Information, Volume 12, Issue 12 (December 2021) – 45 articles

In this paper, we tackle the problem of deploying face recognition (FR) solutions in heterogeneous Internet of Things (IoT) platforms. The main challenges are the optimal deployment of deep neural networks (DNNs) in the high variety of IoT devices (e.g., robots, tablets, smartphones, etc.), the secure management of biometric data while respecting the users’ privacy, and the design of appropriate user interaction with facial verification mechanisms for all kinds of users. We analyze different approaches to solving all these challenges and propose a knowledge-driven methodology for the automated deployment of DNN-based FR solutions in IoT devices, with the secure management of biometric data, and real-time feedback for improved interaction. We provide some practical examples and experimental results with state-of-the-art DNNs for FR in Intel’s and NVIDIA’s hardware platforms as IoT devices. Full article

The DEVS formalism has been recognized to support generic open architectures that allow incorporating multiple engineering domains within integrated simulation models. What is missing for accelerated adoption of DEVS-based methodology for intelligent cyberphysical system design is a set of building blocks and architectural patterns that can be replicated and reused in system development. As a start in this direction, this paper offers a notional architecture for intelligent hybrid cyberphysical system design and proceeds to focus on the decision layer to consider DEVS models for basic behaviors such as choice of alternatives, perception of temporal event relations, and recognition and generation of finite state languages cast into DEVS time segments. We proceed to describe a methodology to define DEVS-based building blocks and architectural patterns for design of systems employing fast, frugal, and accurate heuristics. We identify some elements of this kind and establish their status as minimal realizations of their defined behaviors. As minimal realizations such designs must ipso facto underlie any implementation of the same cognitive behaviors. We discuss architectures drawn from the cognitive science literature to show that the fundamental elements drawn from the fast, frugal, and accurate paradigm provide insights into intelligent hybrid cyberphysical system design. We close with open questions and research needed to confirm the proposed concepts. Full article

The particle swarm optimization (PSO) algorithm has been widely used in various optimization problems. Although PSO has been successful in many fields, solving optimization problems in big data applications often requires processing of massive amounts of data, which cannot be handled by traditional PSO on a single machine. There have been several parallel PSO based on Spark, however they are almost proposed for solving numerical optimization problems, and few for big data optimization problems. In this paper, we propose a new Spark-based parallel PSO algorithm to predict the co-authorship of academic papers, which we formulate as an optimization problem from massive academic data. Experimental results show that the proposed parallel PSO can achieve good prediction accuracy. Full article

In this paper, an integrated system to control and manage a state-of-the-art industrial computer numerical control (CNC) machine (Studer S33) using a commercially available tablet (Samsung Galaxy Tablet S2) is presented as a proof of concept (PoC) for the ubiquitous control of industrial machines. As a PoC, the proposed system provides useful insights to support the further development of full-fledged systems for Industrial Internet of Things (IIoT) applications. The proposed system allows for the quasi-decentralisation of the control architecture of conventional programmable logic controller (PLC)-based industrial control systems (ICSs) through data and information exchange over the transmission control protocol and the internet protocol (TCP/IP) suite using multiple agents. Based on the TCP/IP suite, a network device (Samsung Galaxy Tablet S2) and a process field net (PROFINET) device (Siemens Simatic S7-1200) are interfaced using a single-board computer (Raspberry Pi 4). An override system mainly comprising emergency stop and acknowledge buttons is also configured using the single-board computer. The input signals from the override system are transmitted to the PROFINET device (i.e., the industrial control unit (ICU)) over TCP/IP. A fully functional working prototype is realised as a PoC for an integrated system designated for the wireless and ubiquitous control of the CNC machine. The working prototype as an entity mainly comprises a mobile (handheld) touch-sensitive human-machine interface (HMI), a shielded single-board computer, and an override system, all fitted into a compact case with physical dimensions of 300 mm by 180 mm by 175 mm. To avert potential cyber attacks or threats to a reasonable extent and to guarantee the security of the PoC, a multi-factor authentication (MFA) including an administrative password and an IP address is implemented to control the access to the web-based ubiquitous HMI proffered by the PoC. Full article

