2024 Special Issue
MESSAGE FROM THE GUEST EDITOR
Péter Baranyi, Atsushi Ito, Ádám B. Csapó, Ildikó Horváth, and Tibor Guzsvinecz
Joint Special Issue on Cognitive Infocommunications and Cognitive Aspects of Virtual Reality 
We are pleased to introduce this joint special issue focus ing on Cognitive Infocommunications (CogInfoCom) and Cognitive Aspects of Virtual Reality (cVR). Within this Issue a wide range of research results are presented, focusing on the complex relationship between human cognition and in formation and communication technologies (ICT), along with the revolutionary effects of virtual reality settings on cognitive functions.
PAPERS FROM OPEN CALL
Zoltan Gal, Erzsébet Tóth
Deep Learning-Based Analysis of Ancient Greek Literary Texts in English Version: A Statistical Model Based on Word Frequency and Noise Probability for the Classification of Texts
In our paper we intend to present a methodology that we elaborated for clustering texts based on the word fre quency in the English translations of selected old Greek texts. We used the classification system of the ancient Library of Alex andria, devised by the prominent Greek scholar-poet, Callima chus in the 3rd century BC., as a basis for categorizing literary masterpieces. In our content analysis, we could determine a tri plet of a, b, c values for describing a power function that appro priately fits a curve determined by the word frequencies in the texts. In addition, we have discovered 16 special features of the different texts that correspond to various token categories inves tigated in each text, such as part of speech of the word in the con text, numerals, subordinate conjunction, symbols, etc. We have developed a cognitive model in which several hundred different subtexts were utilized for supervised learning with the aim of subtext class recognition. Concerning 200 subtexts, the triplet of a, b, c values, the classes of the subtexts, and their 16-dimen sional feature vectors were learnt for the Recurrent Neural Net work (RNN). It turned out that the Long-Short Term Memory RNN could efficiently predict which class a chosen subtext could be categorized into without considering the interpretation of the content. The influence of the non-zero error rate of new com munication services on the meaning of the transferred texts was also investigated. The impact of the noise on the classification accuracy was found to be linear, dependent on the character er ror rate.
Reference
DOI: 10.36244/ICJ.2024.5.1
Download
Zakaria Khoudi, Mourad Nachaoui, and Soufiane Lyaqini
Finding the contextual impacts on Students’ Mathematical performance using a Machine Learning-based Approach
An extensive dataset for examining Moroccan eighth-grade pupils’ mathematical prowess was made available by the 2019 Trends in Mathematics and Science Study (TIMSS). The TIMSS 2019 public dataset contained 8390 Moroccan stu- dents, who were the subject of this research. Based on how well they could solve mathematical problems, the participants were split into 3108 high achievers and 5282 poor achievers in the mathematics phase of the exam. This study aimed to pinpoint the essential environmental elements affecting eighth-grade pupils’ mathematical abilities. In order to do this, the research used cutting-edge machine learning methods, particularly the efficient distributed gradient boosting toolkit XGBoost. From a vast collection of 700 possible components, this strategy proved critical in identifying the most relevant variables. These factors included a broad spectrum of components at the student, teach er, and school levels. After a thorough investigation, 12 critical contextual factors distinguishing between arithmetic prodigies and average performers were successfully found. The discov ery of these critical characteristics has significant implications for future instructional efforts, especially in improving high school pupils’ mathematical proficiency. Knowledge of these factors may assist educators and policymakers in creating fo cused interventions and pedagogical approaches that enhance mathematics performance and comprehension. This research emphasizes how complex mathematics accomplishment is and how crucial it is to approach educational planning holistically. Identifying and addressing these critical environmental ele ments can significantly enhance students’ mathematics achieve ments at a crucial juncture in their academic development.
Reference
DOI: 10.36244/ICJ.2024.5.2
Download
Cecilia Sik-Lanyi, Bence Halmosi, Jinat Ara, Judit Szűcs and Tibor Guzsvinecz
Assessing Memory Colors of University Students
Human perception is complex, and can be influ enced by several factors. The study’s purpose is to understand these factors, thus, an application was developed. This appli cation examines memory colors in the CIELAB color space. Memory colors can be affected by nationality, virtual reality game playtime, and the presence or absence of an image cue. The memory colors of banana and orange had the highest agreement between the students, while the memory colors of river and grass had the largest dispersion. Virtual reality games influenced the memory color of grass the most. It can also be concluded that without an image cue, different colors were se lected in 70.90% of the cases.
