Search  English (United States) Hrvatski (Hrvatska)

innovative promotional partnershipICT in renewable energy technologies

MIPRO 2021 - 44th International Convention

SP - MIPRO Junior - Student Papers

Wednesday, 9/29/2021 2:00 PM - 6:45 PM, Online

Virtual Event

Event program
Wednesday, 9/29/2021 2:00 PM - 6:45 PM,
2:00 PM - 2:05 PM Introduction 
2:05 PM - 3:50 PM Papers 
1.M. Kučić (Faculty of Engineering, Rijeka, Croatia)
Creating a Web Corpus Using GO 
2.M. Vasilj, S. Skender, M. Jurdana, M. Horvat (University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
DESPRO: Decentralized Business Platform for Student Non-profit Organizations 
Student non-profit organizations are a specific type of small associations that congregate students from diverse backgrounds around a common purpose. These organizations are non-profit driven, autonomous, and typically have largely similar statutes and regulations. In the context of software engineering, information systems that support their business processes have similar software requirements specifications. DESPRO is a web-based application that fully supports principal use cases of students’ non-profit organizations. The application has three uses: accounting, voting, and fundraising management. DESPRO allows such organizations to begin with their principal operations practically immediately without unnecessary overhead. Unique features that distinguish DESPRO from other similar systems are: 1) lightweight and streamlined deployment process, 2) minimal required remote maintenance, 3) pre-defined functionalities specifically suited for student non-profit organizations, 4) user anonymity customized to specific functional requirements, 5) voting without prior user registration. The application was developed with open technologies Node.js, Vue.js, Bootstrap, Veautify, Sequalize, Web3, Axios, MariaDB, and smart contracts Ethereum blockchain. It is freely available for non-commercial use by contacting the first author.
3.D. Beronić, P. Pufek, B. Mihaljević, A. Radovan (RIT Croatia, Zagreb, Croatia)
On Analyzing Virtual Threads – a Structured Concurrency Model for Scalable Applications on the JVM  
Various blocking operations, such as input/output (IO) operations, are an essential functionality of concurrent applications. However, these operations often cause efficiency-related challenges in multithreaded applications because of the single-thread access policy. IO operations' speed and efficiency heavily rely on operating system (OS) threads and scheduling processes, which is time consuming because of the insufficient distribution of OS resources. Because of their overgeneralization, required to support various usage scenarios, robust OS kernel threads are commonly heavyweight and oversized, created in a limited number, and heavily dependent on OS schedulers. Various asynchronous programming techniques tackled issues in implementing modern concurrent applications with blocking operations with the complete reconstruction of threads and their schedulers. Based on our previous preliminary research, we further explored a model of structured concurrency in Java Virtual Machine (JVM), through the updated implementation of virtual threads and accompanying schedulers, as a novel form of lightweight user-mode threads in the JVM, decoupled from OS threads and managed within the JVM. In this paper, we present our findings about the efficiency of those schedulers utilized for virtual threads on blocking operations, compared with the implementation of OS threads' schedulers, and review possibilities of reducing memory footprints and context switching costs.
4.D. Doljanin, L. Pranjić, L. Jelečević, M. Horvat (University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
Adaptive Intelligent Agent for e-Learning: First Report on Enabling Technology Solutions 
Because of the global COVID-19 pandemic, online learning has become the dominant teaching method. Moreover, a wide range of e-learning pedagogies are rapidly gaining importance, and in some cases emerging as the preferred approach in education over the traditional methods and techniques of classroom teaching. However much has to be done to efficiently assess student engagement and the learning curve. In this regard, we have proposed construction of an intelligent agent for personalized and adaptive assessment of learning performance based on methods for automated estimation of attention and emotion. We report on the first progress towards the development of the intelligent agent. Three classifiers were used in parallel to detect information about the progress of student engagement. Object detection in video is accomplished with YOLOv3, emotion detection from facial expressions using PAZ software library, and detection of head, arms, and upper-body orientation and position with OpenPose system. NimStim facial expression database, WIDER Attribute Dataset, and UPNA Head Pose Database were used for experimental validation of the individual classifiers. Our system attained the highest precision and recall of 79.13% and 94.15%, respectively, and the highest success rate of 59.56% in recognition of 6 discrete emotions from facial expressions.
5.M. Šipek, D. Muharemagić, B. Mihaljević, A. Radovan (Rochester Institute of Technology Croatia, Zagreb, Croatia)
Next-Generation Web Applications with WebAssembly and TruffleWasm 
JavaScript-based eco-system used for the development of web-based applications presents many advantages; it is simple to develop, JavaScript is an interpreted programming language meaning the system a reduced compilation time, and it offers a lot of third-party libraries and extensions. However, with the rise of modern highly user-interactive web sites and browser-based video games, the JavaScript engine lacks performance and responsiveness itself. Developers tend to use a lot of tools and languages such as C++, Python, Go, or similar to create a user-interactive and interoperable system. The interoperability modules offer great advantages but often lack in execution due to high complexity and longer compilation time. This paper studies WebAssembly, a binary format compilation target that includes a low-level assembly-like language used for targeting from other programming languages. The binary format allows near-native performance level due to its compactness, as it prioritizes usage of low-level languages. Simultaneously, in this paper, we continued our research regarding the GraalVM ecosystem with a guest language implementation of a WebAssembly based system, TruffleWasm, which is hosted on GraalVM and Truffle Java framework. Finally, we present the system architecture, several performance tests within our academic environment, as well as a review on the GraalVM based eco-system.
