Information

11 pages, 574 KiB

Open AccessArticle

Quantum for All: Using Social Media to Raise Public Awareness of Quantum Technologies

by Igor Gutorov, Irina Gorelova, Francesco Bellini and Fabrizio D’Ascenzo

Information 2025, 16(5), 375; https://doi.org/10.3390/info16050375 (registering DOI) - 30 Apr 2025

Quantum technology has significantly progressed over the last decade. While initially of interest to a narrow circle of professionals and technology enthusiasts, the general public’s knowledge of the developments in this domain, as well as the pitfalls and benefits, is currently considered low. [...] Read more.

Quantum technology has significantly progressed over the last decade. While initially of interest to a narrow circle of professionals and technology enthusiasts, the general public’s knowledge of the developments in this domain, as well as the pitfalls and benefits, is currently considered low. As quantum innovations are being integrated into strategic agendas on national and supranational levels, initiatives should be undertaken to raise public awareness about these technologies. The present paper examines the current trends of the implementation of social media, and, in particular, Instagram, by supranational organizations and initiatives to raise public awareness of quantum technology advancements. This research conducts an analysis of topical messages from the Instagram accounts of the International Year of Quantum Science and Technology (IYQ), the United Nations Educational, Scientific and Cultural Organization (UNESCO), and the European Commission account for Digital EU. The study highlights the patterns of social media communication by supranational organizations and initiatives on quantum technologies’ properties and provides reflections on the future research avenues to explore public awareness of this disruptive technology. The findings serve as the basis for further research on various aspects of public outreach to inform about the quantum evolution and its potential impact on society, economy, and future digital transformation developments. Full article

11 pages, 1513 KiB

Open AccessArticle

How Human–Robot Interaction Can Influence Task Performance and Perceived Cognitive Load at Different Support Conditions

by Simone Varrasi, Roberto Vagnetti, Nicola Camp, John Hough, Alessandro Di Nuovo, Sabrina Castellano and Daniele Magistro

Information 2025, 16(5), 374; https://doi.org/10.3390/info16050374 (registering DOI) - 30 Apr 2025

Abstract

Cognitive load refers to the mental resources used for executing simultaneous tasks. Since these resources are limited, individuals can only process a specific amount of information at a time. Daily activities often involve mentally demanding tasks, which is why social robots have been [...] Read more.

Cognitive load refers to the mental resources used for executing simultaneous tasks. Since these resources are limited, individuals can only process a specific amount of information at a time. Daily activities often involve mentally demanding tasks, which is why social robots have been proposed to simplify them and support users. This study aimed to verify whether and how a social robot can enhance the performance and support the management of cognitive load. Participants completed a baseline where a cognitive activity was carried out without support, and three other conditions where similar activities of increasing difficulty were collaboratively made with the NAO robot. In each condition, errors, time, and perceived cognitive load were measured. Results revealed that the robot improved performance and perceived cognitive load when compared to the baseline, but this support was then thwarted by excessive levels of cognitive load. Future research should focus on developing and designing collaborative human–robot interactions that consider the user’s mental demand, to promote effective and personalized robotic help for independent living. Full article

(This article belongs to the Special Issue Multimodal Human-Computer Interaction)

► Show Figures

Figure 1

14 pages, 973 KiB

Open AccessArticle

Trajectories of Digital Teaching Competence: A Multidimensional PLS-SEM Study in University Contexts

by Isaac González-Medina, Óscar Gavín-Chocano, Eufrasio Pérez-Navío and Guadalupe Aurora Maldonado Berea

Information 2025, 16(5), 373; https://doi.org/10.3390/info16050373 (registering DOI) - 30 Apr 2025

Abstract

Digital teaching competence (DTC) emerges as a fundamental strategic element in today’s higher education, where the DigCompEdu framework is consolidated as a key tool for assessing the digital skills of teachers. The study sample is composed of 3309 students from educational programs in [...] Read more.

