• Rural Digital Europe
• Publications close
• HR close
• RO close

Artificial intelligence is a field that is applied today in various sectors, one of which is agriculture. It is interpreted as how artificial intelligence, or machine learning, can revolutionize agriculture, which affects the country's economy, directly or indirectly employing more than 30 % of the world's population. Automation can thus meet the needs of the ever-increasing world population. Looking at traditional practices in the field of agriculture such as weeding, spraying with pesticides, monitoring the status of nutrients and others, the above can be performed significantly faster through the use of artificial intelligence and machine learning. Thanks to the above, there is a reduction in water wastage, excessive use of pesticides, help in reducing work, but at the same time there is an increase in the fertility of the soil, and thus the crops. The application of artificial intelligence and machine learning in agriculture is still in development due to the lack of expertise and requirements for the accuracy of big data. What can be expected is that the field of machine learning and the use of artificial intelligence in agriculture will continue to grow in the future. The goal of this paper is specifically focused on the influence of machine learning in the application of pesticides. Umjetna inteligencija područje je koje se danas primjenjuje u različitim sektorima među kojima je upravo i poljoprivreda. Tumači se kako umjetna inteligencija, odnosno strojno učenje, mogu revolucionirati poljoprivredu koja utječe na gospodarstvo zemlje, izravno ili neizravno zapošljavajući više od 30 % svjetskog stanovništva. Automatizacijom se na taj način mogu zadovoljiti potrebe sve većeg svjetskog stanovništva. Gledajući tradicionalne prakse na području poljoprivrede kao što su primjerice kultivacija, prskanje pesticidima, praćenje statusa hranjivih tvari i drugo, navedene se mogu značajno brže izvesti putem korištenja umjetne inteligencije i strojnog učenja. Zahvaljujući navedenom dolazi do osiguranja smanjenja rasipanja vode, prekomjerne uporabe pesticida, pomoći u smanjenju rada, ali ujedno dolazi do povećanja plodnosti tla, a samim time i usjeva. Primjena umjetne inteligencije i strojnog učenja u poljoprivredi je još u razvoju zbog nedostatnosti stručnosti i zahtjeva za točnost velikih podataka. Ono što je za očekivati je kako će područje strojnog učenja i uporabe umjetne inteligencije u poljoprivredi u budućnosti i dalje rasti. Cilj ovog rada je konkretno usmjeren na utjecaj strojnog učenja pri aplikaciji pesticida.

Ovaj završni rad detaljno opisuje i predstavlja koncepte Industrije 4.0 i Industrije 5.0. Početak rada sadrži povijesni pregled industrijskih revolucija od Industrije 1.0 pa sve do Industrije 5.0. U nastavku rada definiran je koncept Industrije 4.0 te su pobliže opisane ključne značajke i tehnologije povezane s istom. Potom su prikazani primjeri uvođenja te studije slučaja povezane sa navedenim konceptom. U daljnjem dijelu, prikazan je koncept Industrije 5.0 sa svim bitnim značajkama i studijama slučaja. Na kraju rada prikazana je usporedba dvaju koncepata sa istaknutim sličnostima i razlikama. This thesis thoroughly describes and presents the concepts of Industry 4.0 and Industry 5.0. The beginning of the paper provides a historical overview of industrial revolutions from Industry 1.0 to Industry 5.0. The subsequent sections define the concept of Industry 4.0 and provide a detailed description of its key features and related technologies. Examples of implementation and case studies associated with this concept are also presented. Furthermore, the paper explores the concept of Industry 5.0, outlining its essential features and providing case studies. In the concluding part of the thesis, a comparison of the two concepts is presented, highlighting their similarities and differences.

U radu sažeto je opisano nekoliko polimernih materijala koji se najviše koriste za proizvodnju proizvoda koji se koriste u poljoprivredi. Opisan je primjer gospodarenja poljoprivrednim polimernim otpadom u Europi. Navedeni su i opisani primjeri polimernih proizvoda koji se koriste u poljoprivredi. Navedena je važnost recikliranja polimernog otpada uključujući poljoprivredni polimerni otpad. Opisan je način prikupljanja otpadnih polimernih poljoprivrednih proizvoda te su objašnjeni pojedini načini recikliranja, odnosno preradbe takvih proizvoda. Na kraju su navedene neke vrste proizvoda koje je moguće dobiti korištenjem recikliranih polimera. The paper briefly describes several polymeric materials that are mostly used to produce products used in agriculture. An example of agricultural polymer waste management in Europe is described. Examples of polymer products used in agriculture are given and described. The importance of recycling polymer waste including agricultural polymer waste is stated. The method of collecting waste polymeric agricultural products is described, and certain methods of recycling, ie processing of such products are explained. Finally, some types of products that can be produced using recycled polymers are listed.

Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction since input images may be only partially anomalous. Previous work has addressed dense out-of-distribution detection by discriminative training with respect to off-the-shelf negative datasets. However, real negative data may lead to over-optimistic evaluation due to possible overlap with test anomalies. To this end, we extend this approach by generating synthetic negative patches along the border of the inlier manifold. We leverage a jointly trained normalizing flow due to a coverage-oriented learning objective and the capability to generate samples at different resolutions. We detect anomalies according to a principled information-theoretic criterion which can be consistently applied through training and inference. The resulting models set the new state of the art on benchmarks for out-of-distribution detection in road-driving scenes and remote sensing imagery despite minimal computational overhead.

The objective of Water-ForCE project WP5 (Modelling and data assimilation), Deliverable 5.4 was to provide an integrated view regarding future potential for improved water modelling using satellite EO. The results of previous WPs and WP5 tasks were used to identify challenges and opportunities for integrating satellite EO data in modelling. The findings show the value of satellite-enhanced models for decision making, including recommendations for future.

This paper describes nacional project e-Kultura „Digitalization of Cultural Heritage“, and will be focusing on the ICT system for the project e-Kultura. The system and its capabilities will be explained in detail, including the central system of the project, administrative permissions for all specific actions in the system such as creating information packages, data agregation and administration of themes in the system, as well as creation and updating of collections of digital data in the system. The paper will also outline the rules for digitizing materials, providing a more detailed explanation of the goals and purposes of digitization, file formats for display and permanent storage in the system, and subsequently, publication on the eKultura portal. It will briefly describe the necessary steps for preparing materials before digitization. Additionally, the paper will describe how to create virtual exhibitions on the eKultura portal through WordPress platform. The second, practical part of the paper will be focused on the user experience of the eKultura portal, where the obtained data through online questionnaires will be described. These data can be categorized as a type of investigation in usability testing. The online questionnaires were completed by 20 students, which is the maximum allowed number of participants using the AttrakDiff and VisAWI tools, used for analysis purposes. This approach will consolidate information in one paper about the ICT system for the e-Kultura project, rules, and guidelines for digitizing materials stored in the system, as well as the user experience of the end-users of the eKultura portal. Ovaj rad opisuje nacionalni projekt e-Kultura „Digitalizacija kulturne baštine“, a usredotočit će se na IKT sustav za projekt e-Kultura. Kroz opis središnjeg sustava te njegovim mogućnostima pobliže će se objasniti središnja te PURL administracija sustava, ovlasti administratora za pojedine radnje u sustavu kao što su izrada informacijskih paketa u sustavu, agregacija podataka i administracija tema u sustavu, stvaranje i ažuriranje zbirki. Kroz rad će se opisati i pravila za digitalizaciju građe koja detaljnije objašnjavaju ciljeve i svrhu digitalizacije građe, formate datoteka za prikaz i trajnu pohranu u sustavu te posljedično i objavu na portalu eKultura kao i ukratko opisati koje su radnje potrebne za pripremu gradiva prije same digitalizacije. Nadalje će se opisati način na koji je moguće kreirati virtualne izložbe na portalu eKultura kroz WordPress platformu. Drugi, praktični, dio rada bit će usredotočen na korisničko iskustvo portala eKultura gdje će se opisati dobiveni podaci kroz online upitnike koje možemo svrstati u tip ispitivanja kod testiranja uporabljivosti. Online upitnike ispunjavalo je 20 studenata, što je najveći dozvoljeni broj ispitanika putem alata AttrakDiff i VisAWI, koji su korišteni u svrhu analize. Na ovaj način u jednom radu biti će objedinjene informacije o IKT sustavu za projekt e-Kultura, pravila i smjernice digitalizacije gradiva koja će biti pohranjena u sustavu te korisničko iskustvo krajnjih korisnika portala eKultura.

