Search Results (72)

While most published research on COVID-19 focused on a few countries and especially on the second wave of the pandemic and the vaccination period, we turn to the first wave (March–May 2020) to examine the sentiments and emotions expressed by Twitter users in Greece. Using deep-learning techniques, the analysis reveals a complex interplay of surprise, anger, fear, and sadness. Initially, surprise was dominant, reflecting the shock and uncertainty accompanying the sudden onset of the pandemic. Anger replaced surprise as individuals struggled with isolation and social distancing. Despite these challenges, positive sentiments of hope, resilience and solidarity were also expressed. The COVID-19 pandemic had a strong imprint upon the emotional landscape worldwide and in Greece. This calls for appealing to emotions as well as to reason when crafting effective public health strategies. Full article

This study explores the effectiveness and efficiency of the popular OpenAI model ChatGPT, powered by GPT-3.5 and GPT-4, in programming tasks to understand its impact on programming and potentially software development. To measure the performance of these models, a quantitative approach was employed using the Mostly Basic Python Problems (MBPP) dataset. In addition to the direct assessment of GPT-3.5 and GPT-4, a comparative analysis involving other popular large language models in the AI landscape, notably Google’s Bard and Anthropic’s Claude, was conducted to measure and compare their proficiency in the same tasks. The results highlight the strengths of ChatGPT models in programming tasks, offering valuable insights for the AI community, specifically for developers and researchers. As the popularity of artificial intelligence increases, this study serves as an early look into the field of AI-assisted programming. Full article

In this paper, based on Gaussian 1σ-criterion and histogram segmentation, a weighted least-squares algorithm is applied and validated on digital holographic speckle pattern interferometric data to perform phase separation on the complex interference fields. The direct structural diagnosis tool is used to investigate defects and their impact on a complex antique wall painting of Giotto. The interferometry data is acquired with a portable off-axis interferometer set-up with a phase-shifted reference beam coupled with the object beam in front of the digital photosensitive medium. A digital holographic speckle pattern interferometry (DHSPI) system is used to register digital recordings of interferogram sequences over time. The surface is monitored for as long as it deforms prior to returning to its initial reference equilibrium state prior to excitation. The attempt to separate the whole vs. local defect complex amplitudes from the interferometric data is presented. The main aim is to achieve isolation and visualization of each defect’s impact amplitude in order to obtain detailed documentation of each defect and its structural impact on the surface for structural diagnosis purposes. Full article

News recommender systems (NRS) are crucial for helping users navigate the vast amount of content available online. However, traditional NRS often suffer from biases that lead to a narrow and unfair distribution of exposure across news items. In this paper, we propose a novel approach, the Contextual-Dual Bias Reduction Recommendation System (C-DBRRS), which leverages Long Short-Term Memory (LSTM) networks optimized with a multi-objective function to balance accuracy and diversity. We conducted experiments on two real-world news recommendation datasets and the results indicate that our approach outperforms the baseline methods, and achieves higher accuracy while promoting a fair and balanced distribution of recommendations. This work contributes to the development of a fair and responsible recommendation system. Full article

This paper presents a study guide and an analysis of its use in the computer programming learning process of an 8-year-old elementary school student through the Scratch program. The research’s objective is to explore and understand how this individual student approaches learning programming skills and tackles challenges within the Scratch environment. An individual case study approach was adopted at home, combining qualitative and quantitative methods to gain a comprehensive insight into the student’s learning process. The study was conducted without grant support, and the researcher actively participated as an educator and observer in the student’s learning sessions. Performance was assessed, and a semi-structured interview was conducted to inquire about the student’s experiences, motivations, and interests regarding programming in Scratch, as well as their feelings after the training. Additionally, the student’s activities during programming sessions were meticulously recorded, and projects created in Scratch were analyzed to assess progress and understanding of concepts. The findings of this research have the potential to contribute to the field of programming education and provide valuable insights into how young elementary school-aged individuals can acquire computer and programming skills in an interactive environment such as Scratch. The results obtained demonstrate that using the proposed guide to introduce elementary school students to programming at home, with parents acting as educators, is feasible. Therefore, it helps facilitate access to this knowledge, which is currently limited for many individuals in an official educational setting. Full article