Digital teaching competence (DTC) emerges as a fundamental strategic element in today’s higher education, where the DigCompEdu framework is consolidated as a key tool for assessing the digital skills of teachers. The study sample is composed of 3309 students from educational programs in Andalusian universities, and this study uses the PLS-SEM methodology to examine the interrelationships among six critical dimensions: professional engagement, digital resources, digital pedagogy, assessment and feedback, student empowerment, and digital competence development. The research proposes five main hypotheses that explore how digital resources drive pedagogy and assessment and how professional engagement directly influences student empowerment and the development of their own digital competencies. The results reveal the complexity inherent in developing digital competencies in the university setting, underscoring the need to implement ongoing training programs that address not only essential technical skills but also innovative pedagogical strategies adapted to digital environments. These programs should train teachers to effectively use digital resources, design interactive learning activities, and encourage active student participation. In addition, the importance of promoting teachers’ professional engagement is highlighted, as this factor significantly influences students’ empowerment and their ability to develop strong digital competencies, thus preparing them for the technological challenges of the 21st century and equipping them with the skills and competencies needed to thrive in an increasingly digitized world. Full article

(This article belongs to the Special Issue ICT, AI, and Assistive Technology for Accessible and Inclusive Education)

► Show Figures

Figure 1

18 pages, 5088 KiB

Open AccessArticle

Augmented Reality as an Educational Tool: Transforming Teaching in the Digital Age

by Miluska Odely Rodriguez-Saavedra, Luis Gonzalo Barrera Benavides, Iván Cuentas Galindo, Luis Miguel Campos Ascuña, Antonio Víctor Morales Gonzales, Jiang Wagner Mamani Lopez and Ruben Washington Arguedas-Catasi

Information 2025, 16(5), 372; https://doi.org/10.3390/info16050372 (registering DOI) - 30 Apr 2025

Abstract

Augmented reality (AR) is revolutionising education by integrating virtual elements into physical environments, enhancing interactivity and participation in learning processes. This study analyses the impact of AR in higher education, examining its influence on ease of adoption, student interaction, academic motivation and educational [...] Read more.

Augmented reality (AR) is revolutionising education by integrating virtual elements into physical environments, enhancing interactivity and participation in learning processes. This study analyses the impact of AR in higher education, examining its influence on ease of adoption, student interaction, academic motivation and educational sustainability. A quantitative and explanatory design was employed, applying structural equation modelling (SmartPLS) to a sample of 4900 students from public and private universities. The results indicate that AR significantly improves the ease of adoption (β = 0.867), favouring its implementation. In addition, student interaction increases academic motivation (β = 0.597), impacting on perceived academic performance (β = 0.722) and educational sustainability (β = 0.729). These findings highlight the need to design effective learning experiences with AR to maximise their impact. However, challenges such as technological infrastructure, teacher training and equitable access must be addressed to ensure sustainable adoption. This study provides empirical evidence on the potential of AR to enhance motivation, learning and educational transformation. Future research should explore its effectiveness in diverse contexts to optimise pedagogical strategies and institutional policies. Full article

(This article belongs to the Collection Augmented Reality Technologies, Systems and Applications)

► Show Figures

Figure 1

16 pages, 2542 KiB

Open AccessArticle

The Eyes: A Source of Information for Detecting Deepfakes

by Elisabeth Tchaptchet, Elie Fute Tagne, Jaime Acosta, Danda B. Rawat and Charles Kamhoua

Information 2025, 16(5), 371; https://doi.org/10.3390/info16050371 (registering DOI) - 30 Apr 2025

Abstract

Currently, the phenomenon of deepfakes is becoming increasingly significant, as they enable the creation of extremely realistic images capable of deceiving anyone thanks to deep learning tools based on generative adversarial networks (GANs). These images are used as profile pictures on social media [...] Read more.

Currently, the phenomenon of deepfakes is becoming increasingly significant, as they enable the creation of extremely realistic images capable of deceiving anyone thanks to deep learning tools based on generative adversarial networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We develop a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our experimental results on the Flickr-Faces-HQ (FFHQ) dataset and images generated by StyleGAN2 demonstrated that our algorithm achieved a remarkable detection accuracy of 0.968 and a sensitivity of 0.911. Additionally, the method had a specificity of 0.907 and a precision of 0.90 for this same dataset. And our experimental results on the CelebA dataset and images generated by ProGAN also demonstrated that our algorithm achieved a detection accuracy of 0.870 and a sensitivity of 0.901. Moreover, the method had a specificity of 0.807 and a precision of 0.88 for this same dataset. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods. Full article

► Show Figures

Figure 1

10 pages, 2448 KiB

Open AccessArticle

Image Generation and Super-Resolution Reconstruction of Synthetic Aperture Radar Images Based on an Improved Single-Image Generative Adversarial Network

by Xuguang Yang, Lixia Nie, Yun Zhang and Ling Zhang

Information 2025, 16(5), 370; https://doi.org/10.3390/info16050370 (registering DOI) - 30 Apr 2025

Abstract

This paper presents a novel method for the super-resolution reconstruction and generation of synthetic aperture radar (SAR) images with an improved single-image generative adversarial network (ISinGAN). Unlike traditional machine learning methods typically requiring large datasets, SinGAN needs only a single input image to [...] Read more.