This paper explains the concept of digital transformation. What it means for service providers, employees and end users, and why digital transformation is important and people have the need for it. There is an explanation of the digital divide, which is always present when it comes to digitization, and how libraries deal with it in their community. This paper covers the topic of digital transformation in Zagreb City Libraries and the four most important digital services available to their users. Catalog of the Zagreb City Libraries, the eZaKi user application and the possibility of borrowing e-books from the ZaKi Book application up to the transition to Readium LPC technology, and the latest service - the loan of audio e-books. Ovaj rad objašnjava pojam digitalne transformacije, što ona znači za pružatelje usluga, zaposlenike i krajnje korisnike te zašto je digitalna transformacija važna i zašto postoji potreba za njom. Objašnjen je pojam digitalnog jaza koji je uvijek prisutan kada je digitalizacija u pitanju te kako se knjižnice nose s njim u svojoj zajednici. Obrađena je tema digitalne transformacije u Knjižnicama grada Zagreba te četiri najznačajnije digitalne usluge dostupne korisnicima. Katalog Knjižnica grada Zagreba, aplikacija eZaKi te mogućnost posudbe e-knjiga od aplikacije ZaKi Book pa sve do prelaska na Readium LPC tehnologiju i najnovija usluga- posudba zvučnih e-knjiga.

The bachelor thesis Impact of Innovations on the Competitiveness of Ryanair examines just how significant innovation can be in driving competitiveness within todays aviation sector. The paper focuses on the analysis of the company Ryanair as a low-cost airline and the research of innovative processes, strategies and digital transformation implemented by the company. The aim of the research is to determine how innovations in the aviation industry contribute to increasing competitive advantage and to analyze the impact of digitalization of the Ryanair company on the air transport industry. Završni rad Utjecaj inovacija na konkurentnost kompanije Ryanair ispituje ulogu inovacija u današnjoj zrakoplovnoj industriji i njihov utjecaj na konkurentnost. Rad se fokusira na analizi kompanije Ryanair kao niskobudžetnog zračnog prijevoznika te istraživanju inovativnih procesa, strategija i digitalne transformacije koje je kompanija implementirala. Cilj istraživanja je utvrditi kako inovacije u zrakoplovnoj industriji doprinose povećanju konkurentske prednosti te analizirati utjecaj digitalizacije kompanije Ryanair na industriju zračnog prijevoza.

Abstract: Modern geoinformation technologies, such as remote sensing satellite missions and classification methods, are becoming increasingly prominent in land cover classification. Due to the emergence of high spatial resolution missions with improved temporal and spectral resolutions, such as Worldview-3, this approach enabled new possibilities in land management. To provide an in-depth analysis of such possibilities, this study reviews methods of land cover classification using WorldView-3 satellite imagery. With 29 different spectral channels and a spatial resolution of 1.2 m, Worldview-3 multispectral satellite images represent the most modern currently publicly available commercial multispectral images. The classification of multispectral images is performed to facilitate the identification and recognition of objects in the images. Analyzed classification methods are: supervised (semi-automatic) classification methods, unsupervised (automatic) classification methods, and object-based classification methods. In order to increase the accuracy in land cover studies, it was determined as necessary to develop automatic methods that rely on a combination of controlled and uncontrolled classification methods. This approach enables the automatic determination of samples for conducting supervised classifications of interest for land management.

Black stem borer, Xylosandrus germanus (Coleoptera: Scolytinae), was first recorded in Croatia in 2009. Until now, the insect has been reported only as a part of ambrosia beetles entomofauna in oak stands (Quercus robur and Quercus petraea). In 2021, severe attack of ambrosia beetles causing tree decline and mortality have been observed in three orchards of hybrid sweet chestnut (Castanea sativa x Castenea crenata). Orchards near Topusko, Marija Bistrica and Vugrovec were inspected for the symptoms. Twenty-seven adult ambrosia beetle specimens were collected from eight samples of damaged sweet chestnut trees, and were identified according to their morphology. All 27 ambrosia beetles were morphologically identified as X. germanus. This is the first record of black stem borer causing damage on cultivated sweet chestnut in Croatia. Considering similar reports from Italy and Slovenia, X. germanus could be regarded as a new, potentially damaging pest in chestnut plantations.