Machine learning (ML) has become increasingly prevalent in various domains. However, ML algorithms sometimes give unfair outcomes and discrimination against certain groups. Thereby, bias occurs when our results produce a decision that is systematically incorrect. At various phases of the ML pipeline, such as data collection, pre-processing, model selection, and evaluation, these biases appear. Bias reduction methods for ML have been suggested using a variety of techniques. By changing the data or the model itself, adding more fairness constraints, or both, these methods try to lessen bias. The best technique relies on the particular context and application because each technique has advantages and disadvantages. Therefore, in this paper, we present a comprehensive survey of bias mitigation techniques in machine learning (ML) with a focus on in-depth exploration of methods, including adversarial training. We examine the diverse types of bias that can afflict ML systems, elucidate current research trends, and address future challenges. Our discussion encompasses a detailed analysis of pre-processing, in-processing, and post-processing methods, including their respective pros and cons. Moreover, we go beyond qualitative assessments by quantifying the strategies for bias reduction and providing empirical evidence and performance metrics. This paper serves as an invaluable resource for researchers, practitioners, and policymakers seeking to navigate the intricate landscape of bias in ML, offering both a profound understanding of the issue and actionable insights for responsible and effective bias mitigation. Full article

This paper analyzes the ways that the widespread use of generative AIs (GAIs) in education and, more broadly, in contributing to and reflecting the collective intelligence of our species, can and will change us. Methodologically, the paper applies a theoretical model and grounded argument to present a case that GAIs are different in kind from all previous technologies. The model extends Brian Arthur’s insights into the nature of technologies as the orchestration of phenomena to our use by explaining the nature of humans’ participation in their enactment, whether as part of the orchestration (hard technique, where our roles must be performed correctly) or as orchestrators of phenomena (soft technique, performed creatively or idiosyncratically). Education may be seen as a technological process for developing these soft and hard techniques in humans to participate in the technologies, and thus the collective intelligence, of our cultures. Unlike all earlier technologies, by embodying that collective intelligence themselves, GAIs can closely emulate and implement not only the hard technique but also the soft that, until now, was humanity’s sole domain; the very things that technologies enabled us to do can now be done by the technologies themselves. Because they replace things that learners have to do in order to learn and that teachers must do in order to teach, the consequences for what, how, and even whether learning occurs are profound. The paper explores some of these consequences and concludes with theoretically informed approaches that may help us to avert some dangers while benefiting from the strengths of generative AIs. Its distinctive contributions include a novel means of understanding the distinctive differences between GAIs and all other technologies, a characterization of the nature of generative AIs as collectives (forms of collective intelligence), reasons to avoid the use of GAIs to replace teachers, and a theoretically grounded framework to guide adoption of generative AIs in education. Full article

The emergence of fog computing has significantly enhanced real-time data processing by bringing computation resources closer to data sources. This adoption is very beneficial in the healthcare sector, where abundant time-sensitive processing tasks exist. Although such adoption is very promising, there is a challenge with the limited computational capacity of fog nodes. This challenge becomes even more critical when mobile IoT nodes enter the network, potentially increasing the network load. To address this challenge, this paper presents a framework that leverages a Many-to-One offloading (M2One) policy designed for modelling the dynamic nature and time-critical aspect of processing tasks in the healthcare domain. The framework benefits the multi-tier structure of the fog layer, making efficient use of the computing capacity of mobile fog nodes to enhance the overall computing capability of the fog network. Moreover, this framework accounts for mobile IoT nodes that generate an unpredictable volume of tasks at unpredictable intervals. Under the proposed policy, a first-tier fog node, called the coordinator fog node, efficiently manages all requests offloaded by the IoT nodes and allocates them to the fog nodes. It considers factors like the limited energy in the mobile nodes, the communication channel status, and low-latency demands to distribute requests among fog nodes and meet the stringent latency requirements of healthcare applications. Through extensive simulations in a healthcare scenario, the policy’s effectiveness showed an improvement of approximately 30% in average delay compared to cloud computing and a significant reduction in network usage. Full article