This paper presents a novel method for the super-resolution reconstruction and generation of synthetic aperture radar (SAR) images with an improved single-image generative adversarial network (ISinGAN). Unlike traditional machine learning methods typically requiring large datasets, SinGAN needs only a single input image to extract internal structural details and generate high-quality samples. To improve this framework further, we introduced SinGAN with a self-attention module and incorporated noise specific to SAR images. These enhancements ensure that the generated images are more aligned with real-world SAR scenarios while also improving the robustness of the SinGAN framework. Experimental results demonstrate that ISinGAN significantly enhances SAR image resolution and target recognition performance. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

18 pages, 811 KiB

Open AccessArticle

RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks

by Owais Khan, Sana Ullah, Muzammil Khan and Han-Chieh Chao

Information 2025, 16(5), 369; https://doi.org/10.3390/info16050369 - 30 Apr 2025

Abstract

Applications of wireless sensor networks have significantly increased in the modern era. These networks operate on a limited power supply in the form of batteries, which are normally difficult to replace on a frequent basis. In wireless sensor networks, sensor nodes alternate between [...] Read more.

Applications of wireless sensor networks have significantly increased in the modern era. These networks operate on a limited power supply in the form of batteries, which are normally difficult to replace on a frequent basis. In wireless sensor networks, sensor nodes alternate between sleep and active states to conserve energy through different methods. Duty cycling is among the most commonly used methods. However, it suffers from problems like unnecessary idle listening, extra energy consumption, and packet drop rate. A Deep Reinforcement Learning-based B-MAC protocol called (RL-BMAC) has been proposed to address this issue. The proposed protocol deploys a deep reinforcement learning agent with fixed hyperparameters to optimize the duty cycling of the nodes. The reinforcement learning agent monitors essential parameters such as energy level, packet drop rate, neighboring nodes’ status, and preamble sampling. The agent stores the information as a representative state and adjusts the duty cycling of all nodes. The performance of RL-BMAC is compared to that of conventional B-MAC through extensive simulations. The results obtained from the simulations indicate that RL-BMAC outperforms B-MAC in terms of throughput by 58.5%, packet drop rate by 44.8%, energy efficiency by 35%, and latency by 26.93% Full article

(This article belongs to the Special Issue Sensing and Wireless Communications)

► Show Figures

Figure 1

19 pages, 840 KiB

Open AccessArticle

Exploring Large Language Models’ Ability to Describe Entity-Relationship Schema-Based Conceptual Data Models

by Andrea Avignone, Alessia Tierno, Alessandro Fiori and Silvia Chiusano

Information 2025, 16(5), 368; https://doi.org/10.3390/info16050368 - 29 Apr 2025

Abstract

In the field of databases, Large Language Models (LLMs) have recently been studied for generating SQL queries from textual descriptions, while their use for conceptual or logical data modeling remains less explored. The conceptual design of relational databases commonly relies on the entity-relationship [...] Read more.

In the field of databases, Large Language Models (LLMs) have recently been studied for generating SQL queries from textual descriptions, while their use for conceptual or logical data modeling remains less explored. The conceptual design of relational databases commonly relies on the entity-relationship (ER) data model, where translation rules enable mapping an ER schema into corresponding relational tables with their constraints. Our study investigates the capability of LLMs to describe in natural language a database conceptual data model based on the ER schema. Whether for documentation, onboarding, or communication with non-technical stakeholders, LLMs can significantly improve the process of explaining the ER schema by generating accurate descriptions about how the components interact as well as the represented information. To guide the LLM with challenging constructs, specific hints are defined to provide an enriched ER schema. Different LLMs have been explored (ChatGPT 3.5 and 4, Llama2, Gemini, Mistral 7B) and different metrics (F1 score, ROUGE, perplexity) are used to assess the quality of the generated descriptions and compare the different LLMs. Full article

(This article belongs to the Special Issue Applications of Information Extraction, Knowledge Graphs, and Large Language Models)

► Show Figures

Figure 1

26 pages, 4974 KiB

Open AccessArticle

Artificial Intelligence-Based Prediction Model for Maritime Vessel Type Identification

by Hrvoje Karna, Maja Braović, Anita Gudelj and Kristian Buličić

Information 2025, 16(5), 367; https://doi.org/10.3390/info16050367 - 29 Apr 2025

Abstract

This paper presents an artificial intelligence-based model for the classification of maritime vessel images obtained by cameras operating in the visible part of the electromagnetic spectrum. It incorporates both the deep learning techniques for initial image representation and traditional image processing and machine [...] Read more.

