Digital

Accurate and efficient estrus detection in sows is crucial in modern agricultural practices to ensure optimal reproductive health and successful breeding outcomes. A non-contact method using computer vision to detect a change in a sow’s vulva size holds great promise for automating and enhancing this critical process. However, achieving precise and reliable results depends heavily on maintaining a consistent camera distance during image capture. Variations in camera distance can lead to erroneous estrus estimations, potentially resulting in missed breeding opportunities or false positives. To address this challenge, we propose a robust six-step methodology, accompanied by three stages of evaluation. First, we carefully annotated masks around the vulva to ensure an accurate pixel perimeter calculation of its shape. Next, we meticulously identified keypoints on the sow’s vulva, which enabled precise tracking and analysis of its features. We then harnessed the power of machine learning to train our model using annotated images, which facilitated keypoint detection and segmentation with the state-of-the-art YOLOv8 algorithm. By identifying the keypoints, we performed precise calculations of the Euclidean distances: first, between each labium (horizontal distance), and second, between the clitoris and the perineum (vertical distance). Additionally, by segmenting the vulva’s size, we gained valuable insights into its shape, which helped with performing precise perimeter measurements. Equally important was our effort to calibrate the camera using monocular depth estimation. This calibration helped establish a functional relationship between the measurements on the image (such as the distances between the labia and from the clitoris to the perineum, and the vulva perimeter) and the depth distance to the camera, which enabled accurate adjustments and calibration for our analysis. Lastly, we present a classification method for distinguishing between estrus and non-estrus states in subjects based on the pixel width, pixel length, and perimeter measurements. The method calculated the Euclidean distances between a new data point and reference points from two datasets: “estrus data” and “not estrus data”. Using custom distance functions, we computed the distances for each measurement dimension and aggregated them to determine the overall similarity. The classification process involved identifying the three nearest neighbors of the datasets and employing a majority voting mechanism to assign a label. A new data point was classified as “estrus” if the majority of the nearest neighbors were labeled as estrus; otherwise, it was classified as “non-estrus”. This method provided a robust approach for automated classification, which aided in more accurate and efficient detection of the estrus states. To validate our approach, we propose three evaluation stages. In the first stage, we calculated the Mean Squared Error (MSE) between the ground truth keypoints of the labia distance and the distance between the predicted keypoints, and we performed the same calculation for the distance between the clitoris and perineum. Then, we provided a quantitative analysis and performance comparison, including a comparison between our previous U-Net model and our new YOLOv8 segmentation model. This comparison focused on each model’s performance in terms of accuracy and speed, which highlighted the advantages of our new approach. Lastly, we evaluated the estrus–not-estrus classification model by defining the confusion matrix. By using this comprehensive approach, we significantly enhanced the accuracy of estrus detection in sows while effectively mitigating human errors and resource wastage. The automation and optimization of this critical process hold the potential to revolutionize estrus detection in agriculture, which will contribute to improved reproductive health management and elevate breeding outcomes to new heights. Through extensive evaluation and experimentation, our research aimed to demonstrate the transformative capabilities of computer vision techniques, paving the way for more advanced and efficient practices in the agricultural domain. Full article

In response to the escalating threats of cybersecurity attacks and breaches, ensuring the development and deployment of secure IT products has become paramount for organizations in their cybersecurity transformation. This work emphasizes the critical need for a comprehensive and secure IT project management life cycle that safeguards products from their initial development stages through decommissioning. The primary objective is to seamlessly integrate security considerations into every facet of IT project management life cycles. This work embraces a cyber-resilient IT project management framework and advocates the inclusion of cybersecurity measures in IT projects and their strategic, organized, continuous, and systematic integration throughout the entire product life cycle. It introduces a pioneering framework that harmonizes the cybersecurity risk management process with the IT project management life cycle. This framework delineates a methodical sequence of steps, each encompassing a distinct set of activities. The effectiveness and practical applicability of the proposed framework were validated through a comprehensive case study focused on the Personal Health Record (PHR) system. The PHR case study served as a real-world scenario to assess the framework’s ability to address cybersecurity challenges in a specific domain. The results of the experiment demonstrated the framework’s efficacy in enhancing the security posture of IT projects, showcasing its adaptability and scalability across diverse applications. Full article