6.M. Iveta (Faculty of Electrical Engineering and Computing, Zagreb, Croatia), A. Radovan (BISS, Zagreb, Croatia), B. Mihaljević (Rochester Institute of Technology Croatia, Zagreb, Croatia)
Prediction of Traffic Accidents Severity Based on Machine Learning and Multiclass Classification Model 
Road traffic accidents are a common and seemingly inevitable problem. While its occurrences rely on many unpredictable factors, this paper shows how to utilize machine learning to predict the severity of the accident. The dataset used was related to road accidents in the United Kingdom over a period of a few years. Some of the parameters observed were the weather conditions, sun position, speed limit, and time of the day. To predict the severity of the accident given the circumstances and road conditions, a multiclass classification model is used. Different datasets were combined to cover different situations and scenarios that happen in traffic and taking the severity of accidents in prediction. The dataset values were normalized before the training process and the training set and validated on the validation dataset. The prediction results show the correlation between used weather conditions, daylight time, and traffic accident severity.
7.L. Shkurti (South East European University, Prizren, Kosovo), H. Snopçe, L. Abazi-Bexheti, M. Selimi (South East European University, Tetovo, Macedonia), F. Kabashi (South East European University, Prizren, Kosovo)
Plagiarism on Controlled Documents: A case study from University ”Ukshin Hoti” Prizren 
The issue of plagiarism has only become a recent priority in Kosovo, some public universities have taken steps to create their anti-plagiarism system which is one of the methods that are being done to prevent plagiarism. The only public University that has implemented the anti-plagiarism system in Kosovo is the University ”Ukshin Hoti” Prizren. The research is based on the dataset obtained from the University ”Ukshin Hoti” Prizren. In this paper, the data extracted from the SAP anti-plagiarism software of the University ”Ukshin Hoti” for the controlled documents from 17.11.2020 to 19.01.2021 are analyzed. Initially, we will examine the frequency distribution analyzes for faculties, levels of studies, the status of documents, and the type of documents were extracted from the dataset. Then, we show descriptive statistics for local similarity, RL similarity, character, and word count. After the descriptive statistics, we are going to analyze the One-Way ANOVA for total similarity, local similarity, and URL Similarity by faculty. Also, by the T-Test, we analyzed differences in similarity rates by study level and document type. The results obtained show that there are significant differences between faculties in terms of plagiarism ratio. Also, there are differences in plagiarism according to the type of documents. However, no significant difference was found in plagiarism according to the level of studies.
3:50 PM - 4:20 PM Break 
4:20 PM - 6:35 PM Papers 
8.L. Udovičić, N. Tanković (Sveučilište Jurja Dobrile u Puli, Fakultet informatike u Puli, Pula, Croatia)
Dew-Based Service Orchestration Model for Systems Spanning Multiple Computing Layers 
Cloud-Edge systems have emerged to reduce the latency of data processing in the Cloud. With the addition of a third layer that focuses on on-premises computing, resource capacity can be further increased and the availability of computational resources in close proximity of end-users can satisfy stringent latency requirements or enable different functionalities that depend on the quality of available resources. A lot of work has been done on the Dew computing layer as the lowest layer and how it fits into the current paradigm. One of the major challenges of service-oriented architecture that spans multiple computing layers is resource management and service distribution. In this paper, we propose a model for describing what services, resources, and devices are needed to enable functionalities to the end-users, and a model that uses what we call functionality graphs to distribute, manage and orchestrate services in a multi-layered system from the Dew layer.
9.M. Sršen, T. Orehovački (Juraj Dobrila University of Pula, Pula, Croatia)
Developing Game Engine in C# Programming Language 
A video game refers to a digital breed of entertainment experienced on various devices, including personal computers, gaming consoles, tablets, and smartphones. For some time now, video games have not been perceived as a form of play solely reserved for children but as the way of spending the leisure time enjoyed by a vast of adults worldwide. As a result, the video games sector has become a behemoth larger than the movie and music industry combined, and it is growing on daily basis. The process of developing video games is more complex than ever which is the reason why every now and then novel game engine is proposed. The objective of this paper is to present features of a game engine that was implemented in C# programming language. The introduced game engine draws on MonoGame library that contains collection of functions and commands thus facilitating the creation of a virtual space and supporting the development of video games. The functionalities and capabilities of the presented game engine are demonstrated on the examples of 2D and 3D video games prototypes.
10.M. Cerjan, K. Rabuzin, R. Kudelić (Faculty of Organization and Informatics, Varaždin, Croatia)
Primjena ključ-vrijednost baza podataka 
Današnji zahtjevi s kojima se svijet susreće zahtijevaju brza i efikasna rješenja. Takva rješenja omogućavaju nerelacijske baze podataka koje su usmjerene na poslovne sustave ne bi li se rukovalo sa nestrukturiranim i strukturiranim podacima i samim time povećala fleksibilnost i brzina razvoja. Problem koji se razmatra u radu je kako pospješiti komunikacijski proces između profesora i studenta/učenika u školskom sustavu koristeći nove tehnologije. Kroz rad će se demonstrirati izrada aplikacije te iznijeti prednosti i nedostaci NoSQL sustava i ključ-vrijednost baze podataka.