This paper presents an artificial intelligence-based model for the classification of maritime vessel images obtained by cameras operating in the visible part of the electromagnetic spectrum. It incorporates both the deep learning techniques for initial image representation and traditional image processing and machine learning methods for subsequent image classification. The presented model is therefore a hybrid approach that uses the Inception v3 deep learning model for the purpose of image vectorization and a combination of SVM, kNN, logistic regression, Naïve Bayes, neural network, and decision tree algorithms for final image classification. The model is trained and tested on a custom dataset consisting of a total of 2915 images of maritime vessels. These images were split into three subsections: training (2444 images), validation (271 images), and testing (200 images). The images themselves encompassed 11 distinctive classes: cargo, container, cruise, fishing, military, passenger, pleasure, sailing, special, tanker, and non-class (objects that can be encountered at sea but do not represent maritime vessels). The presented model accurately classified 86.5% of the images used for training purposes and therefore demonstrated how a relatively straightforward model can still achieve high accuracy and potentially be useful in real-world operational environments aimed at sea surveillance and automatic situational awareness at sea. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

26 pages, 1345 KiB

Open AccessArticle

Benchmarking 21 Open-Source Large Language Models for Phishing Link Detection with Prompt Engineering

by Arbi Haza Nasution, Winda Monika, Aytug Onan and Yohei Murakami

Information 2025, 16(5), 366; https://doi.org/10.3390/info16050366 - 29 Apr 2025

Abstract

Phishing URL detection is critical due to the severe cybersecurity threats posed by phishing attacks. While traditional methods rely heavily on handcrafted features and supervised machine learning, recent advances in large language models (LLMs) provide promising alternatives. This paper presents a comprehensive benchmarking [...] Read more.

Phishing URL detection is critical due to the severe cybersecurity threats posed by phishing attacks. While traditional methods rely heavily on handcrafted features and supervised machine learning, recent advances in large language models (LLMs) provide promising alternatives. This paper presents a comprehensive benchmarking study of 21 state-of-the-art open-source LLMs—including Llama3, Gemma, Qwen, Phi, DeepSeek, and Mistral—for phishing URL detection. We evaluate four key prompt engineering techniques—zero-shot, role-playing, chain-of-thought, and few-shot prompting—using a balanced, publicly available phishing URL dataset, with no fine-tuning or additional training of the models conducted, reinforcing the zero-shot, prompt-based nature as a distinctive aspect of our study. The results demonstrate that large open-source LLMs (≥27B parameters) achieve performance exceeding 90% F1-score without fine-tuning, closely matching proprietary models. Among the prompt strategies, few-shot prompting consistently delivers the highest accuracy (91.24% F1 with Llama3.3_70b), whereas chain-of-thought significantly lowers accuracy and increases inference time. Additionally, our analysis highlights smaller models (7B–27B parameters) offering strong performance with substantially reduced computational costs. This study underscores the practical potential of open-source LLMs for phishing detection and provides insights for effective prompt engineering in cybersecurity applications. Full article

35 pages, 1615 KiB

Open AccessArticle

Toward Robust Security Orchestration and Automated Response in Security Operations Centers with a Hyper-Automation Approach Using Agentic Artificial Intelligence

by Ismail, Rahmat Kurnia, Zilmas Arjuna Brata, Ghitha Afina Nelistiani, Shinwook Heo, Hyeongon Kim and Howon Kim

Information 2025, 16(5), 365; https://doi.org/10.3390/info16050365 - 29 Apr 2025

Abstract

The evolving landscape of cybersecurity threats demands the modernization of Security Operations Centers (SOCs) to enhance threat detection, response, and mitigation. Security Orchestration, Automation, and Response (SOAR) platforms play a crucial role in addressing operational inefficiencies; however, traditional no-code SOAR solutions face significant [...] Read more.