The application of machine learning techniques to the epidemiology of COVID-19 is a necessary measure that can be exploited to curtail the further spread of this endemic. Conventional techniques used to determine the epidemiology of COVID-19 are slow and costly, and data are scarce. We investigate the effects of noise filters on the performance of machine learning algorithms on the COVID-19 epidemiology dataset. Noise filter algorithms are used to remove noise from the datasets utilized in this study. We applied nine machine learning techniques to classify the epidemiology of COVID-19, which are bagging, boosting, support vector machine, bidirectional long short-term memory, decision tree, naïve Bayes, k-nearest neighbor, random forest, and multinomial logistic regression. Data from patients who contracted coronavirus disease were collected from the Kaggle database between 23 January 2020 and 24 June 2020. Noisy and filtered data were used in our experiments. As a result of denoising, machine learning models have produced high results for the prediction of COVID-19 cases in South Korea. For isolated cases after performing noise filtering operations, machine learning techniques achieved an accuracy between 98–100%. The results indicate that filtering noise from the dataset can improve the accuracy of COVID-19 case prediction algorithms. Full article

The removal of direct human involvement from the decision to apply lethal force is at the core of the controversy surrounding autonomous weapon systems, as well as broader applications of artificial intelligence and related technologies to warfare. Far from purely a technical question of whether it is possible to remove soldiers from the ‘pointy end’ of combat, the emergence of autonomous weapon systems raises a range of serious ethical, legal, and practical challenges that remain largely unresolved by the international community. The international community has seized on the concept of ‘meaningful human control’. Meeting this standard will require doctrinal and operational, as well as technical, responses at the design stage. This paper focuses on the latter, considering how value sensitive design could assist in ensuring that autonomous systems remain under the meaningful control of humans. However, this article will also challenge the tendency to assume a universalist perspective when discussing value sensitive design. By drawing on previously unpublished quantitative data, this paper will critically examine how perspectives of key ethical considerations, including conceptions of meaningful human control, differ among policymakers and scholars in the Asia Pacific. Based on this analysis, this paper calls for the development of a more culturally inclusive form of value sensitive design and puts forward the basis of an empirically-based normative framework for guiding designers of autonomous systems. Full article

This study explores the interactive characteristics of the public, referencing existing data mining methods. This research attempts to develop a community data mining and integration technology to investigate the trends of global retail chain brands. Using social media mining and ensemble learning, it examines key image cues to highlight the various reasons motivating participation by fans. Further, it expands the discussion on image and marketing cues to explore how various social brands induce public participation and the evaluation of information efficiency. This study integrates random decision forests, extreme gradient boost, and adaboost for statistical verification. From 1 January 2011 to 31 December 2019, the studied brands published a total of 25,538 posts. The study combines community information and participation in its research framework. The samples are divided into three categories: retail food brand, retail home improvement brand, and retail warehouse club brand. This research draws on brand image and information cue theory to design the theoretical framework, and then uses behavior response factors for the theoretical integration. This study contributes a model that classifies brand community posts and mines related data to analyze public needs and preferences. More specifically, it proposes a framework with supervised and ensemble learning to classify information users′ behavioral characteristics. Full article

The Natural Language Processing (NLP) community has witnessed huge improvements in the last years. However, most achievements are evaluated on benchmarked curated corpora, with little attention devoted to user-generated content and less-resourced languages. Despite the fact that recent approaches target the development of multi-lingual tools and models, they still underperform in languages such as Portuguese, for which linguistic resources do not abound. This paper exposes a set of challenges encountered when dealing with a real-world complex NLP problem, based on user-generated complaint data in Portuguese. This case study meets the needs of a country-wide governmental institution responsible for food safety and economic surveillance, and its responsibilities in handling a high number of citizen complaints. Beyond looking at the problem from an exclusively academic point of view, we adopt application-level concerns when analyzing the progress obtained through different techniques, including the need to obtain explainable decision support. We discuss modeling choices and provide useful insights for researchers working on similar problems or data. Full article

In the last years, methods for detecting text in real scenes have made significant progress with an increase in neural networks. However, due to the limitation of the receptive field of the central nervous system and the simple representation of text by using rectangular bounding boxes, the previous methods may be insufficient for working with more challenging instances of text. To solve this problem, this paper proposes a scene text detection network based on cross-scale feature fusion (CSFF-Net). The framework is based on the lightweight backbone network Resnet, and the feature learning is enhanced by embedding the depth weighted convolution module (DWCM) while retaining the original feature information extracted by CNN. At the same time, the 3D-Attention module is also introduced to merge the context information of adjacent areas, so as to refine the features in each spatial size. In addition, because the Feature Pyramid Network (FPN) cannot completely solve the interdependence problem by simple element-wise addition to process cross-layer information flow, this paper introduces a Cross-Level Feature Fusion Module (CLFFM) based on FPN, which is called Cross-Level Feature Pyramid Network (Cross-Level FPN). The proposed CLFFM can better handle cross-layer information flow and output detailed feature information, thus improving the accuracy of text region detection. Compared to the original network framework, the framework provides a more advanced performance in detecting text images of complex scenes, and extensive experiments on three challenging datasets validate the realizability of our approach. Full article

