Primjena metoda strojnog učenja u interpretaciji NMR spektra

undergraduate thesis

• Title (english): Application of machine learning methods in interpreting NMR spectra
• Author: Bruno Palavra
• Mentor: Miroslav Jerković (mentor)
• Committee member: Miroslav Jerković (predsjednik povjerenstva)
• Committee member: Irena Škorić (član povjerenstva)
• Committee member: Željka Ujević Andrijić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Chemical Engineering and Technology; Zagreb
• Defense date and country: 2022-09-20, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

Nuklearna magnetska rezonanca (NMR) je tehnika koja se najčešće koristi u medicini, organskoj kemiji i biokemiji. Zasniva se na magnetskom spinu jezgre koji se pobuđuje radiofrekventnim zračenjem, te prilikom relaksacije otpušta zračenje koje se detektira prijamnikom. Zračenje se Fourirerovim transformacijama pretvara iz vremenske u frekvencijsku domenu, a rezultat su karakteristični pikovi koji se dalje asigniraju pripadajućim jezgrama. U medicini se koristi pri identifikaciji stranih tijela (npr. tumori), dok se u organskoj kemiji koristi pri identifikaciji i karakterizaciji novih spojeva. U biokemiji se također koristi za karakterizaciju proteina i ostalih većih biomolekula. U organskoj kemiji se najčešće analiziraju jezgre ugljika i vodika, stoga rad najviše obrađuje tu primjenu. Ostale jezgre se koriste u fizikalnim i spektroskopskim istraživanjima. Algoritmi strojnog učenja spadaju u granu računarstva, a čak se mogu svrstati u podpodručje statistike, iako su i dalje nejasno definirane granice. Zasnivaju se na korištenju matematičkih funkcija i modela za obradu podataka, te iz tih podataka koje unosimo (eng. Input) mogu učiti i davati neke informacije (eng. Output). Upravo iz tog razloga se primjenjuju u različitim granama znanosti. Svugdje gdje imamo veću količinu podataka možemo ih koristiti za lakšu analizu i interpretaciju tih podataka.

Abstract (english)

Nuclear magnetic resonance (NMR) is a technique most commonly used in medicine, organic chemistry and biochemistry. It is based on the magnetic spin of the nucleus, which is aroused by radiofrequency radiation, and during relaxation it releases radiation that is detected by the receiver. The radiation is transformed from the time to the frequency domain by Fourirer transformations, and the result is characteristic peaks that are further assigned to the associated nuclei. In medicine, it is used in the identification of foreign bodies (e.g. tumors), while in organic chemistry it is used when identifying and characterizing new compounds. In biochemistry, it is also used to characterize proteins and other larger biomolecules. In organic chemistry, carbon and hydrogen nuclei are most often analyzed, so the work processes this application the most. Other nuclei are used in physical and spectroscopic research. Machine learning algorithms belong the branch of computer science, and can even be classified as a subfield of statistics, although boundaries remain vaguely defined. They are based on the use of mathematical functions and models for data processing, and they can learn and provide some information (output) from the dana we enter (input). It is for this reason that they are applied in various branches of science. Wherever we have a large amount of dana, we can use it for easier analysis and interpretetation of that dana.

• Keywords: nuklearna magnetska rezonanca (NMR); NMR spektar; metode strojnog učenja
• Keywords (english): nuclear magnetic resonance (NMR); NMR spectra; machine learning methods
• Language: croatian
• URN:NBN: urn:nbn:hr:149:102140
• Study programme: Title: Applied Chemistry - Undergraduate study; specializations in: Environmental chemistry and green technologies, Advanced materials and technologies, Applied organic chemistry; Course: Applied organic chemistry; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) primijenjene kemije (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) primijenjene kemije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-03-09 13:20:49