Hibridni događaj

Program događaja

srijeda, 29.9.2021 14:00 - 18:15, Collegium, Grand hotel Adriatic, Opatija Radovi  1. D. Oreščanin (Poslovna inteligencija, Zagreb, Croatia), T. Hlupić (Poslovna inteligencija d.o.o., Zagreb, Croatia) Data Lakehouse - a Novel Step in Analytics Architecture  Data Lakes, as a novel concept of raw analytical data storage, were longely presented as a next step that will take over Data Warehouses. With a significant time distance from the Data Lakes emergence, it is clear those two architectures complement each other with their actual usage. A new architecture concept, Data Lakehouse, has recently been introduced as a next step in the analytical data storage. The Data Lakehouse architecture should be able to deal with currently insurmountable challenges that both Data Warehouses and Data Lakes can not overcome. In this article, a current state of the Data Lakehouse architecture and vendor implementation will be given, Next, a comparison of the Data Lakehouse will be done against both Data Warehouses and Data Lakes with a focus on tackling their known challenges. Finally, an approach to combine existing Data Warehouses and Data Lakes into a unified Data Lakehouse will be presented, with a a special focus on the high-level architecture. 2. A. Čorňák, R. Delina (Technical University of Košice, Košice, Slovakia) The Potential Role of Hydrometeorological Data in Agricultural Supply Chain  Agricultural industry represents one of the most important human activities for tens of thousands of years. The current trend in agriculture is so-called Agriculture 4.0. Precision farming techniques have potential for use in a range of areas that lead to more effective management of strategic decision-making in agricultural supply chains. One of the most important attributes of agricultural products is their price, quantity and quality. These attributes are influenced by a number of factors from hydrometeorological conditions to the methods of pest and disease control. This paper is focused on finding potential role of hydrometeorological data in agricultural supply chain. Our main focus is to create crop yield estimation model of selected cereal crops based on hydrometeorological indices and NDVI using various machine learning techniques. 3. V. Fomichov (Moscow Aviation Institute (National Research University), Moscow, Russian Federation) Intelligent Monitoring of News on Economics and Finance Based on Formal Semantics of the Movement Verbs  During last decade, a new class of business intelligence systems has emerged. It consists of natural language (NL) processing systems discovering significant business events in the news posted on the Web. The analysis shows that, very often, the descriptions of business events are metaphoric. E.g., the sentences describing the dynamics of various goods’ prices may include the forms of the verbs “to jump”, “to climb down”, “to crash down”, etc. The paper suggests an original approach (and its software implementation) to designing intelligent monitoring systems looking for the changes of selected parameters (price, exchange rate, etc.) associated with a selected set of goods (feed wheat, aluminum, oil, etc.). The approach is based on formal semantics of the verbs characterizing the movement. The central idea is to use domain-independent formal representations of the verbs’ semantics. With this aim, the powerful expressive means of the theory of K-representations (knowledge representations) are used. It is an original theory of designing semantic parsers of NL-texts with the broad use of formal means for representing input, intermediary, and output data. TKR and its computer applications are described in numerous papers in English. TKR introduces a new class of formal languages – the class of SK-languages (standard knowledge languages). TKR is used in the paper in an optimized form, because the paper suggests a simplified (an optimized) form of its fist basic mathematical model (it describes a set of primary units of conceptual level and the relationships between them). With this aim, the notion of an optimized conceptual basis is introduced. 4. N. Čerkez, V. Vareškić (VSITE, ZAGREB, Croatia) Machine Learning Approaches to Personality Classification on Imbalanced MBTI Datasets  The MBTI (Myers-Briggs Type Indicator) is a widely known approach to personality classification. Datasets for the machine learning approach to personality classification using MBTI are highly imbalanced. Handling imbalanced data sets is a significant open problem with a considerable impact on machine learning methods. This paper presents the results of applying different techniques and suggests their best in mitigating the challenge of imbalanced MBTI datasets. Even though most techniques could be used and implemented to some other problems and areas, like images and sound processing, natural language processing has enough challenges to focus on natural language processing and the specific issue of the MBTI datasets. 5. T. Hlupić, J. Puniš (Poslovna inteligencija d.o.o., Zagreb, Croatia) An Overview of Current Trends in Data Ingestion and Integration  Data ingestion and integration present a significant factor in the data analytics, especially with the emerging data of high volume and velocity. The existing approaches, which were focused mostly on the batch processing, had to be adjusted in order to align with the new trends in data processing and storage. At the same time, data ingestion tools have gained a popularity as they have supported new development and analytics trends. Moreover, major vendors have shifted their focus to cloud solutions, which affected both the existing and emerging tools. Due to the huge variety in the ingestion and integration approaches, the tools vary in features, from different programming language support up to the platform-specific usage. In this article, state-of-the-art data ingestion and integration tools are systematically individually reviewed, with their key features identified. Also, the current tools categories are observed and compared, together with list of tools which they encompass, based on their features. 6. N. Vlahović, V. Brozović, F. Škavić (Faculty of Economics and Business University of Zagreb, Zagreb, Croatia) Investor Classification Model Based on Behavioural Finance Studies  In recent years there have been numerous research studies in the field of Behavioural finance. The findings can be used to better understand the decision-making process in dynamic and volatile environment in relation to high risk. Traditional theories have always based the decision processes in rationality even though practical research and evidence testifies otherwise. Since then, the field of Behavioural finance studies has matured and enabled the description of relevant circumstances and characteristics of decision making in financial investment that better explain both successful and unsuccessful risk management. The goal of this paper is to create a decision making model for classification of investor propensity to risk based on recent behavioural finance studies. For the purpose of modelling this body of knowledge, a decision tree model will be used. The model itself will represent the knowledge on evaluating the behaviour of investors based both on current literature and practical experience. The resulting model can be used for evaluation of investor behaviour in both practical applications and further scientific research, as it will be demonstrated. 7. M. Pribisalić (Sveučilište u Rijeci, Rijeka, Croatia) Evaluation of BI Solutions for Business Needs  By using new business intelligence (BI) technologies many companies, organizations, institutions, and governments can achieve operational benefits. To choose the right BI solution, among the many solutions offered on the market, it is important to know which features are needed and which features are not needed to achieve the desired results in our organization. In our paper, we present a comparison of twenty business intelligence solutions present on the market and describe their most essential and upcoming features. The comparison of BI solutions, more precisely their capabilities based on the implemented features, was analyzed according to the BARC (2018) guidelines. BARC provides a trend overview of BI solutions features, ranking individual features from 0 to 10. The study is additionally expanded according to Gartner's report (2019) to find better differences between solutions. Finally, we present a summary of the results of the conducted analyzes, discuss the gained insight and give guidelines for choosing the right BI solution together with the discovered development trends. 8. I. Završki, M. Davidović (VSITE, Zagreb, Croatia) Upravljanje odnosima visokog učilišta s vanjskim dionicima  Sustav administracije visokog učilište realizira osnovne funkcije upravljanja odnosima sa studentima i nastavnicima kao ključnim unutarnjim dionicima. U ovom radu analiziraju se prednosti koje visoka učilišta dobivaju korištenjem CRM sustava u organizaciji poslovanja i upravljanju odnosima s vanjskim dionicima. Opisan je projekt uvođenja CRM sustava u poslovanje visokog učilišta od definiranja opsega projekta do trenutka migracije razvojnog sustava u produkciju. Djelovanje CRM sustava visokog učilišta je prikazano na primjeru upravljanja odnosima s potencijalnim studentima i primjeni CRM-a u organizaciji studentskih praksi.