Part of Speech (POS) tagging is one of the most common techniques used in natural language processing (NLP) applications and corpus linguistics. Various POS tagging tools have been developed for Arabic. These taggers differ in several aspects, such as in their modeling techniques, tag sets and training and testing data. In this paper we conduct a comparative study of five Arabic POS taggers, namely: Stanford Arabic, CAMeL Tools, Farasa, MADAMIRA and Arabic Linguistic Pipeline (ALP) which examine their performance using text samples from Saudi novels. The testing data has been extracted from different novels that represent different types of narrations. The main result we have obtained indicates that the ALP tagger performs better than others in this particular case, and that Adjective is the most frequent mistagged POS type as compared to Noun and Verb. Full article

Facebook users are exposed to diverse news and political content; this means that Facebook is a significant tool for the enhancement of civic participation and engagement in politics. However, it has been argued that Facebook, through its algorithmic curation reinforces the pre-existing attitudes of individuals, rather than challenging or potentially altering them. The objective of this study is to elucidate the emotional and behavioural impact of the personalization of Facebook users’ News Feeds results, and thereby to uncover a possible link between their online and offline civic attitudes. Firstly, we investigate the extent to which users’ Facebook News Feeds results are personalized and customized to fit users’ pre-existing civic attitudes and political interests. Secondly, we explore whether users embody new roles as a result of their emotional and behavioural interaction with political content on Facebook. Our methodology is based on a quantitative survey involving 108 participants. Our findings indicate that, while Facebook can potentially expose users to varying political views and beliefs, it tends to reinforce existing civic attitudes and validate what users already hold to be true. Furthermore, we find that users themselves often assume a proactive stance towards Facebook News Feed results, acquiring roles in which they filter and even censor the content to which they are exposed and thus trying to obfuscate algorithmic curation. Full article

The attraction of games comes from the player being able to have fun in games. Gambling games that are based on the Variable-Ratio schedule in Skinner’s experiment are the most typical addictive games. It is necessary to clarify the reason why typical gambling games are simple but addictive. Also, the Multiarmed Bandit game is a typical test for Skinner Box design and is most popular in the gambling house, which is a good example to analyze. This article mainly focuses on expanding on the idea of the motion in mind model in the scene of Multiarmed Bandit games, quantifying the player’s psychological inclination by simulation experimental data. By relating with the quantification of player satisfaction and play comfort, the expectation’s feeling is discussed from the energy perspective. Two different energies are proposed: player-side ($E_r$) and game-side energy ($E_i$). This provides the difference of player-side ($E_r$) and game-side energy ($E_i$), denoted as $E_d$ to show the player’s psychological gap. Ten settings of mass bandit were simulated. It was found that the setting of the best player confidence ($E_r$) and entry difficulty ($E_i$) can balance player expectation. The simulation results show that when $m=0.3,0.7$, the player has the biggest psychological gap, which expresses that player will be motivated by not being reconciled. Moreover, addiction is likely to occur when $m\in [0.5,0.7]$. Such an approach can also help the developers and educators increase edutainment games’ efficiency and make the game more attractive. Full article

The creation of linguistic resources is crucial to the continued growth of research and development efforts in the field of natural language processing, especially for resource-scarce languages. In this paper, we describe the curation and annotation of corpora and the development of multiple linguistic technologies for four official South African languages, namely isiNdebele, Siswati, isiXhosa, and isiZulu. Development efforts included sourcing parallel data for these languages and annotating each on token, orthographic, morphological, and morphosyntactic levels. These sets were in turn used to create and evaluate three core technologies, viz. a lemmatizer, part-of-speech tagger, morphological analyzer for each of the languages. We report on the quality of these technologies which improve on previously developed rule-based technologies as part of a similar initiative in 2013. These resources are made publicly accessible through a local resource agency with the intention of fostering further development of both resources and technologies that may benefit the NLP industry in South Africa. Full article