Reference
DOI: 10.36244/ICJ.2024.5.3
Download
Tibor Guzsvinecz, Judit Szűcs, Veronika Szucs, Robert Demeter, Jozsef Katona and Attila Kovari
The Accuracy of the k-Nearest Neighbors and k-Means Algorithms in Gesture Identification
In today’s digital era, human-computer interac tion interfaces evolve and increase together with the needs of the users. However, the existing technologies have their limita tions, which can hinder the efficiency of modern input devices like the Kinect sensor or other similar sensors. In this paper we improved our previous algorithm by extending it with two algo rithms that aim to help telerehabilitation for individuals with movement disabilities. These two algorithms are based on the k Nearest Neighbors, the k-Means algorithms. The algorithms are designed to accommodate the needs of the patients by adapting to their gestures based on their previous three. Using these ges tures, the algorithms create multiple gesture acceptance domains around each coordinate of the gesture. Consequently, they decide whether the next user-input gesture can be considered the same movement. The accuracy of these algorithms was evaluated in three acceptance domains by comparing gesture descriptors with either the Euclidean or the Manhattan distance calculation meth ods. The results show that k-Nearest Neighbors algorithm yields better results in larger acceptance domains, while the k-Means algorithm can provide a better gesture acceptance rate in the smaller ones. The results show that both algorithms can be used in the telerehabilitation process, although the k-Means algorithm is more accurate than the k-Nearest Neighbors algorithm.
Reference
DOI: 10.36244/ICJ.2024.5.4
Download
Péter Baranyi, Borbála Berki, and Ádám B. Csapó
Concepts of Cognitive Infocommunications
Cognitive Infocommunications (CogInfoCom) is an interdisciplinary field that explores the interplay between the cognitive sciences and infocommunication technologies (ICT). This paper presents recent transformative changes in Cognitive Infocommunications, emerging both on the technological and the human side. Concepts such as Digital Reality and Cogni tive Entities are also presented, which have emerged as a result recent technological convergence and further entanglement of ICT with human cognition. In addition, the current focal points of CogInfoCom research are presented to emphasize the entan gled nature of human-technology interactions and human-tech nology co-evolution.
Reference
DOI: 10.36244/ICJ.2024.5.5
Download
Jinat Ara, and Cecilia Sik-Lanyi
Computation of Accessibility Score of Educational Institute Webpages using Machine Learning Approaches
The availability of digital platforms by ensur ing accessibility and usability is considered a virtual gateway to provide a wide array of information to its stakeholders. An accessible web platform can disseminate information among a variety of target audiences. Thereby accessibility of academic web pages requires special attention. Herein we proposed an accessibility computation approach for higher education in stitute webpage (Homepage) in the context of universities in Hungary. The proposed approach incorporated two machine learning (ML) classifiers: Random Forest (RF), and Decision Tree (DT) to experiment on our custom dataset to compute the overall accessibility score. Performance of ML methods vali dated through confusion matrix and classification report result. The empirical results of ML methods and statistical evaluation showed poor accessibility scores which depicts that none of the selected web pages are free from accessibility issues associ ated with disabilities. As such, accessibility is a crucial aspect that needs further concern as most of the considered academic webpages have experienced accessibility issues and showed im provement demands. Abstract—The availability of digital platforms by ensuring accessibility and usability is considered a virtual gateway to provide a wide array of information to its stakeholders. An accessible web platform can disseminate information among a variety of target audiences. Thereby accessibility of academic web pages requires special attention. Herein we proposed an accessibility computation approach for higher education institute webpage (Homepage) in the context of universities in Hungary. The proposed approach incorporated two machine learning (ML) classifiers: Random Forest (RF), and Decision Tree (DT) to experiment on our custom dataset to compute the overall accessibility score. Performance of ML methods validated through confusion matrix and classification report result. The empirical results of ML methods and statistical evaluation showed poor accessibility scores which depicts that none of the selected web pages are free from accessibility issues associated with disabilities. As such, accessibility is a crucial aspect that needs further concern as most of the considered academic webpages have experienced accessibility issues and showed im provement demands.
