Informatica
https://www.informatica.si/index.php/informatica
<p>Informatica <span>(print edition ISSN: 0350-5596, online edition ISSN: 1854-3871) </span> is an international journal with its base in Europe. It publishes peer-reviewed papers from all areas of computer science, informatics and cognitive sciences,<br />with a focus on intelligent systems and software in general.</p><p>Informatica publishes <span>several types of papers, including</span>:</p><ul><li>Technical papers reporting novel research</li><li>Overview papers covering a subarea of computer and information science</li><li><span>Position papers presenting an interesting plausible scientific opinion</span></li><li><span>PhD paper describing recent doctoral dissertation on 2 pages</span></li><li><span>Student papers</span></li></ul><p>Informatica has been published continuously since 1977, at least four times a year by the <a href="http://www.drustvo-informatika.si/" target="_blank">Slovenian Society Informatika</a>.</p><p>2023 indexes:<br />Scopus SCImago h-index: 38<br />Impact Scopus score: 1.90<br />SJR: 0.242<br />Academic Accelerator computed the simulated Impact factor: <a href="https://academic-accelerator.com/Impact-of-Journal/Informatica-Ljubljana" target="_blank">0.762</a>.</p><p><span>The acceptance rate for the year 2023 is 32%.</span></p><div class="moz-cite-prefix">At the first step of submission, please input N, F or UF in the Comments for the Editor section to select Normal, Fast (guaranteed 6 months, free of charge) and Ultra Fast (1 months, fee) review. For UF also send an email to <a href="mailto:journal.informatica.si@gmail.com" target="_blank">journal.informatica.si@gmail.com</a>.</div><div class="moz-cite-prefix"> </div><div class="moz-cite-prefix"><a title="Updated guidelines for authors" href="/index.php/informatica/about/submissions#authorGuidelines" target="_self"><strong>Updated guidelines for authors</strong></a></div><div class="moz-cite-prefix"> </div>
Slovenian Society Informatika
en-US
Informatica
0350-5596
<p>I assign to<em> Informatica</em>, <em>An International Journal of Computing and Informatics</em> ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.</p><p>I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.</p><p>In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.</p><p>I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.</p><p><span><span><br /></span></span></p><p><span id="docs-internal-guid-fe2b3ee1-6049-9593-cc52-04d02fbbc889"><span>Copyright © Slovenian Society Informatika</span></span></p>
-
An Overview on Robot Process Automation: Advancements, Design Standards, its Application, and Limitations
https://www.informatica.si/index.php/informatica/article/view/5058
In a variety of areas, including healthcare, banking, and manufacturing, repetitive and rule-based processes are automated using robotic process automation (RPA), a fast developing technology. An overview of RPA's, its uses, limitation, and applications are given in this paper. RPA can lower costs, increase process speed, accuracy, and efficiency, and free up staff to concentrate on jobs of higher value. RPA is frequently used for tasks including data input, billing, and customer care. RPA can't, however, execute activities that call for human judgment, decision-making, or creativity, for instance. The adoption of RPA also needs a sizable initial investment and continual maintenance. This paper also touches on a few RPA-related ethical issues, like employment displacement and data privacy. While RPA has a great deal of promise to alter sectors, its deployment can only be successful if its limitations and ethical implications are carefully considered.
