Research Directions of Applications of Cognitive Infocommunications (CogInfoCom)

1. Introduction

Nowadays, an increasing number of scientific studies are published in the interdisciplinary field of Cognitive InfoCommuncation (CogInfoCom) [1,2], which shows the wide range of possibilities and importance of the topics included in the discipline. One of the outstanding research areas is related to robotics. The efficiency of complex remote robot control [3], synchronised collaboration between machines essential in manufacturing technology [4], and Human–robot Interaction (HRI) [5,6,7] can be increased using cognitive info communication. Humanoid robots can also be of good service in medicine. They can aid sick children in haematology departments lying in a small sterile room waiting for stem cell transplantation or surgery [8].

Of course, not only robots can be used to help people with various illnesses or disabilities. The study in [9] examines the cognitive mechanism of identifying different colours in case of colour-blind people, while [10] analyses the interaction between a person and a wheelchair in terms of interpersonal communication. Research [11,12] aimed to improve the movement coordination of blind children and the associated joint mobility and stability using a riding therapy process. Rehabilitation and improvement of patients cannot only be achieved in a real, physical environment but also in the development of a Virtual Environment (VE) [13] or Virtual Reality (VR) applications [14].

VR has become one of the determining topics of recent studies and is expected to become more important in the future such as in the field of digital education [15,16,17], i.e., not only in the field of medicine. The study in [18] analyses the possibilities and benefits of replacing 2D surfaces with 3D surfaces in an industrial environment. People remember visual information better if it is placed not in a traditional 2D interface but in a 3D virtual space [19,20]. The results of the research may have an impact on all areas where human memory is of special importance. In [21], the use of maps during navigation in a virtual environment was examined. VR can also provide significant assistance in the preservation and reconstruction of historical buildings and monuments [22,23]. According to the study in [24], the collaboration of the Brain–computer Interface (BCI) and VR could appear as a new strategy in the CogInfoCom field of science.

Another important research area is related to Human–computer Interaction (HCI). Studies [25,26,27] focus on human–machine communication, and examine the individual components of dialogues and their foresight. One of the objectives of HCI-based communication is to replace traditional input devices, which could even be accomplished with gloves equipped with sensors [28] or a tracking gaze route [29]. The study in [30] describes a gaze route prediction algorithm taught by observing, collecting, and classifying human eye movement parameters.

In addition to the research areas mentioned above, CogInfoCom also includes the following topics:

• Artificial cognitive capabilities
• AI, Machine and deep learning
• HCI, HMI, HRI
• Future Internet
• Cognitive sciences in the digital world
• Embodied and enactive cognitive systems
• Cognitive networks and their intelligent capabilities
• Human Interfaces: bio, cognitive, digital and wearable interfaces
• Intelligent Vehicle and Transportation Systems
• Smart city
• Digital transformation environment for education, CogInfoCom based learnability
• Digital Reality in Human development
• Mathability
• Ergonomics-based aspects of CogInfoCom
• Socio-cognitive ICT
• Ergonomics-based aspects of CogInfoCom
• Affective Computing
• Digital Reality vs. Ecological Footprint
• Augmented Farm and Food
• Internet of Digital Reality (VR, AR, XR MR, Digital Twin, Digital Shadow)
• Digitally Augmented tourism
• Hybrid Corporate Reality
• Augmented Social Reality
• Tech Augmented Legal Environment

2. Overview of Research Directions Based on the Special Issue Papers

The main content and results of the articles published in the Special Issue are summarised below.

According to Tibor Guzsvinecz et al. [31], several factors play a role in the construction of virtual systems, and they also have a certain influence on test completion times. It can be seen that the test completion time increases most often when the user uses the Gear VR display and a contrast ratio of 7:1 is found in the virtual environment. Thanks to the results, more precise time limits can be set for future virtual reality-based spatial perception tests, depending on the structure of the virtual environment. This is sufficiently important in engineering education.

José-Antonio Cervantes et al. [32] provide a biologically based computing model that can endow autonomous unmanned vehicles with cognitive abilities such as continuous perception and exploration of the environment. The results of the performed experiments show that the Visuospatial Working Memory (VSWM) computational model proposed in this paper can maintain the coherent and continuous representation of visual and spatial relationships between objects of interest presented in the environment even when the visual stimulus is lost.

Mahmoud Al-Faris et al. [33] provide a new adaptive methodology for thermal control based on an occupant’s activity, using computer vision for action recognition together with a thermal comfort fuzzy control system. During the research, deep learning and fuzzy logic techniques were used, as they provide both great performance and explainability. An adaptive context-aware fuzzy temperature control system was recommended to adjust heat settings according to the occupants’ actions. The aim of this research is to improve the traditional thermal model by presenting an adaptive method.

According to Štefan Korečko et al. [34] augmented reality makes it possible for activities such as presentations, training or therapy to take place in virtual reality. In order to make online augmented reality available to as many people as possible, solutions have been created that can run directly in the web browser. One of the most recognised solutions is the A-Frame framework developed by the Mozilla VR team, which supports most of the hardware used in augmented reality. Additionally, an extension Networked-Aframe allows multiple users to share virtual environments created with A-Frame in real time. This paper presents and evaluates three components that extend the functionality of A-Frame and Networked-Aframe. The first extends Networked-Aframe with the ability to monitor and control users in a shared virtual scene. The second implements six-degree-of-freedom motion tracking for smartphone-based virtual reality headsets. The third provides gesture support for the Microsoft HoloLens holographic computer.