Over the past few decades, machine learning (ML) has demonstrated significant advancements in all areas of human existence. Machine learning and deep learning models rely heavily on data. Typically, basic machine learning (ML) and deep learning (DL) models receive input data and its matching output. Within the model, these models generate rules. In a physics-guided model, input and output rules are provided to optimize the model’s learning, hence enhancing the model’s loss optimization. The concept of the physics-guided neural network (PGNN) is becoming increasingly popular among researchers and industry professionals. It has been applied in numerous fields such as healthcare, medicine, environmental science, and control systems. This review was conducted using four specific research questions. We obtained papers from six different sources and reviewed a total of 81 papers, based on the selected keywords. In addition, we have specifically addressed the difficulties and potential advantages of the PGNN. Our intention is for this review to provide guidance for aspiring researchers seeking to obtain a deeper understanding of the PGNN. Full article

Urban mobility systems generate a massive volume of real-time data, providing an exceptional opportunity to understand and optimize transportation networks. To harness this potential, we developed UrbanFlow Milano, an interactive map-based dashboard designed to explore the intricate patterns of shared mobility use within the city of Milan. By placing users at the center of the analysis, UrbanFlow empowers them to visualize, filter, and interact with data to uncover valuable insights. Through a comprehensive user study, we observed how individuals interact with the dashboard, gaining critical feedback to refine its design and enhance its effectiveness. Our research contributes to the advancement of user-centric visual analytics tools that facilitate data-driven decision-making in urban planning and transportation management. Full article

The authors focus on innovating the research tool Urban’s Test of Creativity to enhance the evaluation and efficiency of the educational process. This paper presents the possibility of measuring creativity and spatial imagination in the SketchUp virtual environment. Teachers and HR professionals in modern companies require an overview of the key competencies of students and graduates, essential for the transformation towards Industry 5.0. The authors utilize the proven concept of Urban’s Test, modify it into a digital format, and integrate new elements that assess spatial visualization and functional creativity. Teachers and HR professionals gain an efficient tool that is easy to evaluate, time-efficient, and requires minimal infrastructure. The modified research tool is suitable for conducting action research and allows for comparing respondents’ results using quantitative methods. This pilot study aimed to validate the modified test and its properties. A total of one hundred respondents, divided into five groups based on age and education (approximately 10 to 25 years old), were tested. The results confirmed that the concept of Urban’s Test of Creativity can be successfully adapted for commonly available 3D modeling environments. Moreover, it was confirmed that within the target group, the level of spatial visualization improves gradually with age. Full article

Blockchain technology (BCT) is regarded as one of the most important and disruptive technologies in Industry 4.0. However, no comprehensive study addresses the contributions of BCT adoption (BCA) on some special business functionalities projected as financial variables like BCA integrity, transparency, etc. Therefore, the primary objective of this study was to close this theoretical gap and determine how BCA has contributed to the four business sectors that were selected since FinTech had the greatest potential in these domains. The PRISMA approach, a systematic literature review model, was used in this work to make sure that the greatest number of studies on the topic were accessed. The PRISMA model’s output helped identify relevant publications, and an analysis of these studies served as the foundation for this paper’s findings. The findings reveal that BCA for companies with a disrupting financial technology (FinTech) attitude can help in securing corporate transaction transparency; offer knowledge, same-data, and information sharing; enhance fidelity, integrity, and trust; improve organizational procedures; and prevent fraud with cyber-hacking protection and fraudulence suspension. Moreover, blockchain’s smart contract utilization feature offers ESG and sustainability functionality. This paper’s novelty is the projection to four business sectors of the three-layer research sequence: (i) financial variables operated as BCA functionalities, (ii) issues, risks, limitations, and opportunities associated with the financial variables, and (iii) implications, theoretical contributions, questions, potentiality, and outlook of BCA/FinTech issues. And the ability of managers or practitioners to reference this sequence and make decisions on BCA matters is considered a key contribution. The proposed methodology provides business practitioners with valuable insights to reevaluate their economic challenges and explore the potential of blockchain technology to address them. This study combined a systematic literature review (SLR) with qualitative analysis as part of a hybrid research approach. Quantitative analysis was carried out on all 835 selected papers in the first step, and qualitative analysis was carried out on the top-cited papers that were screened. The current work highlights the key challenges and opportunities in established blockchain implementations and discusses the outlook potentiality of blockchain technology adoption. This study will be useful to managers, practitioners, researchers, and scholars. Full article