Augmented Reality (AR) annotations are a powerful way of communication when collaborators cannot be present at the same time in a given environment. However, this situation presents several challenges, for example: how to record the AR annotations for later consumption, how to align virtual and real world in unprepared environments or how to offer the annotations to users with different AR devices. In this paper we present a cross-device AR annotation method that allows users to create and display annotations asynchronously in environments without the need for prior preparation (AR markers, point cloud capture, etc.). This is achieved through an easy user-assisted calibration process and a data model that allows any type of annotation to be stored on any device. The experimental study carried out with 40 participants has verified our two hypotheses: we are able to visualize AR annotations in indoor environments without prior preparation regardless of the device used and the overall usability of the system is satisfactory. Full article

Every step we take in the digital world leaves behind a record of our behavior; a digital footprint. Research has suggested that algorithms can translate these digital footprints into accurate estimates of psychological characteristics, including personality traits, mental health or intelligence. The mechanisms by which AI generates these insights, however, often remain opaque. In this paper, we show how Explainable AI (XAI) can help domain experts and data subjects validate, question, and improve models that classify psychological traits from digital footprints. We elaborate on two popular XAI methods (rule extraction and counterfactual explanations) in the context of Big Five personality predictions (traits and facets) from financial transactions data (N = $6408$). First, we demonstrate how global rule extraction sheds light on the spending patterns identified by the model as most predictive for personality, and discuss how these rules can be used to explain, validate, and improve the model. Second, we implement local rule extraction to show that individuals are assigned to personality classes because of their unique financial behavior, and there exists a positive link between the model’s prediction confidence and the number of features that contributed to the prediction. Our experiments highlight the importance of both global and local XAI methods. By better understanding how predictive models work in general as well as how they derive an outcome for a particular person, XAI promotes accountability in a world in which AI impacts the lives of billions of people around the world. Full article

The Internet of Things (IoT) has seen a surge in mobile devices with the market and technical expansion. IoT networks provide end-to-end connectivity while keeping minimal latency. To reduce delays, efficient data delivery schemes are required for dispersed fog-IoT network orchestrations. We use a Spark-based big data processing scheme (BDPS) to accelerate the distributed database (RDD) delay efficient technique in the fogs for a decentralized heterogeneous network architecture to reinforce suitable data allocations via IoTs. We propose BDPS based on Spark-RDD in fog-IoT overlay architecture to address the performance issues across the network orchestration. We evaluate data processing delays from fog-IoT integrated parts using a depth-first-search-based shortest path node finding configuration, which outperforms the existing shortest path algorithms in terms of algorithmic (i.e., depth-first search) efficiency, including the Bellman–Ford (BF) algorithm, Floyd–Warshall (FW) algorithm, Dijkstra algorithm (DA), and Apache Hadoop (AH) algorithm. The BDPS exhibits low latency in packet deliveries as well as low network overhead uplink activity through a map-reduced resilient data distribution mechanism, better than in BF, DA, FW, and AH. The overall BDPS scheme supports efficient data delivery across the fog-IoT orchestration, outperforming faster node execution while proving effective results, compared to DA, BF, FW and AH, respectively. Full article

From the perspective of energy providers, accurate short-term load forecasting plays a significant role in the energy generation plan, efficient energy distribution process and electricity price strategy optimisation. However, it is hard to achieve a satisfactory result because the historical data is irregular, non-smooth, non-linear and noisy. To handle these challenges, in this work, we introduce a novel model based on the Transformer network to provide an accurate day-ahead load forecasting service. Our model contains a similar day selection approach involving the LightGBM and k-means algorithms. Compared to the traditional RNN-based model, our proposed model can avoid falling into the local minimum and outperforming the global search. To evaluate the performance of our proposed model, we set up a series of simulation experiments based on the energy consumption data in Australia. The performance of our model has an average MAPE (mean absolute percentage error) of 1.13, where RNN is 4.18, and LSTM is 1.93. Full article