Boris Vrdoljak (Croatia), Mirta Baranović (Croatia), Matteo Golfarelli (Italy), Mihaela Vranić (Croatia)

Marko Banek (Croatia), Mirta Baranović (Croatia), Bartosz Bebel (Poland), Ladjel Bellatreche (France), Ljiljana Brkić (Croatia), Alfredo Cuzzocrea (Italy), Todd Eavis (Canada), Enrico Gallinucci (Italy), Dragan Gamberger (Croatia), Paolo Garza (Italy), Matteo Golfarelli (Italy), Igor Mekterović (Croatia), Damir Pintar (Croatia), Sandro Skansi (Croatia), Zoran Skočir (Croatia), A Min Tjoa (Austria), Mladen Varga (Croatia), Mihaela Vranić (Croatia), Boris Vrdoljak (Croatia), Marko Gulić (Croatia)

Popust se ne odnosi na studente doktorskog studija.

Boris Vrdoljak
Fakultet elektrotehnike i računarstva
Unska 3
10000 Zagreb, Hrvatska

Tel.: +385 1 6129 532
Fax: +385 1 6129 915
E-mail: boris.vrdoljak@fer.hr 

Najbolji radovi bit će nagrađeni.
Prihvaćeni radovi bit će objavljeni u zborniku radova s ISSN brojem. Prezentirani radovi na engleskom jeziku bit će poslani za uključenje u digitalnu bazu IEEE Xplore.
.............
Postoji mogućnost da se odabrani znanstveni radovi uz određenu doradu objave u međunarodnom časopisu Journal of Computing and Information Technology (CIT).

Opatija, sa 170 godina dugom turističkom tradicijom, vodeće je ljetovalište na istočnoj strani Jadrana i jedno od najpoznatijih na Mediteranu. Ovaj grad aristokratske arhitekture i stila već 170 godina privlači svjetski poznate umjetnike, političare, kraljeve, znanstvenike, sportaše, ali i poslovne ljude, bankare, menadžere i sve kojima Opatija nudi svoje brojne sadržaje. 

Opatija svojim gostima nudi brojne komforne hotele, odlične restorane, zabavne sadržaje, umjetničke festivale, vrhunske koncerte ozbiljne i zabavne glazbe, uređene plaže i brojne bazene i sve što je potrebno za ugodan boravak gostiju različitih afiniteta. 

U novije doba Opatija je jedan od najpoznatijih kongresnih gradova na Mediteranu, posebno prepoznatljiva po međunarodnim ICT skupovima MIPRO koji se u njoj održavaju od 1979. godine i koji redovito okupljaju preko tisuću sudionika iz četrdesetak zemalja. Ovi skupovi Opatiju promoviraju u nezaobilazan tehnološki, poslovni, obrazovni i znanstveni centar jugoistočne Europe i Europske unije općenito.

Detaljnije informacije se mogu potražiti na www.opatija.hr i www.visitopatija.com.