Traži  English (United States) Hrvatski (Hrvatska)

inovativno promotivno partnerstvoUmjetnom inteligencijom prema EU višejezičnosti

Tehničko kosponzorstvo

MIPRO 2024 - 47. međunarodni skup

DC-CPS - Raspodijeljeno računarstvo i računalno-upravljane okoline

srijeda, 22.5.2024 15:00 - 19:30, Bellavista, Grand hotel Adriatic, Opatija

Hibridni događaj
Program događaja
srijeda, 22.5.2024 15:00 - 19:30,
Bellavista, Grand hotel Adriatic, Opatija
15:00 - 15:15Pozvana prezentacija 
Iva Papeš (Chiron Croatia, Zadar)
Prezentacija tvrtke Chiron Croatia 
15:15 - 19:30Radovi 
Machine Learning 
1.S. Požgaj, A. Kurdija, M. Šilić, G. Delač, K. Vladimir (Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
An Overview of the State-of-the-Art Machine Learning Methods for Traveling Salesman Problem 
The traveling salesman problem is one of the most well-known combinatorial optimization problems that has been studied for decades due to its importance in theory and practice. Traditional approaches to solving this problem include exact and heuristic algorithms, and recently, due to the significant development and excellent results of machine learning in various fields, more and more attention is paid to machine learning approaches. The main motivation for introducing machine learning into solving combinatorial optimization problems was that the development of classical hand-crafted heuristics requires theoretical and empirical expertise, which in the case of machine learning can be replaced by data. Also, the advantage of learned heuristics is that they can be trained on a set of instances of a specific problem that we want to solve in practice, which classical heuristics do not take into account because they are usually developed for the general case. In this paper, we give a detailed overview of machine learning approaches for solving the traveling salesman problem developed so far.
2.L. Čutura, K. Vladimir, G. Delač, M. Šilić (University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
Fairness in Graph-Based Recommendation: Methods Overview 
The development of neural networks and machine learning methods has contributed to the widespread popularity of recommender systems, especially those based on graphs. Recommender systems are integral components of systems that often make decisions based on human factors. Therefore, it is not surprising that the development of such systems frequently leads to problems rooted in human nature, such as discrimination, bias, and inequality, among others. One such issue is fairness. Pairing graph-based recommender systems with the fairness problem has led to the development of methods and algorithms aimed at addressing fairness concerns. This paper provides an overview of some of the more significant methods recently developed, their applications, and the results obtained when applied to specific datasets. The methods and algorithms discussed are based on machine learning, specifically neural network methods. Additionally, this paper aims to demonstrate the importance of fair recommendations and highlight the potential for further action in this area.
Distributed Computing 
1.D. Mileski, M. Gusev (Sts Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering, Skopje, Macedonia)
Architecture of a Distributed Infrastructureless System 
Recent trends in the production of portable devices, such as smartphones, smartwatches, and all other smart devices, show that their computing resources are comparable to laptops and desktop computers produced several years ago. In addition, a lot of installed IoT devices around us, realize that pervasive and ubiquitous computing integrates a remarkable amount of computing power. Unfortunately, these computing resources are underutilized and can be efficiently exploited to realize the ever-increasing demand for computing power. Realizing a system that integrates devices on smaller architectural levels (IoT and edge layers) is a complex and challenging task, especially if the system goes beyond edge computing toward autonomous processing and realizes the essence of dew computing. The system should be platform-agnostic and provider-agnostic, so all surrounding devices may participate and build more powerful computing resources. Finally, the proposed system realizes infrastructureless computing integrating the concept of serverless, deviceless, and thingless computing, where all these computing resources will be offered as a service to nearby consumers. In this paper, we present the architecture of such a distributed computing system.
2.B. Besimi, J. Ajdari, X. Zenuni (South East European University, Tetovo, Macedonia)
Metadata-Driven Cloud-Agnostic Data Integration Framework 
In an era where cloud computing is becoming essential, organizations are actively seeking to build cloud-based data solutions or migrate existing on-premises systems to the cloud. This shift is driven by the need to benefit from the scalability, flexibility, and efficiency offered by cloud environments. However, this transition presents a complex challenge: the integration of cloud data practices that are universally applicable yet sufficiently adaptable to domain specific needs. A significant number of cloud data initiatives fail due to poor planning and the absence of appropriate methodologies for effective cloud data integration. This failure often results in issues related to the completeness, accuracy, and consistency of data, which are essential for building reliable and trustworthy data platforms. This paper addresses this challenge by proposing a cloud-agnostic framework for cloud data integration. The paper's contribution is a comprehensive, adaptable metadata-driven data integration framework that is flexible to be tailored to specific domain requirements and scalable for various cloud service providers. The proposed framework is designed to guide and assist organizations in their cloud data integration efforts, enabling them to focus on deriving organizational value.