11.I. Jurenić, J. Ćurković, V. Šimović (Zagreb University of Applied Sciences, Zagreb, Croatia)
Clutch compensation system for motorcycles using an embedded system 
On a motorcycle the role of the clutch is to disengage and engage the power from the engine of the rear wheel. This paper presents an implementation of a clutch compensation system using an embedded system that allows shifting to a higher gear under full acceleration without using the clutch itself. Throughout the paper we examine its inner workings, its implementation on a specific motorcycle and a look at its potential benefits.
12.D. Gudelj, A. Stama, J. Petrović, P. Pale (Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
Visual Object Detection - an Overview of Algorithms and Results  
Object detection is an active area of research with rapid growth in the number of new publications. It is a computer vision technique widely used in various domains and it forms a foundation for a variety of applications, such as face detection and autonomous driving. The precondition for successful object detection are efficient algorithms that are able to detect features related to a certain object in static or moving images and the processing power which ensures a fast execution. This paper provides an overview of the current most significant visual object detection algorithms, their essential features, their advantages, limitations, as well as datasets used for their training and evaluation. Based on the provided overview, this paper attempts to also recognize directions for further development and contribution to the area.
13.S. Garg, P. Pundir (Jaypee University of Information Technology, Solan, India)
MOFit: A Framework to Reduce Obesity Using Machine Learning and IoT 
From the past few years, due to advancements in technologies, the sedentary living style in urban areas is at its peak. This results in individuals getting a victim of obesity at an early age. There are various health impacts of obesity like Diabetes, Heart disease, Blood pressure problems, and many more. Machine learning from the past few years is showing its implications in all expertise like forecasting, healthcare, medical imaging, sentiment analysis, etc. In this work, we aim to provide a framework that uses machine learning algorithms namely, Random Forest, Decision Tree, XGBoost, Extra Trees, and KNN to train models that would help predict obesity levels (Classification), Bodyweight, and fat percentage levels (Regression) using various parameters. We also applied and compared various hyperparameter optimization (HPO) algorithms such as Genetic algorithm, Random Search, Grid Search, Optuna to further improve the accuracy of the models. The website framework contains various other features like making customizable Diet plans, workout plans, and a dashboard to track the progress. The framework is built using the Python Flask. Furthermore, a weighing scale using the Internet of Things (IoT) was also integrated into the framework to track calories and macronutrients from food intake.
14.S. Domitran, M. Bagić Babac (Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
A Machine Learning Approach to Flight Control of a VTOL Tailsitter UAV 
Unmanned aerial vehicles, commonly known as drones,are used for many different purposes. However, it is still a challenging task to fly a drone, which limits its potential for doing more useful things. The goal of this paper is to explain how to fly a drone using amachine learningapproach, which should make its flight more accurate, efficient and stable. In this paper, we propose an artificial-intelligence-based flight control of unmanned aerial vehicles in a realistic simulated environment.. In addition, the drone can learn to perform a certain task to elaborate the benefits of this approach.
15.G. Borković, M. Fabijanić, M. Magdalenić, A. Malobabić, J. Vuković (Faculty of Electrical Engineering and Computing, Zagreb, Croatia), I. Zielinski (Wroclaw University of Science and Technology, Wroclaw, Poland)
Underwater ROV Software for Fish Cage Inspection 
This paper deals with the development of control software for a remotely operated vehicle (ROV) as part of an automated fish cage inspection system in aquaculture. The ROV navigates autonomously around the fish cages streaming video to the topside computer that runs the algorithms for vertical rope detection. The topside computer sends back the velocity references to the ROV in real-time in order to successfully complete the inspection task. These images are also used to determine the state of net biofouling using a pre-trained convolutional neural network to help determine which nets are in need of cleaning. Robot Operating System (ROS) framework is developed to enable the topside computer to access the video stream from the ROV, process the images, and send back velocity references that would result in the complete inspection of fish cages. The inspection task is planned by following the recognizable rope segments of the outer structure of the fish cage downwards by controlling the vehicle's yaw, heave, and depth.
16.F. Pavić, L. Brkić (University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia)
Methods of Improving and Optimizing React Web-applications 
As web browsers become more advanced every day and support many new technologies, web applications become more complex. Web application performance is vital for its users to have a good experience. It refers to how quickly an application loads and renders in a web browser, and how well it responds to user requests. Good performance may not be obvious to most web application users, but they will immediately recognize a sluggish web application. Paying attention to web application performance is important for both Single Page Applications and traditional server-side rendered web applications. In this paper, we describe and discuss a couple of common approaches to speed up the performances and the initial loading of a React web application. First, we discuss techniques for minimizing program code, then using optimized image formats and the importance of server-side rendering, and finally, we provide a few examples of other performance-optimization techniques that can further improve the user experience.
6:35 PM Closing statement 