Rajkumar Palaniappan
2024-02-28
2024-02-28
48 1
-
Application of Agent-Based Modelling in Learning Process
https://www.informatica.si/index.php/informatica/article/view/4086
<p class="IAbstract">With advances in information and communication technologies and rapid computing and technological progress, modeling, and simulation of real problems, has become the most important teaching and learning method in educational process. Representing and explaining processes through simulations can enable students to easier understand these processes and discover the essential properties of a system. In many situations, in learning different subjects it is not possible to experiment with real objects to find the right solutions, therefore modelling and simulation can be used to build models that represent the real systems. Agent-based modelling (ABM) is a powerful simulation modelling technique, that can be easily incorporated in learning and teaching processes. Agent based modelling (ABM) is a relatively new method compared to system dynamics and discrete event modelling. In ABM a system is modelled as a collection of autonomous decision-making entities called agents, that can interact among each other’s. In this paper, the agent-based modelling simulation is considered as a tool in educational process for learning and teaching different subjects. Anylogic software is used for some simulation examples of agent-based modelling that can be used in educational process.</p>
Natasha Stojkovikj
Limonka Koceva Lazarova
Aleksandra Stojanova
Marija Miteva
Biljana Zlatanovska
Mirjana Kocaleva
2024-01-31
2024-01-31
48 1
-
A Novel Fuzzy Modified RAFSI Method and its Applications in Multi-Criteria Decision-Making Problems
https://www.informatica.si/index.php/informatica/article/view/4144
<p class="papertitle">In real-life decision-making problems, the constraints may change from time to time. Considering the change of elements of certain decisions which lead to the introduction of new alternative or removal of old alternative to the existing decision causing rank reversal. Rank reversal is the most significant problem that can’t be ignored in the MCDM methods. Ranking of alternatives through functional mapping of criterion subintervals into a single interval (RAFSI) method effectively removes the problem of rank reversal, but there are some limitations like standardized decision matrix is obtained by the assumption of supreme value as at least six times improved than the anti-supreme value, which is not always true. This paper aims to address those limitations by giving a modified form of the RAFSI (MRAFSI) method. As real-life problems are associated with uncertainty in form of linguistic terms, a fuzzified form of the MRAFSI method has been given using triangular fuzzy numbers (TFNs) to deal with uncertainty. The effectiveness of the presented method is illustrated using a real-time case study to rank five stocks under the National Stock Exchange (NSE) for the year 2021 and is compared with other MCDM methods for validation. The supplier selection problem has been taken as an example to show the application of the Fuzzy Modified RAFSI (FMRAFSI) method.</p>
Garima Bisht
A. K. Pal
2024-01-31
2024-01-31
48 1
-
A Deep Learning Model for Context Understanding in Recommendation Systems
https://www.informatica.si/index.php/informatica/article/view/4475
<p>Due to the robust growth in the amount of data and Internet users, there has been a significant rise in information overload, hindering timely access to user demand. While information retrieval systems, such as Google, Bing, and Altavista have partially addressed this challenge, prioritization and personalization of information have yet to be fully implemented. Therefore, recommendation systems are developed to resolve the issue by filtering and segmenting important information from an enormous volume of data based on different criteria such as preferences, interests, and user behaviors. By collecting data on users' interests and purchased products, the system can predict whether a particular user would enjoy an item, thus delivering an appropriate suggestion strategy. However, the increased number of Internet users and items has resulted in sparseness in increasingly vast datasets, reducing the performance of recommendation algorithms. Therefore, this study developed a model integrating Convolutional Neural Network (CNN) and Matrix Factorization (MF) to add extra product and user information, extract contexts, and add bias to the observed ratings in the training process, attempting to enhance the recommendation accuracy and context understanding. This approach can take advantage of CNN to efficiently capture an image's or document's local features, with the combination of MF to create relationships between 2 main entities, users and items. The proposed model obtained the highest RMSE of 0.93 when predicting favorable movies for 4,000 users, with an ability to learn complex contextual features and suggest more relevant content. The results are promising and can act as a reference for developing context understanding in recommendation systems, and future work may focus on optimizing the performance and developing more text-processing techniques.</p>
