prikaz prve stranice dokumenta Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika
  Download
PDF 3.13 MB
master's thesis
Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika
2020. urn:nbn:hr:200:753885
Česnek, Filip
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Česnek, F. (2020). Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:753885

Česnek, Filip. "Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:753885

Česnek, Filip. "Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:753885

Česnek, F. (2020). 'Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 22 October 2021, https://urn.nsk.hr/urn:nbn:hr:200:753885

Česnek F. Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2021 October 22] Available at: https://urn.nsk.hr/urn:nbn:hr:200:753885

F. Česnek, "Web sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:753885

Islandora Bookmark - Please login to use this feature
Metadata
TitleWeb sustav za praćenje hitnih medicinskih stanja na temelju analize slike i generiranja prirodnog jezika
Title (english)Web system for monitoring medical emergencies based on image analysis and natural language generation
AuthorFilip Česnek
MentorGoran Martinović (mentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberŽeljko Hocenski (član povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2020-10-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Process Computing
Abstract
U ovom diplomskom radu modelirana je i izrađena web aplikacija za detekciju hitnih medicinskih stanja na temelju analize slike koristeći PoseNet model za detekciju položaja tijela, a korišteno je i načelo generiranja prirodnog jezika za sažimanje veće količine teksta koji predstavlja opis slučaja i upute za postupanje pri pojavi tog slučaja korištenjem web usluge MeaningCloud. Ostvareno je korisničko sučelje koje omogućuje prijavu korisnika, treniranje vlastitog modela strojnog učenja, spremanje vlastitog modela na računalo ili u bazu podataka, spremanje i uređivanje vlastitog skupa podataka za učenje, te evaluaciju vlastitih modela, kao i preddefiniranog modela koji detektira hitne medicinske slučajeve. Izrađena aplikacija ostvarena je pomoću Vue.js programskog okvira za izradu korisničkog sučelja, ml5.js biblioteke za strojno učenje, MeaningCloud usluge za sažimanje teksta, MongoDB baze podataka, te Node.js izvršnog okruženja kojim se ostvaruje programska podrška na strani poslužitelja.
Abstract (english)
In this paper, a web application for detecting medical emergencies was modeled and developed, using the PoseNet model for pose detection, as well as using the concept of natural language generation to summarize large bodies of text which contain medical case descriptions and instructions on what to do in the case of a described emergency using the MeaningCloud web service. A user interface which enables user registration, training an own machine learning model, saving that model locally on the computer or storing it in the database, saving and editing own training datasets, evaluating the trained models, and evaluating the pretrained model which detects emergency medical cases was created. The application was built using the Vue.js frontend framework, ml5.js machine learning library, MeaningCloud service for text summarization, MongoDB database, and Node.js as the backend runtime environment.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:753885
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-12-07 12:36:48