Reference
DOI: 10.36244/ICJ.2024.5.6
Download
Erzsébet Tóth, and Zoltan Gal
Optimizing Text Clustering Efficiency through Flexible Latent Dirichlet Allocation Method: Exploring the Impact of Data Features and Threshold Modification
A parallel corpus comprising Croatian EU legislative documents automatically translated into English spans 28 years and is enriched with metadata, including creation year and hierarchical classifier tags denoting descriptors, document types, and fields. However, nearly two-thirds of the approximately 1.5 thousand texts lack complete metadata, necessitating labor intensive manual efforts that pose challenges for human administration. This incompleteness issue can be observed in the case of official legal sites functioning as regular service provisioning databases. In response, this paper introduces an artificial cognitive and multilabel classification approach to expedite the tagging process with only a fraction of the manual effort. Leveraging the Latent Dirichlet Allocation (LDA) algorithm, our method assigns field values or tags to incompletely labeled documents. We implement a Flexible LDA variant, incorporating the influence of topics close to the most probable topic, regulated by a relative probability threshold (RPT). We evaluate the LDA prediction's dependence on document prefiltering and RPT values. Furthermore, we investigate the dependence of quantitative linguistic properties on the type and speciality of pre-processing tasks. Our algorithm, built on error-correcting optimizing codes, succesfully predicts a mixture of topic probabilities for these legal texts. This prediction is achieved by calculating the Hamming distance of binary feature vectors created using the legal fields of the EUROVOC multilingual thesaurus.
Reference
DOI: 10.36244/ICJ.2024.5.7
Download
István Károly Boda, and Erzsébet Tóth
Knowledge Base Development for Second Language Learning in the 3D Virtual Space
In our study first we provide a short overview of the 3D virtual library project which started about ten years ago as part of the Cognitive Infocommunications (CogInfoCom) research. The current implementation of the virtual library model exploits the 3D features of the MaxWhere Seminar System. In our study we would like to summarize the classroom experiences that we brought together in teaching English as a second language for students of computer science majors at the Faculty of Informatics, University of Debrecen in the academic year of 2020 and 2021. Our main purpose was to improve the students’ linguistic knowledge and to collect their opinions and suggestions about the content of the learning material of our virtual library and where they think is necessary to modify it. Summarizing their views, we decided to add further vocabulary items, contexts and explanations to the material. In addition, their achievements proved that successful language learning needs carefully prepared tests and exercises which support self-assessment and increase motivation. In general, the more tests are available the more efficient the learning process is. But preparing good and varied tests manually is a relatively slow and exhausting work. Therefore, we intended to use JavaScript technology to develop an algorithm which can generate tests and exercises automatically, based on the knowledge base of the virtual library.
Reference
DOI: 10.36244/ICJ.2024.5.8
Download
Attila Kovari
Model of the Internet of Digital Education and its links to VR
Modern technologies are now essential to make the educational process more mobile, informative and versatile. The digitization of the educational institution, taking advantage of the opportunities provided by the Internet, provides an opportunity to exchange the accumulated experience and knowledge, and provides access to information for everyone. The mandatory introduction of online education due to COVID-19 has accelerated the development of digital education. The main direction in the development of education is moving towards modern online courses, which are already being used successfully. A comprehensive concept is needed to ensure that all IT used for learning, education and training is seamless, free of barriers and closed ecosystems. In connection with the above f indings this article first introduces the model and of Internet of Digital Education (IoDE), describes the principles of IoDE, and then summarize the cognitive aspects and VR relations. The purpose of this article is to help readers recognize the IoDE as a whole and predict future trends in IoDE development.
Reference
DOI: 10.36244/ICJ.2024.5.9
Download
Tibor Guzsvinecz, and Judit Szűcs
Textual Analysis of Virtual Reality Game Reviews
Virtual reality systems are complex and made of various parts. Since a person is an integral component of such systems, virtual reality technologies also have a cognitive aspect. As such, these technologies engage with the perceptual, attentional, and decision-making processes of users. Consequently, they can be considered cognitive tools. Thus, it is imperative to understand what people think of such environments. To take a step towards this understanding, textual reviews of virtual reality games made for entertainment were investigated using text mining methods. Thus, 1,635,919 textual reviews were scraped from the Steam digital video game distribution platform in the spring of 2023. The reviews were grouped by whether they were positive or negative. According to the results, the following conclusions can be made regarding virtual reality games: 1) Negative reviews are significantly longer than positive ones. 2) Negative reviews are written significantly earlier than positive ones, although no correlation was found between the review type and the playtime before writing the review. 3) The most frequent words and word correlations are different between review types since negative reviews are more focused on game mechanics and bugs. Due to the results, insights can be provided to virtual reality game developers to help them refine their games. Index Terms—computer games; game review; player experi ence; Steam; textual analysis Abstract—Virtual reality systems are complex and made of various parts. Since a person is an integral component of such systems, virtual reality technologies also have a cognitive aspect. As such, these technologies engage with the perceptual, attentional, and decision-making processes of users. Consequently, they can be considered cognitive tools. Thus, it is imperative to understand what people think of such environments. To take a step towards this understanding, textual reviews of virtual reality games made for entertainment were investigated using text mining methods. Thus, 1,635,919 textual reviews were scraped from the Steam digital video game distribution platform in the spring of 2023. The reviews were grouped by whether they were positive or negative. According to the results, the following conclusions can be made regarding virtual reality games: 1) Negative reviews are significantly longer than positive ones. 2) Negative reviews are written significantly earlier than positive ones, although no correlation was found between the review type and the playtime before writing the review. 3) The most frequent words and word correlations are different between review types since negative reviews are more focused on game mechanics and bugs. Due to the results, insights can be provided to virtual reality game developers to help them refine their games.
