu
Publikováno v:
Sensors, Vol 23, Iss 11, p 4996 (2023)
Reliable detection of COVID-19 from cough recordings is evaluated using bag-of-words classifiers. The effect of using four distinct feature extraction procedures and four different encoding strategies is evaluated in terms of the Area Under Curve (AU
Externí odkaz:
https://doaj.org/article/70d09899c86c4ff2b17bc349ea8c2ba2
Autor:
Iulian B. Ciocoiu, Nicolae Cleju
Publikováno v:
IEEE Access, Vol 8, Pp 218966-218981 (2020)
Targeting off-person ECG-based biometrics, we report a comparative analysis of identification accuracy and verification Equal Error Rate (EER) performances of four distinct types of spatial representations of ECG signals applied as inputs to Convolut
Externí odkaz:
https://doaj.org/article/cd5d9aa01c714740945783408501f1e4
Autor:
Iulian B. Ciocoiu, Hariton N. Costin
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2007 (2007)
Three different localized representation methods and a manifold learning approach to face recognition are compared in terms of recognition accuracy. The techniques under investigation are (a) local nonnegative matrix factorization (LNMF); (b) indepen
Externí odkaz:
https://doaj.org/article/4ad3dd2b635b47e28e155f2c7869b54c
Autor:
Irina Pavel, Iulian B. Ciocoiu
Publikováno v:
2022 E-Health and Bioengineering Conference (EHB).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3ad0a781081163d9f583107dd44e337
https://doi.org/10.1109/ehb55594.2022.9991276
https://doi.org/10.1109/ehb55594.2022.9991276
Autor:
Simona Condaragiu, Iulian B. Ciocoiu
Publikováno v:
2021 International Symposium on Signals, Circuits and Systems (ISSCS).
The paper presents a comparative analysis of five Convolutional Neural Networks (CNN’s) for reliable detection of COVID-19 from chest X-ray (CXR) images. The transfer learning approach is applied to a dataset compiled from public sources, aiming at
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6275328869e562bc19779f6f63c19599
https://doi.org/10.1109/isscs52333.2021.9497418
https://doi.org/10.1109/isscs52333.2021.9497418
Autor:
Nicolae Cleju, Iulian B. Ciocoiu
Publikováno v:
2020 International Symposium on Electronics and Telecommunications (ISETC).
We propose Preconditioned K-SVD, an algorithm for dictionary learning adapted for sparse coding with Least Squares Pursuit. The algorithm resembles K-SVD iterations but operates in a preconditioned signal space, which implies a different optimization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0417958ecda12a7815688fbbabffa8d8
https://doi.org/10.1109/isetc50328.2020.9301060
https://doi.org/10.1109/isetc50328.2020.9301060
Autor:
Iulian B. Ciocoiu
Publikováno v:
2019 6th International Symposium on Electrical and Electronics Engineering (ISEEE).
The paper focuses on several recent applications of deep learning approaches to a broad range of tasks, including a personal view on current trends, critical issues, and limitations of the technology.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::288b70927104f4c23c6877b818942f05
https://doi.org/10.1109/iseee48094.2019.9136131
https://doi.org/10.1109/iseee48094.2019.9136131
Autor:
Iulian B. Ciocoiu, Nicolae Cleju
Publikováno v:
EUSIPCO
We propose a novel greedy algorithm for $\ell_{0}$-based sparse signal recovery, inspired by Iterative Hard Thresholding, which alternates a gradient descent step towards minimizing the sparsity error with a projection step on the affine solution spa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::141f031bbc72a9c75b18aab018982e27
https://doi.org/10.23919/eusipco.2019.8902581
https://doi.org/10.23919/eusipco.2019.8902581
Autor:
Iulian B. Ciocoiu, Nicolae Cleju
Publikováno v:
2019 International Symposium on Signals, Circuits and Systems (ISSCS).
We propose two approaches for obtaining a more robust algorithm for sparse signal recovery based on combining two existing algorithms, Orthogonal Matching Pursuit and the related Least Squares Pursuit. The first approach relies on averaging the gradi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a97274ba9f793a5283be82cdf0f3d48
https://doi.org/10.1109/isscs.2019.8801742
https://doi.org/10.1109/isscs.2019.8801742