3.T. Petrovski, M. Gusev (Faculty of Computer Science and Engineering, University of Ss. Cyril and Methodius, Skopje, Macedonia)
Container vs Function as a Service: Impact on Cloud Deployment for Real-World Applications 
This paper compares Container as a Service (CaaS) and Function as a Service (FaaS) as different cloud deployment strategies for a multitenant ride-sharing web application Trek. The application is highly network-intensive, relying extensively on third-party APIs for collecting location data about cities and driving routes. Additionally, it is CPU intensive due to real-time data processing of driver locations while the vehicle moves towards the destination city. This study evaluates both approaches concerning variable workloads and their impact on system responsiveness, re source utilization, and performance during peak and off peak periods. It closely examines crucial performance metrics such as latency and throughput to analyze the implications of both approaches for end-user experience and overall operational efficiency. Additionally, our study analyzes several critical factors like scalability and deployment complexity. We conducted experiments on AWS ECS (CaaS) and AWS Lambda (FaaS) to gain actionable insights into the trade-offs, benefits, and limitations of each platform, enabling informed decision-making for cloud-based application deployment.
4.K. Bajalcaliev (Innovation Dooel, Skopje, Macedonia), D. Mileski (Ss. Cyril and Methodius University/Faculty of Computer Science and Engineering, Skopje, Macedonia), P. Gushev (Innovation Dooel, Skopje, Macedonia), M. Gusev, B. Jakimovski (Ss. Cyril and Methodius University/Faculty of Computer Science and Engineering, Skopje, Macedonia)
Optimal Scalable Real-Time ECG Monitoring of Thousands of Concurrent Patients 
This paper explores the transformation of electrocardiogram (ECG) monitoring from traditional offline recording to Real-Time analysis, enabled by high-speed mobile networks and affordable data plans. It aims to find an optimal cloud architecture for efficient ECG processing for a large number of patients. The transition to live monitoring presents challenges in data streaming, processing, and the necessity of balancing immediacy with accuracy. Mobile device constraints require energy-efficient protocols for uninterrupted data transmission, while server-side processing must handle Real-Time data with minimal delay to facilitate immediate healthcare responses. The paper focuses on optimizing two critical aspects of cloud architecture: Scalability and Cost-Effectiveness, under the broader umbrella of Cloud Efficiency. It evaluates the architecture’s components and their contribution to overall efficiency, focusing on accommodating over a thousand concurrent patients streaming ECG data, ensuring Near Real-Time Round Trip Time (RTT) of ≤ 3 seconds, and maintaining cost-effectiveness. The goal is to present a comprehensive view of the current challenges and future potential of Real-Time ECG monitoring in the era of ubiquitous mobile connectivity, alongside proposing an efficient cloud architecture model for large-scale implementation.
5.J. Grönman (Satakunta University of Applied Sciences, Pori, Finland), P. Rantanen, P. Sillberg (Tampere University, Pori, Finland), T. Pohjola (University of Turku, School of Economics, Pori Unit, Pori, Finland), T. Jönkkäri (Tampere University, Pori, Finland)
Towards Improving Public Outdoor Sports Facilities by Gamification for Well-Being 
In Finland, and in many other countries, there is a worrying trend that people do not exercise as much as before. The motivation for outdoor activities is on the decline, especially amongst children. This trend can affect the well-being of individuals and cause expenses for the society in lower productivity as well as increases social welfare expenses. In commercial services, gamification has been used to motivate people to exercise, but there is room for improvement on the public sector especially since cities, municipalities and governments often pay the construction and maintenance cost of public sport and hobby venues. Thus, an increase in usage would mean more worth to taxpayers' money. In this paper, we show how basic technological solutions can be utilized to motivate people to exercise by the means of gamification and common goals for participants. We are especially interested in motivating people to take part in sports that are more rarely participated in - in this case cross-country skiing. The details of the system implemented (people counters and a web service), the gamification goals, and the results of a real-life case study in the public skiing track in the city of Pori, Finland, are presented.
6.P. Sillberg (Tampere University, Pori, Finland), J. Grönman (Satakunta University of Applied Sciences, Pori, Finland), M. Saari, M. Nurminen, T. Jönkkäri, P. Rantanen, P. Abrahamsson (Tampere University, Pori, Finland)
Digital Twin Coffee Room Application - Kahvibotti 
This study explores the potential of Internet of Things (IoT) technologies in enhancing energy efficiency in household appliances, focusing particularly on 'non-smart' devices. It examines how IoT can influence user decisions and encourage energy-efficient behavior. Employing a mixed-methods approach, the research is centered on a prototype IoT-enabled home appliance. This prototype provides real-time operational data, and its interaction with users is monitored through both quantitative usage statistics and qualitative feedback, collected via surveys and interviews. The primary objective is to evaluate the influence of IoT feedback on user decision-making and observe any trends towards more energy-efficient practices. The results are expected to offer valuable insights into the role of IoT in promoting sustainable living and energy efficiency within home environments.