Ngo Le Huy Hien
Luu Van Huy
Hoang Huu Manh
Nguyen Van Hieu
2024-01-31
2024-01-31
48 1
-
Identification of Students’ Confusion in Classes from EEG Signals using Convolution Neural Network
https://www.informatica.si/index.php/informatica/article/view/4604
<p>For a student, classes are vital factors for gaining knowledge. The lectures may be online or offline, but getting knowledge without confusion is a major issue. Confusion of students can be rectified after knowing that students are suffering from confusion and the confusion labels can be measured from the electroencephalography signals of the students. Machine learning approaches were implemented on electroencephalography signals to identify the suffering of students from confusion. The performance of traditional<br />machine learning approaches in predicting confusion status is found as poor. The one-dimensional convolution neural network is implemented on the electroencephalography signals of students, when they were watching video classes, to detect confusion in<br />the students. Students’ attention, mediation, electroencephalography signals frequency, delta, theta, alpha1, alpha2, beta1, beta2, gamma1 and gamma2 are generated from electroencephalography signals and are taken into consideration to training one-dimensional convolution neural network classifier and have achieved a better accuracy in detecting the confusion of the students. Besides finding confusion label of students, when understandable classes are creating confusion and difficult classes is understandable by students are identified from electroencephalography signals. This identification can help for improving students’ deficiencies by examining and treating. For future work, more data and different aspects of the students can be taken into consideration for detecting confusion and different obstacles to having perfect knowledge from the classes.</p>
Rekha Sahu
Satya Ranjan Dash
Amarendra Baral
2024-01-31
2024-01-31
48 1
-
A Hybrid Feature Selection Based on Fisher score and SVM-RFE for Microarray Data
https://www.informatica.si/index.php/informatica/article/view/4759
In the last two decades, analyzing microarray data plays a critical role in disease diagnosis and identification of different tumors. However, it is difficult to classify microarray data because of the curse of the dimensionality problem, in which the number of features is huge while the number of samples is small. Thus, dimension reduction techniques, such as feature selection methods, play a vital role in eliminating non-informative features and enhancing cancer classification. In this paper, we propose a Filter-embedded hybrid feature selection method for the gene selection problem. First, the proposed method selects the top-ranked features obtained from the Fisher score to provide a candidate subset for the embedded stage. Second, Support Vector Machine-Recursive Feature Elimination (SVM-RFE) applies to the candidate subset to find the optimal subset. We assess the performance of our proposed method over ten high-dimensional microarray datasets. The results reveal that the proposed method enhances the classification accuracy, reduces the number of selected features, and decreases computational time.
Hind Hamla
Khadoudja Ghanem
2024-01-31
2024-01-31
48 1
-
Prediction of Author’s Profile basing on Fine-Tuning BERT model
https://www.informatica.si/index.php/informatica/article/view/4839
The task of author profiling consists in specifying the infer-demographic features’ of the social networks’ users by studying their published content or the interactions between them. In the literature, many research works were conducted to enhance the accuracy of the techniques used in this process. In fact, the existing methods can be divided into two types: simple linear mod-els and complex deep neural network models. Among them, the transformer-based model exhibited the highest efficiency in NLP analysis in several lan-guages (English, German, French, Turk, Arabic, etc.). Despite their good per-formance, these approaches do not cover author profiling analysis and, thus, should be further enhanced. So, we propose in this paper a new deep learning strategy by training a customized transformer-model to learn the optimal fea-tures of our dataset. In this direction, we fine-tune the model by using the trans-fer learning approach to improve the results with random initialization. We have achieved about 79% of accuracy by modifying model to apply the retrain-ing process using PAN 2018 authorship dataset.