The twin parametric-margin support vector machine (TPMSVM) is an excellent kernel-based nonparallel classifier. However, TPMSVM was originally designed for binary classification, which is unsuitable for real-world multiclass applications. Therefore, this paper extends TPMSVM for multiclass classification and proposes a novel K multiclass nonparallel parametric-margin support vector machine (MNP-KSVC). Specifically, our MNP-KSVC enjoys the following characteristics. (1) Under the “one-versus-one-versus-rest” multiclass framework, MNP-KSVC encodes the complicated multiclass learning task into a series of subproblems with the ternary output $\{-1,0,+1\}$. In contrast to the “one-versus-one” or “one-versus-rest” strategy, each subproblem not only focuses on separating the two selected class instances but also considers the side information of the remaining class instances. (2) MNP-KSVC aims to find a pair of nonparallel parametric-margin hyperplanes for each subproblem. As a result, these hyperplanes are closer to their corresponding class and at least one distance away from the other class. At the same time, they attempt to bound the remaining class instances into an insensitive region. (3) MNP-KSVC utilizes a hybrid classification and regression loss joined with the regularization to formulate its optimization model. Then, the optimal solutions are derived from the corresponding dual problems. Finally, we conduct numerical experiments to compare the proposed method with four state-of-the-art multiclass models: Multi-SVM, MBSVM, MTPMSVM, and Twin-KSVC. Experimental results demonstrate the feasibility and effectiveness of MNP-KSVC in terms of multiclass accuracy and learning time. Full article

Pre-owned cars (i.e., cars with one or more previous retail owners) are extremely popular in Bangladesh. Customers who plan to purchase a pre-owned car often struggle to find a car within a budget as well as to predict the price of a particular pre-owned car. Currently, Bangladesh lacks online services that can provide assistance to customers purchasing pre-owned cars. A good prediction of prices of pre-owned cars can help customers greatly in making an informed decision about buying a pre-owned car. In this article, we look into this problem and develop a forecasting system (using machine learning techniques) that helps a potential buyer to estimate the price of a pre-owned car he is interested in. A dataset is collected and pre-processed. Exploratory data analysis has been performed. Following that, various machine learning regression algorithms, including linear regression, LASSO (Least Absolute Shrinkage and Selection Operator) regression, decision tree, random forest, and extreme gradient boosting have been applied. After evaluating the performance of each method, the best-performing model (XGBoost) was chosen. This model is capable of properly predicting prices more than $91\%$ of the time. Finally, the model has been deployed as a web application in a local machine so that this can be later made available to end users. Full article

In neural networks, a vital component in the learning and inference process is the activation function. There are many different approaches, but only nonlinear activation functions allow such networks to compute non-trivial problems by using only a small number of nodes, and such activation functions are called nonlinearities. With the emergence of deep learning, the need for competent activation functions that can enable or expedite learning in deeper layers has emerged. In this paper, we propose a novel activation function, combining many features of successful activation functions, achieving 2.53% higher accuracy than the industry standard ReLU in a variety of test cases. Full article

The impossibility of replacing hydraulic drives with other type drives in heavy duty machinery is the main reason for the development of a system for controlling hydraulic power steering. Moreover, the need for remote automatic control of the steering in specific types of mobile machinery leads to significant scientific interest in the design of embedded systems for controlling electro-hydraulic steering units. This article introduces an approach, which has been developed by authors, for robust stability and robust performance analysis of two embedded systems for controlling electro-hydraulic power steering in mobile machinery. It is based on the suggested new more realistic “black box” SIMO model with output multiplicative uncertainty. The uncertainty is obtained by parameters confidence interval and Gauss approximation formula. The embedded control systems used a linear-quadratic Gaussian (LQG) controller and H_∞ controller. The synthesis of the controllers was performed on the basis of a nominal part of an uncertainty model. Robust stability and robust performance analyses were performed in the framework of a so-called structured singular value, μ. The obtained theoretical results were experimentally approved by real experiments with both of the developed control systems, which were physically realized as a laboratory test rig. Full article

This study aims to describe the implementation of online learning that is applied today, and to develop a blended learning model as a strategy to provide student services according to the diversity of potential, needs, interests, and learning speeds. This study used research and development design. Several stages were carried out, namely, conducting literature studies, planning, organizing, mapping basic competencies, carrying out learning activities, reporting, and dissemination. The preliminary research samples included 10,466 students, and the samples for the blended learning model trial included 144 students through random sampling. The results showed that many students were happy to study at home, whereas others were happy to study at school. The facilities to support online learning at home were sufficient. The online learning presented by the teachers was quite interesting and most parents support it. Based on these findings, a blended learning model was developed. The results of the model trial show that blended learning is very useful and there is a significant increase in student learning outcomes. The blended learning model is very effective at supporting online learning. It can provide optimal services to students according to their talents, interests, and abilities. For that, a special strategy is needed and the cooperation of all the elements of the school. The development of an IT-based management system is very helpful in monitoring the progress of students and increasing the awareness of teachers and parents in overseeing the success of learning. The blended learning model in high school can be one of the models for schools that implement a semester credit system. Full article

