Title
Realizacija servisa pametnog zdravstva i njihova integracija u koncept pametnih gradova
Creator
Avdić, Aldina, 1987-
CONOR:
29219175
Copyright date
2021
Object Links
Select license
Autorstvo-Nekomercijalno-Bez prerade 3.0 Srbija (CC BY-NC-ND 3.0)
License description
Dozvoljavate samo preuzimanje i distribuciju dela, ako/dok se pravilno naznačava ime autora, bez ikakvih promena dela i bez prava komercijalnog korišćenja dela. Ova licenca je najstroža CC licenca. Osnovni opis Licence: http://creativecommons.org/licenses/by-nc-nd/3.0/rs/deed.sr_LATN. Sadržaj ugovora u celini: http://creativecommons.org/licenses/by-nc-nd/3.0/rs/legalcode.sr-Latn
Language
Serbian
Cobiss-ID
Theses Type
Doktorska disertacija
description
Datum odbrane: 15.10.2021.
Other responsibilities
član komisije
Stoimenov, Leonid
član komisije
Bogdanović, Miloš
član komisije
Marovac, Ulfeta
član komisije
Gajić, Dušan
Academic Expertise
Prirodno-matematičke nauke
Academic Title
-
University
Univerzitet u Nišu
Faculty
Elektronski fakultet
Group
Katedra za računarstvo
Alternative title
Realization of smart health services and their integration into the concept of smart cities
Publisher
[A. R. Avdić]
Format
174 lista
description
Biografija autora: list 174,
Bibliografija: list. 150-165.
description
Medical Informatics, Natural Language Processing; Text mining
Abstract (en)
The development of information technologies has contributed
to the emergence of the concept of a smart city, and one of the
components of this concept is smart health. This component is
important because smart cities directly or indirectly affect the health
of residents.
The main contributions of this doctoral dissertation are a
proposal of a software platform that integrates existing public health
services as well as new e-health services, a proposal for a uniform
way of integrating heterogeneous smart health services into a smart
city, and a proposal and implementation of methods for labelling
terms in medical texts, based on artificial intelligence, without which
part of the smart health service could not be realized in an efficient
way.
The above-mentioned software platform combines the smart
health services that will be proposed (services for information and
prevention of diseases, epidemic control, search of medical
documents, automatic questionnaire processing, air pollution
monitoring, labelling of medical texts, organization of screening
programs, etc.). These services are created based on input data of
different types (sensor data on locations, air pollution, text from
documents and medical information systems and data collected by
crowdsourcing, data from relational and non-relational databases), so
it is necessary to integrate these heterogeneous services in uniform
way.
Part of the proposed e-health services is based on data
processing in medical information systems as well as medical text
documents in the Serbian language. Methods for normalization,
labelling and classification of terms in the Serbian language are a
prerequisite for the successful implementation of these services, and
within this dissertation methods are proposed and implemented whose
F1-score is 0.9082, which is an excellent result compared to methods
for this purpose in other languages. For their implementation, it is
necessary to use artificial intelligence methods, such as natural
language processing, data and text mining, machine learning, etc.
Some of the proposed e-health services are practically implemented
and integrated into the smart city concept.
Authors Key words
pametni gradovi, e-zdravstvo, pametno zdravstvo, servisi pametnog
zdravstva, istraživanje teksta, srpski jezik, mašinsko učenje
Authors Key words
smart cities, e-health, smart health, smart health services, text mining,
Serbian language, machine learning
Classification
(005.21:711.4+614.2):004.8+(004.431.2+811.163.41)(043.3)
Subject
T120
Type
Tekst
Abstract (en)
The development of information technologies has contributed
to the emergence of the concept of a smart city, and one of the
components of this concept is smart health. This component is
important because smart cities directly or indirectly affect the health
of residents.
The main contributions of this doctoral dissertation are a
proposal of a software platform that integrates existing public health
services as well as new e-health services, a proposal for a uniform
way of integrating heterogeneous smart health services into a smart
city, and a proposal and implementation of methods for labelling
terms in medical texts, based on artificial intelligence, without which
part of the smart health service could not be realized in an efficient
way.
The above-mentioned software platform combines the smart
health services that will be proposed (services for information and
prevention of diseases, epidemic control, search of medical
documents, automatic questionnaire processing, air pollution
monitoring, labelling of medical texts, organization of screening
programs, etc.). These services are created based on input data of
different types (sensor data on locations, air pollution, text from
documents and medical information systems and data collected by
crowdsourcing, data from relational and non-relational databases), so
it is necessary to integrate these heterogeneous services in uniform
way.
Part of the proposed e-health services is based on data
processing in medical information systems as well as medical text
documents in the Serbian language. Methods for normalization,
labelling and classification of terms in the Serbian language are a
prerequisite for the successful implementation of these services, and
within this dissertation methods are proposed and implemented whose
F1-score is 0.9082, which is an excellent result compared to methods
for this purpose in other languages. For their implementation, it is
necessary to use artificial intelligence methods, such as natural
language processing, data and text mining, machine learning, etc.
Some of the proposed e-health services are practically implemented
and integrated into the smart city concept.
“Data exchange” service offers individual users metadata transfer in several different formats. Citation formats are offered for transfers in texts as for the transfer into internet pages. Citation formats include permanent links that guarantee access to cited sources. For use are commonly structured metadata schemes : Dublin Core xml and ETUB-MS xml, local adaptation of international ETD-MS scheme intended for use in academic documents.