Search  English (United States) Hrvatski (Hrvatska)

innovative promotional partnershipArtificial Intelligence towards EU Multilingualism

Technical co-sponsorship

 
MIPRO 2017 - 40th Jubilee International Convention

miproBIS - Business Intelligence Systems

Wednesday, 5/24/2017 3:00 PM - 7:00 PM, Congress hall B, Hotel Admiral, Opatija

The IEEE reserves the right to exclude a paper from distribution after the conference (including its removal from IEEE Explore) if the paper is not presented at the conference.

Event program
Wednesday, 5/24/2017 3:00 PM - 7:00 PM,
Congress hall B, Hotel Admiral, Opatija
Invited Lecture
 
A. Cuzzocrea (University of Trieste and ICAR-CNR, Trieste, Italy)
Multidimensional Mining of Big Social Data for Supporting Advanced Big Data Analytics 
Big social data are now everywhere. They constitute a rich source of knowledge that is prone to be explored and mined in order to support advanced big data analytics. Multidimensional mining identifies a promising collection of tools to this end. In this paper, we explore this innovative research context, by highlighting pros and cons of actual literature proposals. We complete our contributions by providing an overview on two state-of-the-art proposals that show how big data analytics over big social data work in practice.
Papers
 
1.M. Zymbler (South Ural State University, Chelyabinsk, Russian Federation)
Accelerating Dynamic Itemset Counting on Intel Many-core Systems 
The paper presents a parallel implementation of a Dynamic Itemset Counting (DIC) algorithm for many-core systems, where DIC is a variation of the classical Apriori algorithm. We propose a bit-based internal layout for transactions and itemsets with the assumption that such a representation of the transaction database fits in main memory. This technique reduces the memory space for storing the transaction database and also simplifies support counting and candidate itemsets generation via logical bitwise operations. Implementation uses OpenMP technology and thread-level parallelism. Experimental evaluation on the platforms of Intel Xeon CPU and Intel Xeon Phi coprocessor with large synthetic database showed good performance and scalability of the proposed algorithm.
2.M. Radonić, I. Mekterović (Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia)
ETLator – a Scripting ETL Framework 
ETL (Extract Transform Load) process is the industry standard term for data extraction, transformation and loading into the Data Warehouse (DW). ETL process is the most resource demanding process in DW implementation and typically has to be evolved and maintained for the duration of the DW. To facilitate the development and maintenance of ETL processes many ETL tools have been developed featuring Graphical User Interfaces and various built-in functionalities (parallelism, logging, rich transformation libraries, documentation generation, etc.). The downside of such GUI ETL tools is that development is carried out heavily using mouse operations and less by writing programming code, which feels unnatural for some developers, especially with many similar, repetitive tasks. In this paper we present an alternative approach – an ETL framework “ETLator” based on Python scripting language where ETL tasks are defined by writing Python code. ETLator implements various typical ETL transformations and allows the user to simply and efficiently define complex ETL tasks with multiple sources and parallel tasks whilst leveraging full flexibility of Python. ETLator also provides logging and can document ETL tasks by generating data flow images. On a test case we show that ETLator simplifies ETL development and rivals the GUI approach.
3.V. Bosilj Vukšić (Faculty of Economics & Business, University of Zagreb , Zagreb, Croatia), M. Pejić Bach (Faculty of Economics & Business, University of Zagreb, Zagreb, Croatia), T. Grublješič, J. Jaklič (Faculty of Economics, University of Ljubljana, Ljubljana, Slovenia), A. Stjepić (Faculty of Economics & Business, University of Zagreb , Zagreb, Croatia)
The role of Alignment for the Impact of Business Intelligence Maturity on Business Process Performance in Croatian and Slovenian Companies 
Business intelligence (BI) allows companies to analyze business information in order to support successful decision making. Currently, the research on the level of BI maturity in Croatian and Slovenian companies is limited. In addition, several BI maturity models have been developed, but most of them are not comprehensive. In order to shed some light to this issue, this paper is focused on two goals: (1) to investigate the impact of BI maturity on business process performance and (2) to explore the requirements for the alignment of two concepts, BI and business process management (BPM) within the organization. Paper presents the following: (i) investigation of BI and BI systems in general, (ii) adaption of the BI maturity model (called biMM) for the purpose of this research, (iii) results of the primary research on the sample of Croatian and Slovenian companies which has been conducted as one of the activities of the project financed by the Croatian Science Foundation: IP-2014-09-3729 Process and Business Intelligence for Business Excellence, (iv) level of BI maturity and the role of BI and business process alignment for the impact of BI maturity on business process performance in investigated companies.
4.M. Ptiček, B. Vrdoljak (Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
MapReduce Research on Warehousing of Big Data 