Reference
DOI: 10.36244/ICJ.2024.5.10
Download
György Persa, and Ádám B. Csapó
Design and Evaluation of Abstract Aggregated Avatars in VR Workspaces
Avatars are commonly used in digital platforms to provide a visual representation of individual users to each other. Generally, avatar design in the past has focused on achieving visual fidelity and realism of social interactions. In this paper, we broaden the concept of avatars to incorporate displays using an abstract visual language and conveying information on aggregated, interpersonal information from the perspective of the digital platform as a whole. We propose a general design methodology for such aggregated avatars, and also introduce and experimentally evaluate an aggregated avatar which we have developed on the MaxWhere VR platform. Results are promising in that users were able to discern several key states of the avatar and correctly associate them with the correct virtual reality scenarios in a statistically meaningful way.
Reference
DOI: 10.36244/ICJ.2024.5.11
Download
Jinshan Luo, Yuki Okaniwa, Natsuno Yamazaki, Yuko Hiramatsu, Madoka Hasegawa, and Atsushi Ito
Cognitive Aspect of Emotion Estimation of a Driver
Despite rapid advancements in the automotive industry, traffic safety risks persist. Addressing this challenge requires innovative driver assistance technologies. Common accidents result from driver inattention, fatigue, and stress, leading to issues like falling asleep at the wheel and improper acceleration and braking. Our study aims to contribute to advanced driver assistance systems that adapt to drivers' emotional needs, ultimately enhancing road safety. In this paper, we mention the result of our research to estimate drivers' emotions using sensors. For that purpose, we developed a sensor network containing sensors such as EEG, eye tracker, and driving simulator. We explored the relationship. As a result, we confirmed the relation between the driver's emotions, especially sleep conditions, driving speed, duration, and brain wave behavior.
Reference
DOI: 10.36244/ICJ.2024.5.12
Download
Péter Földesi, and Eszter Sós
Developing sustainable logistic strategies in the context of cognitive biases
Cognitive biases often occur even in the decision- making process of highly qualified company managers due to the drive for efficiency and time pressure in operations. At the same time, there are also long-term strategic decisions where time pressure is no longer a factor, and yet cognitive bias appears, which has to be considered properly. In strategic issues, decision- makers tend to see their wishes and desires rather than the objective reality. The proposed system of fuzzy indicators based on technical and objective data supports decision-making between logistics strategies by mitigating cognitive biases, which is extremely important in the logistics field, where the decisions have to be made partly based on subjective, vague, or uncertain parameters.
Reference
DOI: 10.36244/ICJ.2024.5.13
Download
Anna Sudár, and Ildikó Horváth
Design Suggestions for Digital Workflow Oriented Desktop VR Spaces
This paper presents an examination of design prin- ciples for 3D Virtual Reality (VR) environments, with a focus on enhancing digital workflows. Employing objective data, the study sets out to clarify the primary design considerations for crafting effective 3D VR spaces. Through empirical research, the authors conducted comparative analyses of task performance within both classical 2D Windows and in 3D VR environmental contexts, exploring users’ perceived difficulty levels alongside eye-tracking data. The findings reveal that, although 3D VR environments rich in distracting elements and demanding high navigational effort increase perceived task difficulty, these factors do not negatively impact overall performance or task completion time. Interestingly, eye-fixation duration results indicate that visual fixation in 3D VR falls within expected norms, whereas in 2D scenarios, fixation rates are significantly higher, more than doubling those observed in 3D settings. Drawing on these insights, the paper supports the design of 3D VR spaces that are simpler and intuitive, necessitating minimal navigation, thereby optimizing task performance efficiency.
Reference
DOI: 10.36244/ICJ.2024.5.14
Download