Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros











Base de dados
Assunto principal
Intervalo de ano de publicação
1.
Artif Intell Med ; 136: 102477, 2023 02.
Artigo em Inglês | MEDLINE | ID: mdl-36710064

RESUMO

Anemia is a condition in which the oxygen-carrying capacity of red blood cells is insufficient to meet the body's physiological needs. It affects billions of people worldwide. An early diagnosis of this disease could prevent the advancement of other disorders. Traditional methods used to detect anemia consist of venipuncture, which requires a patient to frequently undergo laboratory tests. Therefore, anemia diagnosis using noninvasive and cost-effective methods is an open challenge. The pallor of the fingertips, palms, nail beds, and eye conjunctiva can be observed to establish whether a patient suffers from anemia. This article addresses the above challenges by presenting a novel intelligent system, based on machine learning, that supports the automated diagnosis of anemia. This system is innovative from different points of view. Specifically, it has been trained on a dataset that contains eye conjunctiva photos of Indian and Italian patients. This dataset, which was created using a very strict experimental set, is now made available to the Scientific Community. Moreover, compared to previous systems in the literature, the proposed system uses a low-cost device, which makes it suitable for widespread use. The performance of the learning algorithms utilizing two different areas of the mucous membrane of the eye is discussed. In particular, the RUSBoost algorithm, when appropriately trained on palpebral conjunctiva images, shows good performance in classifying anemic and nonanemic patients. The results are very robust, even when considering different ethnicities.


Assuntos
Anemia , Humanos , Anemia/diagnóstico , Túnica Conjuntiva , Palidez/diagnóstico , Algoritmos
2.
Entropy (Basel) ; 22(5)2020 May 08.
Artigo em Inglês | MEDLINE | ID: mdl-33286304

RESUMO

In order to manage spreadability for quantum stochastic processes, we study in detail the structure of the involved monoids acting on the index-set of all integers Z , that is that generated by left and right hand-side partial shifts, the monoid of all strictly increasing maps whose range has finite complement, and finally the collection of all strictly increasing maps of Z . We show that such three monoids are strictly ordered, and the second-named one is the semidirect product between the first and the action of Z generated by the one-step shift. Even if the definition of a spreadable stochastic process is provided in terms of the invariance of the finite joint distributions under the natural action of the last monoid on the indices, we see that spreadability can be directly stated in terms of invariance with respect to the action of the first monoid. Concerning the stochastic processes involving the concrete boolean C ∗ -algebra generated by the annihilators acting on the boolean Fock space (i.e., the concrete C ∗ -algebra satisfying the boolean commutation relations), we study their spreadability directly in terms of the invariance under the monoid generated by all strictly increasing maps whose range has finite complement because, for this case, such an investigation appears more direct and manageable. Finally, we present the version of the Ryll-Nardzewski theorem for the boolean case, establishing that spreadable, exchangeable and stationary stochastic processes coincide, and describing their common structure.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA