5 results on '"Mikulić, Petra"'
Search Results
2. SOX2, JAGGED1, β-Catenin, and Vitamin D Receptor Expression Patterns during Early Development and Innervation of the Human Inner Ear.
- Author
-
Mikulić, Petra, Ogorevc, Marin, Petričević, Marin, Kaličanin, Dean, Tafra, Robert, Saraga-Babić, Mirna, and Mardešić, Snježana
- Subjects
- *
VITAMIN D receptors , *SENSORINEURAL hearing loss , *INNER ear , *NERVE fibers , *CELLULAR signal transduction , *HEARING disorders , *INNERVATION - Abstract
Sensorineural hearing loss can be caused by lesions to the inner ear during development. Understanding the events and signaling pathways that drive inner ear formation is crucial for determining the possible causes of congenital hearing loss. We have analyzed the innervation and expression of SOX2, JAGGED1, β-catenin (CTNNB1), and vitamin D receptor (VDR) in the inner ears of human conceptuses aged 5 to 10 weeks after fertilization (W) using immunohistochemistry. The prosensory domains of the human inner ear displayed SOX2 and JAGGED1 expression throughout the analyzed period, with SOX2 expression being more extensive in all the analyzed timepoints. Innervation of vestibular prosensory domains was present at 6 W and extensive at 10 W, while nerve fibers reached the base of the cochlear prosensory domain at 7–8 W. CTNNB1 and VDR expression was mostly membranous and present during all analyzed timepoints in the inner ear, being the strongest in the non-sensory epithelium. Their expression was stronger in the vestibular region compared to the cochlear duct. CTNNB1 and VDR expression displayed opposite expression trends during the analyzed period, but additional studies are needed to elucidate whether they interact during inner ear development. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Diabetes Monitoring Application
- Author
-
Mikulić, Petra and Botički, Ivica
- Subjects
konverzacijski agent ,education ,dijabetes ,diabetes ,TECHNICAL SCIENCES. Computing ,TEHNIČKE ZNANOSTI. Računarstvo ,chatbot ,edukacija - Abstract
U okviru diplomskog rada izradit će se aplikacija za pacijente koji boluju od dijabetesa. Dijabetes je kompleksna kronična bolest te postoji potreba za pružanje pomoći i adekvatne edukacije tehnološkim rješenjima. Korisnik će pri registraciji ispuniti upitnike kako bi što bolje opisao svoje trenutno znanje o dijabetesu te ciljeve korištenja aplikacije. Glavni moduli aplikacije su edukacijski modul i konverzacijski agent. Edukacijski modul korisniku pruža informativne i obrazovne sadržaje o dijabetesu, poželjnim ponašanjima pacijenta poput prehrane, tjelovježbe i promjena u svakodnevnom životu. Podijeljen je u nekoliko tema gdje svaka ima lekcije s kontrolnim pitanjem. Pri završetku svih lekcija pojedine teme, nalazi se kviz za provjeru naučenog te dnevnik pomoću kojeg korisnik dodaje i prati svoje osobne bilješke. U svrhu poboljšanja edukacijskog modula korisnicima će biti omogućeno ocjenjivati i komentirati pojedine stavke primjerice teme, kvizove ili pojedina pitanja. Konverzacijski agent posjedovat će bazu znanja o raznim pitanjima koje mu korisnik može postaviti. Također, upućivati će korisnika na druge resurse znanja, primjerice edukacijski modul ili vanjski resurs. Potrebno je ostvariti i administrativno sučelje koje služi za ažuriranje sadržaja i pregled izvještaja. Rješenje je potrebno priložiti radu na mediju CD/DVD. As part of the thesis, an application will be developed for patients with diabetes. Diabetes is a complex chronic disease and there is a need to provide assistance and adequate education with technological solutions. When registering, the user will fill in questionnaires in order to better describe their current knowledge about diabetes and the goals of using the application. The main modules of the application are the Education Module and the Chatbot. The educational module provides the user with informative and educational content about diabetes, desirable patient behaviors such as diet, exercise and changes in daily life. It is divided into several topics where each has lessons with a control question. At the end of all lessons on a particular topic, there is a quiz to check what you have learned and a diary where user can add and keep track of their personal notes. In order to improve the Educational Module, users will be able to rate and comment on individual items such as topics, quizzes or individual questions. The Chatbot will have a knowledge base on various questions that the user can ask him. It will also refer the user to other knowledge resources, such as an education module or an external resource. It is also necessary to create an administrative interface for updating the content and reviewing the report. The solution must be attached to the work on CD / DVD.
- Published
- 2020
4. Comparison of Artificial Intelligence Methods and Mathematical Methods in Cryptocurrency Price Prediction
- Author
-
Mikulić, Petra and Botički, Ivica
- Subjects
vizualizacija rezultata ,kriptovalute, predviđanje cijena, vizualizacija rezultata ,TECHNICAL SCIENCES. Computing ,TEHNIČKE ZNANOSTI. Računarstvo ,predviđanje cijena ,cryptocurrencies ,kriptovalute ,price prediction ,result visualization - Abstract
U okviru završnog rada potrebno je napraviti pregled metoda umjetne inteligencije i matematičkih metoda koje se koriste u predviđanju trendova promjene cijene kriptovaluta. Koristeći javno objavljene skupove podataka o kriptovalutama, potrebno je odabrati i implementirati jednu metodu umjetne inteligencije i jednu matematičku metodu, predložiti način njihove parametrizacije, te pokazati njihovu efikasnost prilikom predvidanja promjene cijena kriptovaluta. Dobivene rezultate je potrebno usporediti i vizualizirati. Rješenje je potrebno priložiti radu na mediju CD/DVD. In this paper an overview of artificial intelligence and mathematical methods used in predicting price changes of cryptocurrencies is presented. Using published datasets with cryptocurrency data, one method of artificial intelligence and one mathematical method is to be chosen and implemented, their parameters need to be selected and their efficiency during prediction of price changes to be shown. The obtained results should be compared and visualized.The solution should be attached on CD/DVD media.
- Published
- 2018
5. The “t” time: Investigating handedness through strokes and slopes.
- Author
-
Šunjić, Kata, Banovac, Ana, Kafadar, Tijana, Džin, Nena, Žeravica, Marko, Mikulić, Petra, Penava, Ana, Kulišić, Adriana, Hajdić, Zlatka, Kružić, Ivana, Jerković, Ivan, and Bašić, Željana
- Subjects
- *
HANDEDNESS , *LOGISTIC regression analysis , *DATABASES , *REGRESSION analysis , *HANDWRITING - Abstract
This study investigated the stroke and slope characteristics in left‐handed and right‐handed handwriting. Stroke (letters t, f, đ, and H) and slope (letters t, f, l, d, and g) directions were analyzed on in‐house samples (n = 64), revealing statistically significant differences (p ≤ 0.05) between the groups. Right‐handers predominantly exhibited left‐to‐right strokes (98%–100%), while left‐handers showed greater variability. Although statistically significant for most letters analyzed, slope direction did not demonstrate consistent patterns. A logistic regression model was developed and validated on the same sample to classify handedness based on the averaged strokes of the letter “t.” The model was further tested on samples (n = 252) from a publicly available handwriting database. If the model classified the sample as produced by left hand, it was correct in 100% of cases. In contrast, when the model classified writing as right‐handed, it was correct in 73%–97% of cases, depending on the validation sample. The model classified writing as of left‐handed origin if more than 36% of the letters “t” had a stroke from right to left, while otherwise, writing was classified as of right‐handed origin. The developed method showed great potential for classifying the handedness of the author of disputed handwriting, thus eliminating individuals as text authors or narrowing down the pool of potential authors. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.