The growth of social networks and affordability of various sensing devices has lead to a huge increase of both human and non-human entities that are interconnected via various networks, mostly Internet. All of these entities generate large amounts of various data, and BI analysts have realized that such data contain knowledge that can no longer be ignored. However, traditional support for extraction of knowledge from mostly transactional data - data warehouse - can no longer cope with large amounts of fast incoming various, unstructured data - big data - and is facing a paradigm shift. Big data analytics has become a very active research area in the last few years, as well as the research of underlying data organization that would enhance it, which could be addressed as big data warehousing. One research direction is enhancing data warehouse with new paradigms that have proven to be successful at handling big data. Most popular of them is the MapReduce paradigm. This paper provides an overview on research and attempts to incorporate MapReduce with data warehouse in order to empower it for handling of big data.
5.M. Pejic-Bach, J. Zoroja, B. Jaković (Faculty of Economics & Business, University of Zagreb, Zagreb, Croatia), N. Šarlija (Faculty of Economics, University of Osijek, Osijek, Croatia)
Selection of Variables for Credit Risk Data Mining Models: Preliminary research 
Credit risk is related to the risk of the borrower that the lender will not be able to return their debt including interest. Numerous researches have been conducted in the area of credit risk, both using classical models such as Altman Z-score and using machine learning methodology. However, the research using the data from Croatian financial institutions is scarce, especially research focused on the selection of the demographic and/or behavior variables. In addition, it is important to develop robust models that estimate credit risk as accurately as possible. The goal of this research is to develop a data mining model for prediction of credit risk, using the data from Croatian financial institutions on defaulted clients (demographic and behavior data). Decision tree models are constructed for the prediction of credit risk. Different algorithms for the variable selection are evaluated based on the classification accuracy of the decision trees developed based on the selected variables.
6.L. Zailskaite-Jakste, A. Ostreika, A. Jakstas, E. Stanevičienė, R. Damasevicius (Kaunas University of Technology, Kaunas, Lithuania)
Brand Communication in Social Media: the Use of Image Colours in Popular Posts 
Recent scientific and theoretical studies defining brand communication in social media emphasize the significance consumer engagement in brand-related content. Popularity of brand messages and the reach of target audiences depends on consumer engagement in social media. Therefore, many business companies are seeking to increase an impact on consumers using social media analysis and consumer engagement technics. Usually, consumer actions such as likes, comments and shares in social media channels are used to estimate the popularity of brand posts. One of the factors, which has not widely analyzed before, is the impact of colors for popularity of visual brand-related posts. In this paper, we analyze the effect of colors for popularity of brand-related posts in social media. We analyze our own dataset of images collected from 35 most popular brand Facebook groups. Our results show that black, gray and brown colors were more often used in images of more popular brand-related posts.
7.G. Antolić, L. Brkić (Fakultet elektrotehnike i računarstva, Zagreb, Croatia)
Recommender System Based on the Analysis of Publicly Available Data 
A recommender system is a software system aimed to make recommendations. To be able to do that, recommender system feature several components, such as: data collection and processing, recommender model, recommendation post-processing and a user interface. Recommender systems apply one or the combination of few of the recommendation approaches: content-based filtering, collaborative filtering, graph-based recommendations, stereotyping and item-centric recommendations. In this paper we describe recommender system developed to provide users, registered in our system, with recommendations in accordance with their interests. We deduce user interests based on the user activities and posts in social networks. All social networks (Facebook, Twitter, Instagram ...) provide programming interface allowing access to the information about the user collected on the social network. Thanks to this data we are overcoming the so-called “cold start” problem and building user profile. A recommender system is commonly associated with only one domain, while the recommender system described in this paper is able to generate recommendations from different domains (movies, music, sports, literature ...). In addition to recommendations related with the specific domain, our system is able to recommend the web articles, relevant to the user, that may belong to any or more than one category of interest.
8.I. Kovačević, I. Mekterović (Fakultet elektrotehnike i računarstva, Zagreb, Croatia)
Alternative Business Intelligence Engines 