The evolving landscape of cybersecurity threats demands the modernization of Security Operations Centers (SOCs) to enhance threat detection, response, and mitigation. Security Orchestration, Automation, and Response (SOAR) platforms play a crucial role in addressing operational inefficiencies; however, traditional no-code SOAR solutions face significant limitations, including restricted flexibility, scalability challenges, inadequate support for advanced logic, and difficulties in managing large playbooks. These constraints hinder effective automation, reduce adaptability, and underutilize analysts’ technical expertise, underscoring the need for more sophisticated solutions. To address these challenges, we propose a hyper-automation SOAR platform powered by agentic-LLM, leveraging Large Language Models (LLMs) to optimize automation workflows. This approach shifts from rigid no-code playbooks to AI-generated code, providing a more flexible and scalable alternative while reducing operational complexity. Additionally, we introduce the IVAM framework, comprising three critical stages: (1) Investigation, structuring incident response into actionable steps based on tailored recommendations, (2) Validation, ensuring the accuracy and effectiveness of executed actions, (3) Active Monitoring, providing continuous oversight. By integrating AI-driven automation with the IVAM framework, our solution enhances investigation quality, improves response accuracy, and increases SOC efficiency in addressing modern cybersecurity threats. Full article

(This article belongs to the Special Issue The Convergence of Artificial Intelligence and Internet of Things Security: Shaping the Future of Secure Connected Systems)

► Show Figures

Figure 1

20 pages, 1902 KiB

Open AccessArticle

Distantly Supervised Relation Extraction Method Based on Multi-Level Hierarchical Attention

by Zhaoxin Xuan, Hejing Zhao, Xin Li and Ziqi Chen

Information 2025, 16(5), 364; https://doi.org/10.3390/info16050364 - 29 Apr 2025

Abstract

Distantly Supervised Relation Extraction (DSRE) aims to automatically identify semantic relationships within large text corpora by aligning with external knowledge bases. Despite the success of current methods in automating data annotation, they introduce two main challenges: label noise and data long-tail distribution. Label [...] Read more.

Distantly Supervised Relation Extraction (DSRE) aims to automatically identify semantic relationships within large text corpora by aligning with external knowledge bases. Despite the success of current methods in automating data annotation, they introduce two main challenges: label noise and data long-tail distribution. Label noise results in inaccurate annotations, which can undermine the quality of relation extraction. The long-tail problem, on the other hand, leads to an imbalanced model that struggles to extract less frequent, long-tail relations. In this paper, we introduce a novel relation extraction framework based on multi-level hierarchical attention. This approach utilizes Graph Attention Networks (GATs) to model the hierarchical structure of the relations, capturing the semantic dependencies between relation types and generating relation embeddings that reflect the overall hierarchical framework. To improve the classification process, we incorporate a multi-level classification structure guided by hierarchical attention, which enhances the accuracy of both head and tail relation extraction. A local probability constraint is introduced to ensure coherence across the classification levels, fostering knowledge transfer from frequent to less frequent relations. Experimental evaluations on the New York Times (NYT) dataset demonstrate that our method outperforms existing baselines, particularly in the context of long-tail relation extraction, offering a comprehensive solution to the challenges of DSRE. Full article

(This article belongs to the Collection Natural Language Processing and Applications: Challenges and Perspectives)

► Show Figures

Figure 1

24 pages, 2522 KiB

Open AccessArticle

Digital Requirements for Systems Analysts in Europe: A Sectoral Analysis of Online Job Advertisements and ESCO Skills

by Konstantinos Charmanas, Konstantinos Georgiou, Nikolaos Mittas and Lefteris Angelis

Information 2025, 16(5), 363; https://doi.org/10.3390/info16050363 - 29 Apr 2025

Abstract

Systems analysts can be considered a valuable part of organizations, as their responsibilities and contributions concern the improvement of information systems, which constitute an irreplaceable part of organizations. Thus, by exploring the current labor market of systems analysts, researchers can gather valuable knowledge [...] Read more.

