Development of artificial neural network models based on near-infrared spectroscopy for the grape skin composting evaluation

doctoral thesis

• Title (croatian): Razvoj modela umjetnih neuronskih mreža temeljenih na bliskoj infracrvenoj spektroskopiji za procjenu učinkovitosti kompostiranja pokožice grožđa
• Author: Tea Sokač Cvetnić
• Mentor: Ana Jurinjak Tušek (mentor)
• Committee member: Ivana Radojčić Redovniković (predsjednik povjerenstva)
• Committee member: Tamara Jurina (član povjerenstva)
• Committee member: Tamara Jakovljević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Food Technology and Biotechnology; (Department of Process Engineering); (Laboratory for Measurement, Regulation and Automatisation); Zagreb
• Defense date and country: 2024, Croatia
• Scientific / art field, discipline and subdiscipline: BIOTECHNICAL SCIENCES; Biotechnology
• Universal decimal classification (UDC): 663 - Industrial microbiology. Industrial mycology. Zymurgy, fermentation industry. Beverage industry. Stimulant industry

Abstract

During the vine production, huge amounts of waste (grape pomace) are generated. The grape pomace can be used as a substrate for the composting process. The composting process is an aerobic, biological process in which organic matter is degraded in the presence of water, oxygen, and microorganisms. The efficiency of the composting process can be monitored through a few variables (such as moisture and dry matter content, organic carbon content and ash, carbon-nitrogen ratio, pH value), but these analyses are time-consuming. In the last few years, the use of near-infrared spectroscopy has been noted as a fast, non-destructive method for on-line monitoring the composting process. The aim of this doctoral thesis is the development of artificial neural networks models using chemometric tools based on the near infrared data for the evaluation of the efficiency of the composting process in laboratory reactors.

Abstract (croatian)

Prilikom proizvodnje vina nastaje velika količina otpada, odnosno komina grožđa koja se može procesom kompostiranja prevesti u stabilan produkt. Proces kompostiranja je aeroban biološki proces tijekom kojeg dolazi do razgradnje organskih tvari u prisustvu vode, kisika i mikroorganizama. S obzirom da se učinkovitost procesa kompostiranja prati putem nekoliko varijabli (poput udjela vlage i suhe tvari, udjela organskog ugljika i pepela, omjera ugljika i dušika, pH vrijednosti) čije analize zahtijevaju dosta vremena, u posljednje vrijeme često se spominje upotreba blisko infracrvene spektroskopije kao brze, nedestruktivne metode za on-line praćenje učinkovitosti procesa kompostiranja. Cilj predložene teme ove doktorske disertacije je razvoj modela umjetnih neuronskih mreža primjenom kemometrijskih alata na temelju podataka dobivenih blisko infracrvenom spektroskopijom za procjenu učinkovitosti procesa kompostiranja pokožice grožđa u laboratorijskim reaktorima.

• Keywords: composting; grape pomace; near-infrared spectroscopy; artificial neural network.
• Keywords (croatian): kompostiranje; komina grožđa; bliska infracrvena spektroskopija; umjetne neuronske mreže
• Language: english
• URN:NBN: urn:nbn:hr:159:850801
• Promotion: 2024
• Study programme: Title: Postgraduate PhD Study in Nutrition; Study programme type: university; Study level: postgraduate; Academic / professional title: doktor/doktorica znanosti, područje biotehničkih znanosti, polje nutricionizam (doktor/doktorica znanosti, područje biotehničkih znanosti, polje nutricionizam)
• Type of resource: Text
• Extent: 247 str. ; 30 cm
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-06-06 11:42:56