Business Intelligence (BI) engines enable companies and researchers to perform fast and efficient data analysis and extract relevant information from their data. At the present, it implies the usage of reporting tools and OLAP on top of traditional relational database systems. This paper gives an overview of alternative BI engines, based on various NoSQL and NewSQL database technologies. NoSQL (Not-only SQL) systems were developed to address the scalability issues of traditional relational databases when exposed to huge amounts of data and large read and write requirements. NewSQL, an even newer class of database systems, aspire to achieve good NoSQL scaling properties whilst preserving the key features of relational systems – ACID transactions, SQL and relational schema. Various NoSQL and NewSQL systems bear significant differences in terms of architecture, data representation, query capabilities and optimization techniques, and thus offer diverse opportunities in terms of data analysis. In this paper we discuss the data analysis requirements for the BI engines and present an overview of specific data analysis capabilities of various NoSQL and NewSQL systems with their usage scenarios and performance considerations. Finally, the paper brings an overall comparison of these alternative database systems with respect to their usage as BI engines.
9.V. Bosilj Vukšić (Faculty of Business and Economics, University of Zagreb, Zagreb, Croatia), M. Indihar Štemberger (Faculty of Economics, University of Ljubljana, Ljubljana, Slovenia), D. Suša Vugec (Faculty of Economics and Business, University of Zagreb, Zagreb, Croatia)
Insights into BPM Maturity in Croatian and Slovenian Companies 
In recent period, business process management (BPM) has been increasingly a matter of interest for numerous authors as well as numerous organizations, due to the understanding of business processes as the core part of every organization. Significant efforts have been put into researching and implementing BPM within organizations. With the purpose of investigating the current state of BPM and business intelligence (BI) adoption in Croatia and Slovenia, Croatian Science Foundation has been financing the project PROSPER - Process and Business Intelligence for Business Excellence (IP-2014-09-3729). As one of the objectives of the mentioned project, this paper’s goal is to present the current state of BPM maturity and usage of social BPM within the companies operating in Croatia and Slovenia by analysing data collected by the PROSPER research group through questionnaires. Moreover, organizational culture is included in the analysis as well. Results indicate higher BPM maturity level and higher usage of social BPM within Slovenian companies than within Croatian ones and some other differences regarding dominant organizational cultures have also been found.
10.I. Sorić, D. Dinjar, M. Štajcer, D. Oreščanin (Poslovna inteligencija d.o.o., Zagreb, Croatia)
Efficient Social Network Analysis in Big Data Architectures 
Social network analysis (SNA) is the application of graph theory to understand, categorize and quantify relationships in a social network. It can be a great tool to improve analytic capabilities in any field, for example marketing analytics, churn prediction, health care, etc. In terms of SNA, network structure is defined by nodes, edges and metrics which quantify the importance or influence of certain nodes in the network or relationship strength between nodes. Algorithms for network metrics calculation are complex and that makes SNA difficult to implement in big data environments on large datasets with many nodes and edges. In this paper we will elaborate how to efficiently and performance wise perform SNA and visualize results of the analysis on large datasets using increasingly popular GraphX and JavaScript libraries.
11.D. Jakšić (Odjel za informatiku - Sveučilište u Rijeci, Rijeka, Croatia), V. Jovanović (Georgia Southern University, Statesboro, GA, United States), P. Poščić (Odjel za informatiku - Sveučilište u Rijeci, Rijeka, Croatia)
Integrating Evolving MDM and EDW Systems by Data Vault Based System Catalog 
The paper presents results of a research on integration of enterprise data warehouses (EDW) and a master data management (MDM) system. The primary goal was solving a schema evolution problem, and the corner stone of our approach was utilization of a data vault modeling of an integrated meta-model of EDW and MDM as an expansion of a traditional relational database system catalog. The main contributions of this paper are: a) common integration architecture, b) new system catalog based on a meta-model for EDW and MDM integration, and c) research prototype used for empirical validation of the effectiveness of the proposed solution.
12.G. Pakasin (HEP-ODS d.o.o. Elektra Koprivnica, Koprivnica, Croatia), V. Komen (HEP-ODS d.o.o. Elektroprimorje Rijeka, Rijeka, Croatia), D. Franković (Sveučilište u Rijeci, Tehnički fakultet, Rijeka, Croatia)
Integracija GIS-a i alata za proračune distribucijskih mreža 
Većina podataka o elementima distribucijske mreže i postrojenjima pohranjena je u Geografskom informacijskom sustavu (GIS). Tehnički podaci o elementima mreže i podaci o njihovoj međusobnoj povezanosti postoje u GIS-u, a potrebni su kod proračuna distribucijske mreže i moraju se ponovno ručno unositi u aplikacije za proračune. Dolazi do nepotrebne redundancije podataka i gubitka vremena kod unosa, te kasnije kod održavanja podataka. U radu je izvršeno povezivanje dva sustava koji u praksi uglavnom rade nezavisno, a koriste isti fond podataka i bitni su za poslovno odlučivanje. Rezultati proračuna i analiza prezentirani su u GIS-u. Kao predstavnik GIS softvera korišten je General Electric Smallworld - DeGIS, dok je kao aplikacija za proračune korišten Neplan. U radu su prikazani koraci i kompromisi koje je trebalo poduzeti kako bi se navedene aplikacije povezale, te dobio jasan prikaz rezultata proračuna.