The new era of IoT brings the necessity of smart synergy for diverse communication and computation entities. The two extremes are, on the one hand, the 5G Ultra-Reliable Low-Latency Communications (URLLC) required for Industrial IoT (IIoT) and Vehicle Communications (V2V, V2I, V2X). While on the other hand, the Ultra-Low Power, Wide-Range, Low Bit-rate Communications, such as Sigfox, LoRa/LoRaWAN, NB-IoT, Cat-M1, etc.; used for smart metering, smart logistics, monitoring, alarms, tracking applications. This extreme variety and diversity must work in synergy, all inter-operating/inter-working with the Internet. The communication solutions must mutually cooperate, but there must be a synergy in a broader sense that includes the various communication solutions and all the processing and storage capabilities from the edge cloud to the deep-cloud. In this paper, we consider a non-orthogonal multiple access (NOMA)-based device to device (D2D) communication system coexisting with a cellular network and utilize Greedy Asynchronous Distributed Interference Avoidance Algorithm (GADIA) for dynamic frequency allocation strategy. We analyze a max–min fairness optimization problem with energy budget constraints to provide a reasonable boundary rate for the downlink to all devices and cellular users in the network for a given total transmit power. A comprehensive simulation and numerical evaluation is performed. Further, we compare the performance of maximum achievable rate and energy efficiency (EE) at a given spectral efficiency (SE) while employing NOMA and orthogonal frequency-division multiple access (OFDMA). Full article

During the search for S-boxes resistant to Power Attacks, the S-box space has recently been divided into Hamming Weight classes, according to its theoretical resistance to these attacks using the metric variance of the confusion coefficient. This partition allows for reducing the size of the search space. The swap operator is frequently used when searching with a random selection of items to be exchanged. In this work, the theoretical probability of changing Hamming Weight class of the S-box is calculated when the swap operator is applied randomly in a permutation. The precision of these probabilities is confirmed experimentally. Its limit and a recursive formula are theoretically proved. It is shown that this operator changes classes with high probability, which favors the exploration of the Hamming Weight class of S-boxes space but dramatically reduces the exploitation within classes. These results are generalized, showing that the probability of moving within the same class is substantially reduced by applying two swaps. Based on these results, it is proposed to modify/improve the use of the swap operator, replacing its random application with the appropriate selection of the elements to be exchanged, which allows taking control of the balance between exploration and exploitation. The calculated probabilities show that the random application of the swap operator is inappropriate during the search for nonlinear S-boxes resistant to Power Attacks since the exploration may be inappropriate when the class is resistant to Differential Power Attack. It would be more convenient to search for nonlinear S-boxes within the class. This result provides new knowledge about the influence of this operator in the balance exploration–exploitation. It constitutes a valuable tool to improve the design of future algorithms for searching S-boxes with good cryptography properties. In a probabilistic way, our main theoretical result characterizes the influence of the swap operator in the exploration–exploitation balance during the search for S-boxes resistant to Power Attacks in the Hamming Weight class space. The main practical contribution consists of proposing modifications to the swap operator to control this balance better. Full article

As the amount of textual data available on the Internet grows substantially each year, there is a need for tools to assist with exploratory data analysis. Furthermore, to democratize the process of text analytics, tools must be usable for those with a non-technical background and those who do not have the financial resources to outsource their data analysis needs. To that end, we developed TextQ, which provides a simple, intuitive interface for exploratory analysis of textual data. We also tested the efficacy of TextQ using two case studies performed by subject matter experts—one related to a project on the detection of cyberbullying communication and another related to the user of Twitter for influence operations. TextQ was able to efficiently process over a million social media messages and provide valuable insights that directly assisted in our research efforts on these topics. TextQ is built using an open access platform and object-oriented architecture for ease of use and installation. Additional features will continue to be added to TextQ, based on the needs and interests of the installed base. Full article