Bassem Bsir
Nabil Khoufi
Mounir Zrigui
2024-01-31
2024-01-31
48 1
-
Liver Disease Classification - An XAI Approach to Biomedical AI
https://www.informatica.si/index.php/informatica/article/view/4611
<p>Explosive amounts of biological and physiological data, including medical images, electroencephalograms, genomic information, and protein sequences, have been made available to us thanks to advances in biological and medical technologies. Understanding human health and disease is made easier by using this data for learning. Deep learning-based algorithms, which were developed from artificial neural networks, have significant potential for identifying patterns and extracting features from large amounts of complex data. However, these recent advancements involve blackbox models: algorithms that do not provide human-understandable explanations in support of their decisions. This limitation hampers the fairness, accountability and transparency of these models; the field of XAI tries to solve this problem providing human-understandable explanations for black-box models. This paper focuses on the requirement for XAI to be able to explain in detail the decisions made by an AI in a biomedical setting to the expert in the domain, e.g., the physician in the case of AI-based clinical decisions related to diagnosis, treatment, or prognosis of a disease. In this paper, we made use of the Indian Patient Liver Dataset (IPLD) collected from Andhra Pradesh region. The deep learning model with a 0.81 accuracy score (0.82 for the hyperparameter- tuned model) is built on Keras-Tensorflow and due to the imbalance in the target values, we integrated GANs as a means of oversampling the dataset. This study integrated the XAI concept of Shapley Values to shed light on the predictive results obtained by the liver disease detection model.</p>
Ebenezer Agbozo
Daniel Musafiri Balungu
2024-01-31
2024-01-31
48 1
-
Simulation for Dynamic Patients Scheduling based on Many Objective Optimization and Coordinator
https://www.informatica.si/index.php/informatica/article/view/5256
<div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>Problem načrtovanja sprejema pacientov (PASP) vključuje načrtovanje pacientovega </span><span>sprejema, l</span><span>okacije in časa v bolnišnici, da se dosežejo določeni cilji glede kakovosti storitev in stroškov, zaradi česar je problem kombinatorične optimizacije z več cilji in NP</span><span>-</span><span>težke narave. Poleg tega se PASP uporablja v dinamičnih scenarijih, kjer se pričakuje, da bodo pacienti prispeli v bolnišnice zaporedno, kar zahteva dinamično ravnanje z optimizacijo. Ob upoštevanju obeh vidikov, optimizacije in dinamičnega upoštevanja, predlagamo simulacijo za dinamično razporejanje pacientov, ki temelji na optimizaciji z več cilji, oknu in koordinatorju. Vloga optimizacije z več cilji je obravnavanje številnih mehkih omejitev in zagotavljanje nabora nedominiranih rešitev koordinatorju. Vloga okenca je zbiranje novoprispelih </span><span>pacientov in predhodno nepotrjenih pacientov z namenom posredovanja koordinatorju. Nazadnje, vloga </span><span>koordinatorja je, da iz okna izloči podmnožico pacientov in jih posreduje algoritmu za optimizacijo. Po drugi strani pa je koordinator odgovoren tudi za izbiro ene od neprevladujočih rešitev, da jo aktivira v bolnišnici in odloča o nepotrjenih bolnikih, da jih vstavi v okno za naslednji krog. Vrednotenje simulatorja in primerjava med več optimizacijskimi algoritmi kažeta superiornost NSGA</span><span>-III glede na pokritost nabora in vrednosti mehkih omejitev. Zato je obra</span><span>vnavanje PASP kot dinamične optimizacije z več cilji koristna rešitev. NSGA</span><span>-II je zagotovil 0,96 odstotka prevlade nad NSGA-II in 100-odstotni odstotek prevlade vseh drugih algoritmov </span></p></div></div></div>
Ali Nader Mahmed
M. N. M. Kahar
2024-02-28
2024-02-28
48 1
-
Multimedia VR Image Improvement and Simulation Analysis Based on Visual VR Restructuring Algorithm
https://www.informatica.si/index.php/informatica/article/view/5368
Due to the advancement of science and technology, the application of virtual reality technology is more and more extensive, and people can truly immerse themselves in virtual space through virtual reality. Relying on the visual VR reconstruction algorithm, this paper deals with the problems of "burring" and insufficient compression of relatively simple video imaging devices. Based on the virtual reality technology, the multimedia effect of the video image is processed, and according to six operation modules, a system combining virtual reality technology is designed. From the aspect of determining the relationship between video image data and color, it is classified into three types: binary image, pseudo-color image, and grayscale image, and the grid of each point is defined and quantified. The extreme value filtering algorithm performs a sorting calculation on the image pixels in the filtering window to improve the image effect with the threshold value suitable for filtering processing. Simulation results show that the VR visual restoration algorithm has a higher compression ratio and visual efficiency and can effectively support multimedia VR image improvement and simulation analysis