This systematic literature review aimed to assess the methodological quality of user-centered usability evaluation of digital applications to promote citizens’ engagement and participation in public governance by (i) systematizing their purposes; (ii) analyzing the evaluation procedures, methods, and instruments that were used; (iii) determining their conformance with recommended usability evaluation good practices; and (iv) identifying the implications of the reported results for future developments. An electronic search was conducted on Web of Science, Scopus, and IEEE Xplore databases, and after a screening procedure considering predefined eligibility criteria, 34 studies were reviewed. These studies performed user-centered usability evaluation of digital applications related to (i) participatory reporting of urban issues, (ii) environmental sustainability, (iii) civic participation, (iv) urban planning, (v) promotion of democratic values, (vi) electronic voting, and (vii) chatbots. In terms of the methodological quality of the included studies, the results suggest that there is a high heterogeneity of the user-centered usability evaluation. Therefore, there is a need for recommendations to support user-centered usability evaluations of digital applications to promote citizens’ engagement and participation in public governance to improve the planning and conduction of future research. Full article

Pursuing human-centered, sustainable, and resilient production is shaping a future-oriented approach to manufacturing processes in the context of Industry 5.0. How can such production be implemented? For this purpose, this article analyses the effects of the developed Dresden Model of Adaptability (acronym: DreMoWabe) on the integration of holistic sustainability. The focus is on investigating the promotion of economic, environmental, and social sustainability goals in terms of the 17 Sustainable Development Goals and analyzing strategies to increase resilience to changing environmental conditions. A human-centered perspective is considered. The model proves to be a holistic approach that drives sustainable development of the production system through the comprehensive integration of human, technology, and organizational structures. Full article

This study aims to characterize the digital skills and pedagogical practices using digital technology among primary teachers (first CEB), as well as to map their understanding and practices of promoting gender equality using digital technology. To this end, an online questionnaire survey was conducted among teachers, which yielded 3871 valid responses, representing 17.5% of the population. The sample structure is identical to that of the population, in terms of sociodemographic and territorial characteristics, as well as to the years of schooling covered. It was found that teachers perceive themselves as digitally competent to carry out the essential part of their teaching tasks. Most have already tried to carry out a diverse set of pedagogical practices and activities using digital technology. However, as the overwhelming majority did not find differences between the uses that boys and girls make of digital technology, they also do not act to promote digital skills differently among girls. Some contextual variables were also found that explain these differences in perception and practices regarding digital in education. Full article

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop. Full article

Identifying and understanding visitor needs and expectations is of the utmost importance for a number of stakeholders and policymakers involved in the touristic domain. Apart from traditional forms of feedback, an abundance of related information exists online, scattered across various data sources like online social media, tourism-related platforms, traveling blogs, forums, etc. Retrieving and analyzing the aforementioned content is not a straightforward task and in order to address this challenge, we have developed the StreetLines platform, a novel information system that is able to collect, analyze and produce insights from the available tourism-related data. Its highly modular architecture allows for the continuous monitoring of varying pools of heterogeneous data sources whose contents are subsequently stored, after preprocessing, in a data repository. Following that, the aforementioned data feed a number of independent and parallel processing modules that extract useful information for all individuals involved in the tourism domain, like place recommendation for visitors and sentiment analysis and keyword extraction reports for professionals in the tourism industry. The presented platform is an outcome of the StreetLines project and apart from the contributions of its individual components, its novelty lies in the holistic approach to knowledge extraction and tourism data mining. Full article

The study empirically analyzed activism participants’ roles drawn from the lens of social media affordance and identified the activism opinion leaders based on the framework of network connectivity, message diffusion, and semantic relevancy through the case of the #Marchforourlives Twitter network, which has been rebranded as X. The study defines the #Marchforourlives Twitter network as a co-created activism network in collaboration with different degrees of contributors, such as the core advocates, the advocates, the supporters, and the amplifiers. The results showed that a very small number of tweets created by the core advocates played significant roles due to their extensive adoption by other participants, while many other original tweets were never mentioned or retweeted in the network. This study disclosed the extensive proportion of amplifiers as 95.13% among the examined participants. The study findings suggest that creating core agenda tweets with high amplifiability might be critical for successful hashtag activism to attract like-minded masses as networked protesters. Full article