Systems analysts can be considered a valuable part of organizations, as their responsibilities and contributions concern the improvement of information systems, which constitute an irreplaceable part of organizations. Thus, by exploring the current labor market of systems analysts, researchers can gather valuable knowledge to understand some invaluable societal needs. In this context, the objectives of this study are to investigate the sets of digital skills from the European Skills, Competences, Qualifications, and Occupations (ESCO) taxonomy required by systems analysts in Europe and examine the key characteristics of various relevant sectors. For this purpose, a tool combining topic extraction, machine learning, and statistical analysis is utilized. The outcomes prove that systems analysts may indeed possess different types of digital skills, where 12 distinct topics are discovered, and that the professional, scientific, and technical activities demand the most unique sets of digital skills across 17 sectors. Ultimately, the findings show that the numerous sectors indeed have divergent requirements and should be approached accordingly. Overall, this study can offer valuable guidelines for identifying both the general duties of systems analysts and the specific needs of each sector. Also, the presented tool and methods may provide ideas for exploring different domains associated with content information and distinct groups. Full article

(This article belongs to the Special Issue Application of Machine Learning in Data Science and Computational Intelligence)

► Show Figures

Figure 1

27 pages, 10552 KiB

Open AccessArticle

Enhancing Dongba Pictograph Recognition Using Convolutional Neural Networks and Data Augmentation Techniques

by Shihui Li, Lan Thi Nguyen, Wirapong Chansanam, Natthakan Iam-On and Tossapon Boongoen

Information 2025, 16(5), 362; https://doi.org/10.3390/info16050362 - 29 Apr 2025

Abstract

The recognition of Dongba pictographs presents significant challenges due to the pitfalls in traditional feature extraction methods, classification algorithms’ high complexity, and generalization ability. This study proposes a convolutional neural network (CNN)-based image classification method to enhance the accuracy and efficiency of Dongba [...] Read more.

The recognition of Dongba pictographs presents significant challenges due to the pitfalls in traditional feature extraction methods, classification algorithms’ high complexity, and generalization ability. This study proposes a convolutional neural network (CNN)-based image classification method to enhance the accuracy and efficiency of Dongba pictograph recognition. The research begins with collecting and manually categorizing Dongba pictograph images, followed by these preprocessing steps to improve image quality: normalization, grayscale conversion, filtering, denoising, and binarization. The dataset, comprising 70,000 image samples, is categorized into 18 classes based on shape characteristics and manual annotations. A CNN model is then trained using a dataset that is split into training (with 70% of all the samples), validation (20%), and test (10%) sets. In particular, data augmentation techniques, including rotation, affine transformation, scaling, and translation, are applied to enhance classification accuracy. Experimental results demonstrate that the proposed model achieves a classification accuracy of 99.43% and consistently outperforms other conventional methods, with its performance peaking at 99.84% under optimized training conditions—specifically, with 75 training epochs and a batch size of 512. This study provides a robust and efficient solution for automatically classifying Dongba pictographs, contributing to their digital preservation and scholarly research. By leveraging deep learning techniques, the proposed approach facilitates the rapid and precise identification of Dongba hieroglyphs, supporting the ongoing efforts in cultural heritage preservation and the broader application of artificial intelligence in linguistic studies. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining: Innovations in Big Data Analytics)

► Show Figures

Figure 1

35 pages, 644 KiB

Open AccessReview

Machine Learning in Baseball Analytics: Sabermetrics and Beyond

by Wenbing Zhao, Vyaghri Seetharamayya Akella, Shunkun Yang and Xiong Luo

Information 2025, 16(5), 361; https://doi.org/10.3390/info16050361 - 29 Apr 2025

Abstract

In this article, we provide a comprehensive review of machine learning-based sports analytics in baseball. This review is primarily guided by the following three research questions: (1) What baseball analytics problems have been studied using machine learning? (2) What data repositories have been [...] Read more.

In this article, we provide a comprehensive review of machine learning-based sports analytics in baseball. This review is primarily guided by the following three research questions: (1) What baseball analytics problems have been studied using machine learning? (2) What data repositories have been used? (3) What and how machine learning techniques have been employed for these studies? The findings of these research questions lead to several research contributions. First, we provide a taxonomy for baseball analytics problems. According to the proposed taxonomy, machine learning has been employed to (1) predict individual game plays; (2) determine player performance; (3) estimate player valuation; (4) predict future player injuries; and (5) project future game outcomes. Second, we identify a set of data repositories for baseball analytics studies. The most popular data repositories are Baseball Savant and Baseball Reference. Third, we conduct an in-depth analysis of the machine learning models applied in baseball analytics. The most popular machine learning models are random forest and support vector machine. Furthermore, only a small fraction of studies have rigorously followed the best practices in data preprocessing, machine learning model training, testing, and prediction outcome interpretation. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining: Innovations in Big Data Analytics)

► Show Figures

Figure 1

35 pages, 4874 KiB

Open AccessArticle

A COVID Support App Demonstrating the Use of a Rapid Persuasive System Design Approach

by Rashmi P. Payyanadan, Linda S. Angell and Amanda Zeidan

Information 2025, 16(5), 360; https://doi.org/10.3390/info16050360 - 29 Apr 2025

Abstract

Background: The persuasive systems design approach draws together theories around persuasive technology and their psychological foundations to form, alter and/or reinforce compliance, attitudes, and/or behaviors, which have been useful in building health and wellness apps. But with pandemics such as COVID and their [...] Read more.