Basic information:

Nikola Filip Fijan (Croatia), Dubravko Sabolić (Croatia), Benjamin Kušen (Croatia)

Registration / Fees:
Price in EUR
Up to 13 September 2021
From 14 September 2021
Members of MIPRO and IEEE
Students (undergraduate and graduate), primary and secondary school teachers

The discount doesn't apply to PhD students.


Nikola Filip Fijan
Unska 3
HR-10000 Zagreb, Croatia

GSM: +385 91 753 8638

The best papers will get a special award.
Accepted papers will be published in the ISSN registered conference proceedings. Presented papers in English will be submitted for inclusion in the IEEE Xplore Digital Library.
There is a possibility that the selected scientific papers with some further modification and refinement are being published in the Journal of Computing and Information Technology (CIT).


Opatija, with its 170-year-old tourism 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 artists, kings, politicians, scientists, sportsmen, as well as business people, bankers and managers for more than 170 years.

The tourist offer in Opatija includes a vast number of hotels, excellent restaurants, entertainment venues, art festivals, superb modern and classical music concerts, beaches and swimming pools – this city satisfies all wishes and demands.

Opatija, the Queen of the Adriatic, is also one of the most prominent congress cities in the Mediterranean, particularly important for its ICT conventions, one of which is MIPRO, which has been held in Opatija since 1979, and has attracted more than a thousand participants from over forty countries. These conventions promote Opatija as one of the most desirable technological, business, educational and scientific centers in South-eastern Europe and the European Union in general.

For more details, please visit and

News about event
Currently there are no news
Patrons - random
UNIPUT-HT ZagrebHEP ZagrebSveučilište u ZagrebuSveučilište u Rijeci