Xiangyang Xu
2024-02-28
2024-02-28
48 1
-
IoT Based Model for Data Analytics of KPI Platform in Continuous Process Industry
https://www.informatica.si/index.php/informatica/article/view/3826
<p class="abstractSi">Internet of Things (IoT) is gaining momentum now a days to real time operational environment. The related technologies of IoT is converging to the main stream of industrial applications and replacing the conventional models of data acquisition, analysis, visualization and control in continuous manufacturing process industries. In this paper, we are proposing an IoT based model platform for acquiring various data that is generated in a continuous process manufacturing plant. This includes data from mobile devices and ERP systems as well. This is analyzed using machine learning and artificial intelligence technologies which leads to visualization of Key Performance Indicators (KPIs). It can be displayed on plant level as well as head office level in static and mobile devices. Control instructions can also be given from static devices as well as from mobile devices. Along with proposed platform concept, a prototype is also developed for cement manufacturing plant which is a core engineering continuous process manufacturing industry. The general KPIs in cement plants are explained and the KPIs generated in visualizing devices by the prototype platform are also provided in this paper. </p>
Jeeva Jose
Vijo Mathew
2024-01-31
2024-01-31
48 1
-
Generating Lyrics Using Constrained Random Walks on a Word Network
https://www.informatica.si/index.php/informatica/article/view/3366
<span style="left: 112.26px; top: 294.725px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.989506);">In the paper we present an approach for automatic lyrics generation. From the Amer</span><span style="left: 112.26px; top: 310.532px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(1.02381);">ican National Corpus of written texts we build a</span><em><span style="left: 394.76px; top: 310.532px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(1.00237);"> Word Network</span></em><span style="left: 476.947px; top: 310.532px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.969279);">, which encodes word</span><span style="left: 112.26px; top: 326.339px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.909817);">sequences. Lyrics are then generated by performing a constrained random walk over </span><span style="left: 112.26px; top: 342.146px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.982051);">the </span><em><span style="left: 134.442px; top: 342.146px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.987001);">Word Network</span></em><span style="left: 215.376px; top: 342.146px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.949705);">. The constraints include the structure of the generated sentence, the</span><span style="left: 112.26px; top: 357.953px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.952642);"> rhythm of the lines of the stanza or the rhymes of the stanza itself. Lyrics are generated </span><span style="left: 112.26px; top: 373.762px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.967814);">using each constraint individually and also using all three constraints at the same time.</span><span style="left: 112.26px; top: 389.569px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.96975);"> We tested the single constraint strategies using a toy example, while the results of the</span><span style="left: 112.26px; top: 405.376px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.99353);"> joint strategy were subject to human review. While the given properties of the toy ex</span><span style="left: 112.26px; top: 421.183px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.989504);">ample, were kept in the results, replicating the toy example perfectly proved a difficult </span><span style="left: 112.26px; top: 436.99px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.947054);">task. The results of the questionnaire showed that lack of a deeper meaning and strange </span><span style="left: 112.26px; top: 452.799px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(0.954496);">capitalization were the main reasons that our results did not appear as though they were</span><span style="left: 112.26px; top: 468.606px; font-size: 12.7273px; font-family: sans-serif; transform: scaleX(1.00197);"> written by a human.</span>
Žiga Babnik
Jasmina Pegan
Domen Kos
Lovro Šubelj
2024-01-31
2024-01-31
48 1
-
Enabling Decentralized Privacy Preserving Data Processing in Sensor Networks
https://www.informatica.si/index.php/informatica/article/view/5739
The paper summarizes the findings of the Doctoral Thesis [1]. We propose a paradigm shift from traditional privacy-preserving joint computation, which relies on data obfuscation methods, to privacy preservation through anonymity. The main contribution of the thesis is a privacy-preserving protocol based on the Onion Routing concept that allows sensor network nodes to jointly compute an arbitrary function and keeps the participating nodes and their inputs private. We demonstrate the protocol's security and, through simulations, its effectiveness in large sensor networks.
Niki Hrovatin
2024-02-21
2024-02-21
48 1