Mobile apps utilize the features of a mobile device to offer an ever-growing range of functionalities. This vast choice of functionalities is usually available for a small fee or for free. These apps access the user’s personal data, utilizing both the sensors on the device and big data from several sources. Nowadays, Artificial Intelligence (AI) is enhancing the ability to utilize more data and gain deeper insight. This increase in the access and utilization of personal information offers benefits but also challenges to trust. Using questionnaire data from Germany, this research explores the role of trust from the consumer’s perspective when purchasing mobile apps with enhanced AI. Models of trust from e-commerce are adapted to this specific context. A model is proposed and explored with quantitative methods. Structural Equation Modeling enables the relatively complex model to be tested and supported. Propensity to trust, institution-based trust, perceived sensitivity of personal information, and trust in the mobile app are found to impact the intention to use the mobile app with enhanced AI. Full article

In this article, we introduce a web-based malware detection system that leverages a deep-learning approach. Our primary objective is the development of a robust deep-learning model designed for classifying malware in executable files. In contrast to conventional malware detection systems, our approach relies on static detection techniques to unveil the true nature of files as either malicious or benign. Our method makes use of a one-dimensional convolutional neural network 1D-CNN due to the nature of the portable executable file. Significantly, static analysis aligns perfectly with our objectives, allowing us to uncover static features within the portable executable header. This choice holds particular significance given the potential risks associated with dynamic detection, often necessitating the setup of controlled environments, such as virtual machines, to mitigate dangers. Moreover, we seamlessly integrate this effective deep-learning method into a web-based system, rendering it accessible and user-friendly via a web interface. Empirical evidence showcases the efficiency of our proposed methods, as demonstrated in extensive comparisons with state-of-the-art models across three diverse datasets. Our results undeniably affirm the superiority of our approach, delivering a practical, dependable, and rapid mechanism for identifying malware within executable files. Full article

This small-scale study comprised an evaluation of a teacher professional learning experience that involved the collaborative creation of resources using immersive virtual reality (VR) as a retrieval practice tool, specifically focusing on the open access aspects of the SchooVR platform. SchooVR offers teachers and students tools to enhance teaching and learning by providing a range of virtual field trips and the ability to create customised virtual tours aligned with curriculum requirements. By leveraging the immersive 360° learning environment, learners can interact with content in meaningful ways, fostering engagement and deepening understanding. This study draws on the experiences of a group of postgraduate teacher education students and co-operating teachers in Ireland and Northern Ireland who collaborated on the creation of a number of immersive learning experiences across a range of subjects during a professional learning event. The research showcases how immersive realities, such as VR, can be integrated effectively into blended learning spaces to create resources that facilitate retrieval practice and self-paced study, thereby supporting the learning process. By embedding VR experiences into the curriculum, students are given opportunities for independent practice, review, and personalised learning tasks, all of which contribute to the consolidation of knowledge and the development of metacognitive skills. The findings suggest that SchooVR and similar immersive technologies have the potential to enhance educational experiences and promote effective learning outcomes across a variety of subject areas. Full article

This paper presents a case study on using Emacs and Org-mode for literate programming in undergraduate computer and data science courses. Over three academic terms, the author mandated these tools across courses in R, Python, C++, SQL, and more. The onboarding relied on simplified Emacs tutorials and starter configurations. Students gained proficiency after undertaking initial practice. Live coding sessions demonstrated the flexible instruction enabled by literate notebooks. Assignments and projects required documentation alongside functional code. Student feedback showed enthusiasm for learning a versatile IDE, despite some frustration with the learning curve. Skilled students highlighted efficiency gains in a unified environment. However, the uneven adoption of documentation practices pointed to a need for better incorporation into grading. Additionally, some students found Emacs unintuitive, desiring more accessible options. This highlights a need to match tools to skill levels, potentially starting novices with graphical IDEs before introducing Emacs. The key takeaways are as follows: literate programming aids comprehension but requires rigorous onboarding and reinforcement, and Emacs excels for advanced workflows but has a steep initial curve. With proper support, these tools show promise for data science education. Full article