Samuel D. Okegbile et al. [35] examine user performance in a hybrid spectrum access model in a large cognitive radio network (CRN), where multiple primary users (PUs) and secondary users (SUs) broadcast simultaneously on the same channel. SUs first detect the channel state by channel sensing, and based on the channel sensing result, select the appropriate channel access scheme (or underlay or overlay) for their transmissions. When at least one PU is active, the SUs transmit according to the down-channel access scheme using the power control technique to ensure that the interference generated in the primary network is below the predetermined interference threshold. In the absence of a PU, the SUs transmit at full transmission power according to the overlay channel access scheme, thereby maximizing their transmission rate. Follow-up analyses using the tool of stochastic geometry were determined on important metrics such as the probability of success, throughput and average age of information (AoI) in both primary and secondary networks, while the interference between the two networks was recorded. The defined results provide an efficient way to understand the metrics of AoI, throughput, and success probability in hybrid spectrum access-based CRN.

Félix Francisco Ramos Corchado et al. [36] present a cognitive approach to pervasive service composition, where the implementation of InfoCom tools and cognitive functions interact to create comprehensive composite services. The central hypothesis is that cognitive theory can help solve real problems requiring a comprehensive service composition. To test the approach, in this paper the case of urban uncertainty is presented. In various countries, street robbery with firearms is one of the problems that has a great impact due to its frequency. This article proposes a comprehensive service to deter criminals from committing their crimes. The results obtained by simulating our proposal in our case study are promising.

Beatrix Séllei et al. [37] used logistic regression models to examine the incremental predictive power of positive psychological factors relative to pre-enrolment measures of academic achievement. The study is based on the data of 302 business and economics undergraduate students of the Budapest University of Technology and Economics. Coping was found to be the most important factor highlighting the importance of stress management for students. We also found that the well-chosen psychological factors that measure coping, personality traits, the psychological immune system, emotional intelligence and PERMA (P-positive emotion, E-commitment, R-relationships, M-meaning, A-performances) factors, as well as university admission score and academic performance are significantly better predicted than when relying solely on pre-enrolment performance measures.

Wei-Liang Ou et al. [38] developed an application of visible-light wearable eye trackers, a pupil tracking methodology based on deep-learning technology. Using deep learning object detection technology based on the You Only Look (YOLO) model, the proposed pupil tracking method can effectively estimate and predict the center of the pupil in visible light mode. Using the developed YOLOv3-tiny-based model to test the pupil tracking performance, the detection accuracy reaches 80% and the recall rate is close to 83%.

Hippokratis Apostolidis et al. [39] examine the deployment of a cost-effective biofeedback system that provides anxiety awareness during online examination activities. Human anxiety is classified based on the evaluation of biosignals related to skin conductance, skin temperature, and heart rate. The first goal of the study is to verify the performance of the presented system. Thus, the convergent validity of the system was tested in terms of self-report measures of anxiety. The second aim of this study is to identify the participants’ personality dimensions based on the Technology Readiness Index (TRI) that influence their academic performance and real-time anxiety as provided by a biofeedback tool during study trials.

Marianna Koctúrová et al. [40] focused on the study of problematic speech activity detection using EEG data. The novel approach used in the research involved the use of visual stimuli, such as reading and colour naming, as well as speech activity signals detectable with EEG technology. The proposed solution is based on a shallow feedforward artificial neural network with only 100 hidden neurons. Standard features such as signal energy, standard deviation, RMS, skewness, and curvature were calculated from the original signal of the 16 EEG electrodes. In the field of brain and computer interface applications, the new approach was used to calculate additional features from the minimum phase signal. The experimental results demonstrated a speech detection accuracy of 86.80% and 83.69%, respectively, for the F1 value based on the analysis of EEG signals from one subject and several subjects.

Piotr Sulikowski et al. [41] examined human–computer interactions for vertical, horizonal, and mixed layouts of recommending interfaces of four major e-commerce stores, and was based on our document object model events-based behavior analysis tool. The results of this implicit feedback study are presented and analysed, showing that vertical recommendation zones attracted more attention than horizontal ones.

Agisilaos Chaldogeridis et al. [42] designed and implemented a video game aimed at working memory (WM) training using a Serious Game (SG). Its effectiveness was tested and evaluated through an evaluation process. The results showed that participants’ WM performance improved, especially for those who achieved the pretest at test, while those with high pretests only maintained their initial status.

Akira Sasaki et al. [43] adapted a sightseeing app for use with a wearable device (smartwatch) to avoid using a smartphone while walking and introduced a prospect theory to evaluate information based on personal interest and behavior. The research proved that the app provided travellers with the most appropriate sightseeing information and prevented walking hazards.

Alejandro Benito-Santos et al. [44] used a new visual text analysis tool based on previous studies in order to automatically recognise interesting knowledge associations and groups of common interests among these communities of practice. The results show that it is possible to propose interactive, semi-supervised visual approaches aimed at defragmenting a research set using text-based automatic literature analysis methods.

Daniel Bella et al. [45] presented the geovisualisation of spatial databases of a Hungarian settlement on the web, using the open source webGIS system and Google application programming interfaces (APIs). The geovisualisation techniques developed are able to provide information about the different spatial data for users in a visual way, and also help to understand better the spatial information using a cognitive approach. The advantage of interactive web maps created with the technologies applied over traditional static maps is a new approach, which allows the user to manipulate the temporal and spatial data directly in the most appropriate way.

Jozsef Katona [46] presented an overview of human–computer interaction (HCI) and virtual reality (VR) research fields in CogInfoCom during an eight-year period from 2012 to 2020 based on the International Conference on Cognitive Infocommunications and its Special Issues. These works were classified in terms of application areas into the following two categories: human–computer interaction and virtual reality.

3. Conclusions

This short review of the papers shows that the research directions of applications of CogInfoCom offer a very wide range of research opportunities, in which multidisciplinarity will remain important in the future.