In this study, banks’ business performance efficiency was analysed using data envelopment analysis (DEA), with expense categories as inputs and income categories as outputs. By incorporating a bootstrap method and a fuzzy data approach into a DEA model, additional insights and sensitivity analysis of the results were obtained. This study shows how fuzzy and bootstrap DEA can be used for investigating real market problems with uncertain data in an uncertain sample. The empirical analysis was based on the period of 2009–2018 for a sample of seven of Croatia’s largest private banks. The aim of the study was also to interpret the DEA results with regards to the specific market, legal, and macroeconomic conditions, caused by the changes introduced in the last decade. The results, and the changes in the inputs and outputs over time, revealed that the market processes occurring in the observed period had a significant impact on banks’ business performance, but led to a more efficient banking system. Two banks were found to be dominant over the others regardless of the changes in the sample and data fuzziness. DEA results were additionally compared to the most important financial indicators and accounting ratios, as an alternative or additional measure of banks’ efficiency and profitability. Full article

Nowadays, recommender systems are present in multiple application domains, such as e-commerce, digital libraries, music streaming services, etc. In the music domain, these systems are especially useful, since users often like to listen to new songs and discover new bands. At the same time, group music consumption has proliferated in this domain, not just physically, as in the past, but virtually in rooms or messaging groups created for specific purposes, such as studying, training, or meeting friends. Single-user recommender systems are no longer valid in this situation, and group recommender systems are needed to recommend music to groups of users, taking into account their individual preferences and the context of the group (when listening to music). In this paper, a group recommender system in the music domain is proposed, and an extensive comparative study is conducted, involving different collaborative filtering algorithms and aggregation methods. Full article

This paper focuses on the financial health prediction of businesses. The issue of predicting the financial health of companies is very important in terms of their sustainability. The aim of this paper is to determine the financial health of the analyzed sample of companies and to distinguish financially healthy companies from companies which are not financially healthy. The analyzed sample, in the field of heat supply in Slovakia, consisted of 444 companies. To fulfil the aim, appropriate financial indicators were used. These indicators were selected using related empirical studies, a univariate logit model and a correlation matrix. In the paper, two main models were applied—multivariate discriminant analysis (MDA) and feed-forward neural network (NN). The classification accuracy of the constructed models was compared using the confusion matrix, error type 1 and error type 2. The performance of the models was compared applying Brier score and Somers’ D. The main conclusion of the paper is that the NN is a suitable alternative in assessing financial health. We confirmed that high indebtedness is a predictor of financial distress. The benefit and originality of the paper is the construction of an early warning model for the Slovak heating industry. From our point of view, the heating industry works in the similar way in other countries, especially in transition economies; therefore, the model is applicable in these countries as well. Full article

Improving the development level of tourism service facilities in historic areas of old cities and realizing the sustainable tourism are important strategies for urban historical protection, economic development, and cultural rejuvenation. Districts at different tourism development stages show different characteristics of tourism service facilities. This study collects location-based service data and uses space syntax to identify the correlation between the distribution of tourism service facilities and street networks, which helps decision-makers to optimize the spatial layout of tourism facilities in the planning of historic areas. Taking the southern historic area of Nanjing, China, as an example, this is an area with a rich collection of cultural heritage and many historic districts, and the study reveals that the areas with strongest street agglomeration and best accessibility, as well as the districts with most mature tourism development, are the core of the tourism facilities. The agglomeration of transportation and accommodation facilities should be set at the traffic nodes as much as possible due to the highest correlation with the street network. Instead, the entertainment, catering, and shopping facilities can be set in the nontraffic node areas under the premise of ensuring good traffic accessibility owing to the insignificantly relationship with the street network. The research results can be used as an important reference for urban decision-makers regarding the planning of historic areas. Full article

The development of the field of digital humanities in recent years has led to the increased use of knowledge graphs within the community. Many digital humanities projects tend to model their data based on CIDOC-CRM ontology, which offers a wide array of classes appropriate for storing humanities and cultural heritage data. The CIDOC-CRM ontology model leads to a knowledge graph structure in which many entities are often linked to each other through chains of relations, which means that relevant information often lies many hops away from their entities. In this paper, we present a method based on graph walks and text processing to extract entity information and provide semantically relevant embeddings. In the process, we were able to generate similarity recommendations as well as explore their underlying data structure. This approach was then demonstrated on the Sphaera Dataset which was modeled according to the CIDOC-CRM data structure. Full article