High-Performance Computing 
1.J. Rybicki, C. Böttcher (Forschungszentrum Juelich GmbH, Juelich, Germany)
Data Logistics Service in eFlows4HPC 
Modern scientific endeavors often require complex, data-intensive workflows leveraging distributed and heterogeneous computing resources. Such workflows often include multiple steps of classical simulations, but increasingly also ML and AI components. As a result, they use not only HPC, but also cloud-like resources. Efficient and user-friendly execution and management of such workflows pose many challenges. In this paper, we share our experience in implementing three such workflows in the eFlows4HPC project. We focus, however, on the data management dimension of the workflows. How to ensure the timely availability of the required data, how to move data to and from compute resources, and how to make the workflows complete and portable. To this end, we implemented the Data Logistics Service, integrated it with the workflow execution engine, and defined multiple data movement pipelines to cater for specific scientific needs. We will share our experience from implementation and operation of the service. This will include building a solution for continuous deployment and access management in a federated environment. On a more abstract level, we also explore how the presented approach fits into the vision of the FAIR paradigm.
2.Z. Krpić, L. Loina, F. Sušac (Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, Croatia)
Optimizing HPL Performance on big.LITTLE Architectures: A Case Study with Odroid-MC1 Using ATLAS and OpenBLAS 
The rise of Edge Computing has brought Single Board Computing Clusters (SBCCs) back into the spotlight. With their efficient performance-to-power ratio, SBCs are becoming key players in Edge Computing infrastructure. Previous studies have explored the performance and power efficiency of SBCCs, yet often lack a systematic approach to benchmarking, especially for big.LITTLE ARM-based SBCs like the Odroid-MC1, Odroid-N2+, and ASUS’ Tinker Board 2 series. This study addresses the need for thorough benchmarking of such systems by employing the High Performance Linpack Benchmark (HPL). With precise tuning and improved cooling, we achieved up to 24% better performance on the same platforms using ATLAS and OpenBLAS, revealing more potential than initially anticipated and further improving their already notable performance-per-watt ratio.
Embedded Systems, Control and Automation 
1.M. Davidović (College for Information Technologies, Zagreb, Croatia), B. Vojnović (Rudjer Boskovic Institute, Zagreb, Croatia)
An Approach to System Effectiveness Determination 
Based on the comparison of approaches to definition of system effectiveness presently in use, a modified model is proposed. The model is a result of definition of system effectiveness as the probability of the performing system mission in defined time interval under the given conditions, divided by the relative cost of system mission. The possibility and limitation of this model in practice are considered (embedded systems).
2.T. Špoljarić (University of Applied Sciences in Zagreb, Zagreb, Croatia), A. Šešok, I. Pavić (Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia), B. Vuletić Komljen (University of Applied Sciences in Zagreb, Zagreb, Croatia)
Salp Swarm Algorithm Application in Simultaneous Parameter Selection of Generators’ Excitation Controllers for Power System Rotor Angle Stability Enhancement - WSCC Case Study 
In this paper a rotor angle stability of a power system, represented by WSCC model (Western standard coordinated council) is investigated after testing such a system in several disturbance conditions. In these conditions generators’ excitation controllers AVR and PSS are being simultaneously tuned with the purpose of achieving satisfactory oscillations in angular speeds, voltages, and transmission line power transfer. Four different single-objective metaheuristic algorithms are used for controllers’ parameter change, algorithm comparison and performance analysis. Every algorithm has the same starting population, two different single objective functions (time-domain error oriented function and transitional process quality oriented function) and three power system disturbance scenarios. Proposed SSA algorithm is also compared with three other algorithms: PSO (particle swarm optimization), SA (simulated annealing) and ALO (ant lion optimizer). Algorithms' performance is compared by quality indicators: best result, mean value, standard deviation, and convergence capability.
3.D. Miljković (Hrvatska elektroprivreda d.d., Zagreb, Croatia)
Brief Introduction to Active Noise Control in Cars 
Active noise control (ANC), is a method for reducing unwanted sound based on destructive interference between offending primary noise and secondary “antinoise”. Noise in interiors of vehicles is composed of induction noise, exhaust noise, noise from accessories, tire noise and noise radiation from engine sources. This paper reviews basic concepts of ANC applied to cars. It is achieved by introduction of ANC controller in addition to classical passive approaches of noise reduction. ANC in cars is quite successful at canceling tonal and low frequency noises. Reduction of lower mid frequencies could be achieved by ANC implemented by active headrests, with virtual microphones and even head position tracking.