Basic information:
Chairs:

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

Program Committee:

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

Registration / Fees:
REGISTRATION / FEES
Price in EUR
Before 8 May 2017
After 8 May 2017
Members of MIPRO and IEEE
180
200
Students (undergraduate and graduate), primary and secondary school teachers
100
110
Others
200
220

The discount doesn't apply to PhD students.

Contact:

Boris Vrdoljak
University of Zagreb
Faculty of Electrical Engineering and Computing
Unska 3
HR-10000 Zagreb, Croatia

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

The best papers will get a special award.
Accepted papers will be published in the ISBN registered conference proceedings. Papers written in English and presented at the Conference will be submitted for posting to IEEE Xplore.


 

Location:

Opatija, with its 170 years long tourist tradition, is the leading seaside resort of the Eastern Adriatic and one of the most famous tourist destinations on the Mediterranean. With its aristocratic architecture and style Opatija has been attracting renowned artists, politicians, kings, scientists, sportsmen as well as business people, bankers, managers for more than 170 years.

The tourist offering of Opatija includes a vast number of hotels, excellent restaurants, entertainment venues, art festivals, superb modern and classical music concerts, beaches and swimming pools and is able to provide the perfect response to all demands.

Opatija, the Queen of the Adriatic, is also one of the most prominent congress cities on the Mediterranean, particularly important for its international ICT conventions MIPRO that have been held in Opatija since 1979 gathering more than a thousand participants from more than forty countries. These conventions promote Opatija as the most desirable technological, business, educational and scientific center in Southeast Europe and the European Union in general.


For more details please look at www.opatija.hr/ and www.visitopatija.com

Download
 
News about event
Currently there are no news
 
Patrons - random
Sveučilište u ZagrebuSveučilište u RijeciFER ZagrebPomorski fakultet RijekaTehnički fakultet Rijeka