The emergence of Industry 5.0 has revolutionized technology by integrating physical systems with digital networks. These advancements have also led to an increase in cyber threats, posing significant risks, particularly for small and medium-sized enterprises (SMEs). This research investigates the resistance of SMEs in Saudi Arabia and the United Kingdom (UK) to cyber security measures within the context of Industry 5.0, with a specific focus on governance and policy. It explores the cultural and economic factors contributing to this resistance, such as limited awareness of cyber security risks, financial constraints, and competing business priorities. Additionally, the study examines the role of government policies and regulations in promoting cyber security practices among SMEs and compares the approaches adopted by Saudi Arabia and the UK. By employing a mixed methods analysis, including interviews with SME owners and experts, the research highlights challenges and opportunities for improving cyber security governance and policy in both countries. The findings emphasize the need for tailored solutions due to the differing cultural and economic contexts between Saudi Arabia and the UK. Specifically, the study delves into the awareness and implementation of cyber security measures, focusing on SMEs in Saudi Arabia and their adherence to the Essential Cyber Security Controls (ECC-1:2018) guidelines. Furthermore, it examines the existing cyber security awareness practices and compliance in the UK, while also comparing official guidance documents aimed at supporting SMEs in achieving better cyber security practices. Based on the analysis, greater engagement with these documents is recommended in both countries to foster awareness, confidence, and compliance among SMEs, ultimately enhancing their cyber security posture. This paper offers a comparative research study on governance and policy between Saudi Arabia and the UK, presenting a set of recommendations to strengthen cyber security awareness and education, fortify regulatory frameworks, and foster public–private partnerships to combat cyber security threats in the Industry 5.0 landscape. Full article

This paper examines the status of the development of national digital health information systems (HIS) in Commonwealth of Independent States (CIS) member states. Data for research were collected using a questionnaire adapted from the questionnaire of the WHO’s Third Global Survey on eHealth. The results showed that the digital transformation of HIS was occurring in all seven CIS member states (participating in the study), which were financed by different resources. Laws and regulations on electronic medical records (EMR) use were present in almost all participating CIS member states. Various international standards and classifications were used to support development and the interoperability of digital health information system (d-HIS), including International Classification of Diseases (ICD), Digital Imaging and Communications in Medicine (DICOM), ISO 18308, Logical Observation Identifiers, Names, and Codes (LOINC), Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT), and ISO TC 215. Several CIS member states had adopted a national information security strategy for the safe processing of both personal data and medical confidential information. The digital transformation of healthcare and the Empowerment through Digital Health initiative are taking place in all CIS member states, which are at different stages of introducing electronic medical and health records. Full article

Convolutional Neural Networks (CNNs) are well-studied and commonly used for the problem of object detection thanks to their increased accuracy. However, high accuracy on its own says little about the effective performance of CNN-based models, especially when real-time detection tasks are involved. To the best of our knowledge, there has not been sufficient evaluation of the available methods in terms of their speed/accuracy trade-off. This work performs a review and hands-on evaluation of the most fundamental object detection models on the Common Objects in Context (COCO) dataset with respect to this trade-off, their memory footprint, and computational and storage costs. In addition, we review available datasets for medical mask detection and train YOLOv5 on the Properly Wearing Masked Faces Dataset (PWMFD). Next, we test and evaluate a set of specific optimization techniques, transfer learning, data augmentations, and attention mechanisms, and we report on their effect for real-time mask detection. Based on our findings, we propose an optimized model based on YOLOv5s using transfer learning for the detection of correctly and incorrectly worn medical masks that surpassed more than two times in speed (69 frames per second) the state-of-the-art model SE-YOLOv3 on the PWMFD while maintaining the same level of mean Average Precision (67%). Full article