Osnovni podaci:

Vlado Sruk (Croatia), Dejan Škvorc (Croatia)

Programski odbor:

Goran Delač (Croatia), Željko Hocenski (Croatia), Leonardo Jelenković (Croatia), Hrvoje Mlinarić (Croatia), Adrian Satja Kurdija (Croatia), Vlado Sruk (Croatia), Marin Šilić (Croatia), Dejan Škvorc (Croatia), Klemo Vladimir (Croatia)


Do 6.5.2024.
Od 7.5.2024.
Članovi MIPRO i IEEE
Studenti (preddiplomski i diplomski studij) te nastavnici osnovnih i srednjih škola

Popust se ne odnosi na studente doktorskog studija.

OBAVIJEST AUTORIMA: Uvjet za objavu rada je plaćanje najmanje jedne kotizacije po radu. Autorima 2 ili više radova, ukupna se kotizacija umanjuje za 10%.


Vlado Sruk
Fakultet elektrotehnike i računarstva
Unska 3 
10000 Zagreb, Hrvatska 

Tel.: +385 1 612 99 45
Faks: +385 1 612 96 53 

Dejan Škvorc

Fakultet elektrotehnike i računarstva
Unska 3 
10000 Zagreb, Hrvatska 

Tel.: +385 1 612 99 43
Faks: +385 1 612 96 53 

Najbolji radovi bit će nagrađeni.
Prihvaćeni radovi bit će objavljeni u zborniku radova s ISSN brojem. Radovi na engleskom jeziku prezentirani na skupu bit će poslani za uključenje u digitalnu bazu IEEE Xplore
Postoji mogućnost da se odabrani znanstveni radovi uz određenu doradu objave u sljedećim časopisima: Journal of Computing and Information Technology (CIT)MDPI Applied ScienceMDPI Information JournalFrontiers i EAI Endorsed Transaction on Scalable Information Systems.


Mjesto održavanja:

Opatija je vodeće ljetovalište na istočnoj strani Jadrana i jedno od najpoznatijih na Mediteranu. Ovaj grad aristokratske arhitekture i stila već više od 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 i

Novosti o događaju
Trenutno nema novosti
Suorganizatori - nasumično
A1 HrvatskaEkonomski fakultet RijekaTehničko veleučilište u ZagrebuHATZUNIPU