ChatGPT has significantly increased in popularity in recent months because of its capacity to generate novel content and provide genuine responses to questions. Nevertheless, like all technologies, it is crucial to assess its limitations and features prior to implementing it into an educational setting. A major obstacle associated with ChatGPT is its tendency to produce consistent yet occasionally unreliable and inaccurate responses. Our study provides students with training in this area, and its objective was to analyse the opinion of those same university students studying education-related degrees regarding the efficacy of the usefulness of ChatGPT for their learning. We used a mixed methodology and two instruments for data collection: questionnaires and discussion groups. The sample comprised 150 university students pursuing degrees in teaching and social education. The results show that the majority of students are familiar with the technology but have not had any formal training in a university. They use this tool to complete academic assignments outside the classroom, and they emphasise the need for training in it. Furthermore, following the training, the students highlight an increase in motivation and a positive impact on the development of generic skills, such as information analysis, synthesis and management, problem solving, and learning how to learn. Ultimately, this study provides an opportunity to consider the implementation of educational training of this tool at the university level in order to ensure its appropriate use. Full article

Animated videos have been used in education for many years, and their efficacy in enhancing student motivation, engagement, and performance has been evaluated and reported in many studies. The aim of this study is twofold. First, after examining seventy-seven research articles, this study will attempt to provide an updated comprehensive literature review on the topic for the last decade. The articles were obtained from Google Scholar and Scopus following a certain methodology (search keywords, inclusion and exclusion criteria). The articles were examined for aspects such as the educational fields in which animated videos have been utilized over the last ten years, the researchers’ countries, the types of animated videos, the software tools used to create the educational animations, the research methods employed, and the aims and findings of the studies. The second part of this paper will present animated videos produced by teachers together with their experiences from the development process and classroom use. This study concentrates on the software tools the educators chose to use and their perceptions about developing their own animations. Findings indicate that when animated videos are produced by teachers, their creativity is boosted, and their communication skills are enhanced. Full article

By exploring the top three airports in Asia, this study explores the area of smart airport systems. With the goal of analyzing the significant elements of airport services that captivate travelers’ attention through online reviews and establishing a correlation between sentiment in reviews and numerical ratings given by travelers, the study analyzes what captivates travelers’ attention. Data mining, frequency analysis, sentiment analysis, and linear regression are employed in this study in order to analyze a dataset of 10,202 online reviews. The results indicate that the most common attributes of airport services significantly impact customer satisfaction, as well as how the sentiment expressed in online reviews correlates with the numerical ratings. A significant contribution of this study lies in its contribution to understanding the dynamics of customer satisfaction in the field of airport services as well as in identifying areas for improvement that could enhance the overall traveler experience in the burgeoning field of smart airports. In the context of smart airport systems, the analysis of exploratory and predictive data provides valuable insights into the optimization of airport operations, thus enriching the body of knowledge in this rapidly evolving area and providing the foundation for future research. Full article

Data envelopment analysis (DEA), which is frequently used in efficiency analysis, has also been applied to the measurement of entrepreneurial efficiency for the attainment of desired values of macroeconomic indicators (such as the objectives of sustainable economic growth). For this application, DEA takes into account the economic, environmental, and social impact of entrepreneurship as the three dimensions of sustainability. This paper aimed to investigate the potential for a scalable (in diversity, equity, and inclusion dimensions) DEA application in sustainable entrepreneurship performance (SEP) assessment through three channels (assessing SEP without ESG activities; ESG→SEP; ESG (DEI)→SEP) and present an empirical study related to economic growth assessment and its environmental, social, and governance (ESG), and diversity, equity and inclusion (DEI) determinants across selected Western Balkans (WB) and European Union (EU) companies, based on the use of the proposed scalable DEA. It highlights how crucial a scalable nonparametric approach to macroeconomic efficiency analysis is and provides a more comprehensive perspective to the researchers on this issue. This study used a non-oriented DEA model with variable return-to-scale in a group of 60 WB and 60 EU companies, all of which adopted ICT/Blockchain (BC) technologies (the 11 ESG metrics). The annual corporate data was collected for seven years from 2017 until 2023. We projected the selected data to three country particularities (mass acceptance, adoption, and implementation of ICT/BC; mass labor force return from overseas; and ethnic, cultural, and religious particularities) and performed statistical analysis. Our findings estimate the influence of these three particularities on economic growth potential. In all countries’ cases, we found a statistically sound (significant, positive) correlation between ESG and SEP’s economic growth quality performance. Particularly, when corporate social and DEI initiatives mediate (channel III), SEP’s economic growth gains the best performance (+18%) in countries with ethnic, cultural, and religious particularities (BiH, NM), a +17% in countries enjoying massive labor force return from overseas (AL) and performs well in quality (particularly in the innovation and integrity) SEP performance success dimensions (all WB and EU countries). The proposed scalable DEA shows clearly, by performing an empirical analysis, which modern business (adopting ICT/BC) is the most effective in achieving sustainability projected to country particularities, helping corporate management to improve economic growth efficiency. Full article

Artificial intelligence (AI) has helped enhance the management of software development projects through automation, improving efficiency and enabling project professionals to focus on strategic aspects. Despite its advantages, applying AI in software development project management still faces several challenges. Thus, this study investigates key obstacles to applying artificial intelligence in project management, specifically in the project planning phase. This research systematically reviews the existing literature. The review comprises scientific articles published from 2019 to 2024 and, from the inspected records, 17 papers were analyzed in full-text form. In this review, 10 key barriers were reported and categorized based on the Technology–Organization–Environment (TOE) framework. This review showed that eleven articles reported technological challenges, twelve articles identified organizational challenges, and six articles reported environmental challenges. In addition, this review found that there was relatively little interest in the literature on environmental challenges, compared to organizational and technological barriers. Full article

Brain tumors are frequently classified with high accuracy using convolutional neural networks (CNNs) to better comprehend the spatial connections among pixels in complex pictures. Due to their tiny receptive fields, the majority of deep convolutional neural network (DCNN)-based techniques overfit and are unable to extract global context information from more significant regions. While dilated convolution retains data resolution at the output layer and increases the receptive field without adding computation, stacking several dilated convolutions has the drawback of producing a grid effect. This research suggests a dilated parallel deep convolutional neural network (PDCNN) architecture that preserves a wide receptive field in order to handle gridding artifacts and extract both coarse and fine features from the images. This article applies multiple preprocessing strategies to the input MRI images used to train the model. By contrasting various dilation rates, the global path uses a low dilation rate (2,1,1), while the local path uses a high dilation rate (4,2,1) for decremental even numbers to tackle gridding artifacts and to extract both coarse and fine features from the two parallel paths. Using three different types of MRI datasets, the suggested dilated PDCNN with the average ensemble method performs best. The accuracy achieved for the multiclass Kaggle dataset-III, Figshare dataset-II, and binary tumor identification dataset-I is 98.35%, 98.13%, and 98.67%, respectively. In comparison to state-of-the-art techniques, the suggested structure improves results by extracting both fine and coarse features, making it efficient. Full article

Algorithms, indispensable to understand Artificial Intelligence (AI), are omnipresent in social media, but users’ understanding of these computational processes and the way they impact their consumption of information is often limited. There is a need for Media and Information Literacy (MIL) research investigating (a) how MIL can support algorithm literacy (AL) as a subset of competences and with what working definition, (b) what competences users need in order to evaluate algorithms critically and interact with them effectively, and (c) how to design learner-centred interventions that foster increased user understanding of algorithms and better response to disinformation spread by such processes. Based on Crossover project research, this paper looks at four scenarios used by journalists, developers and MIL experts that mirror users’ daily interactions with social media. The results suggest several steps towards integrating AL within MIL goals, while providing a concrete definition of algorithm literacy that is experience-based. The competences and design considerations are organised in a conceptual framework thematically derived from the experimentation. This contribution can support AI developers and MIL educators in their co-design of algorithm-literacy interventions and guide future research on AL as part of a set of nested AI literacies within MIL. Full article