Background: The persuasive systems design approach draws together theories around persuasive technology and their psychological foundations to form, alter and/or reinforce compliance, attitudes, and/or behaviors, which have been useful in building health and wellness apps. But with pandemics such as COVID and their ever-changing landscape, there is a need for such design processes to be even more time sensitive, while maintaining the inclusion of empirical evidence and rigorous testing that are the basis for the approach’s successful deployment and uptake. Objective: In response to this need, this study applied a recently developed rapid persuasive systems design (R-PSD) process to the development and testing of a COVID support app. The aim of this effort was to identify concrete steps for when and how to build new persuasion features on top of existing features in existing apps to support the changing landscape of target behaviors from COVID tracing and tracking, to long-term COVID support, information, and prevention. Methods: This study employed a two-fold approach to achieve this objective. First, a rapid persuasive systems design framework was implemented. A technology scan of current COVID apps was conducted to identify apps that had employed PSD principles, in the context of an ongoing analysis of behavioral challenges and needs that were surfacing in public health reports and other sources. Second, a test case of the R-PSD framework was implemented in the context of providing COVID support by building a COVID support app prototype. The COVID support prototype was then evaluated and tested to assess the effectiveness of the integrated approach. Results: The results of the study revealed the potential success that can be obtained from the application of the R-PSD framework to the development of rapid release apps. Importantly, this application provides the first concrete example of how the R-PSD framework can be operationalized to produce a functional, user-informed app under real-world time and resource constraints. Further, the persuasive design categories enabled the identification of essential persuasive features required for app development that are intended to facilitate, support, or precipitate behavior change. The small sample study facilitated the quick iteration of the app design to ensure time sensitivity and empirical evidence-based application improvements. The R-PSD approach can serve as a guided and practical design approach for future rapid release apps particularly in relation to the development of support apps for pandemics or other time-urgent community emergencies. Full article

► Show Figures

Figure 1

19 pages, 1433 KiB

Open AccessArticle

Optimized Deep Learning for Mammography: Augmentation and Tailored Architectures

by Syed Ibrar Hussain and Elena Toscano

Information 2025, 16(5), 359; https://doi.org/10.3390/info16050359 - 29 Apr 2025

Abstract

This paper investigates the categorization of mammogram images into benign, malignant and normal categories, providing novel approaches based on Deep Convolutional Neural Networks to the early identification and classification of breast lesions. Multiple DCNN models were tested to see how well deep learning [...] Read more.

This paper investigates the categorization of mammogram images into benign, malignant and normal categories, providing novel approaches based on Deep Convolutional Neural Networks to the early identification and classification of breast lesions. Multiple DCNN models were tested to see how well deep learning worked for difficult, multi-class categorization problems. These models were trained on pre-processed datasets with optimized hyperparameters (e.g., the batch size, learning rate, and dropout) which increased the precision of classification. Evaluation measures like confusion matrices, accuracy, and loss demonstrated their great classification efficiency with low overfitting and the validation results well aligned with the training. DenseNet-201 and MobileNet-V3 Large displayed significant generalization skills, whilst EfficientNetV2-B3 and NASNet Mobile struck the optimum mix of accuracy and efficiency, making them suitable for practical applications. The use of data augmentation also improved the management of data imbalances, resulting in more accurate large-scale detection. Unlike prior approaches, the combination of the architectures, pre-processing approaches, and data augmentation improved the system’s accuracy, indicating that these models are suitable for medical imaging tasks that require transfer learning. The results have shown precise and accurate classifications in terms of dealing with class imbalances and dataset poor quality. In particular, we have not defined a new framework for computer-aided diagnosis here, but we have reviewed a variety of promising solutions for future developments in this field. Full article

(This article belongs to the Special Issue Applications of Deep Learning in Bioinformatics and Image Processing)

► Show Figures

Figure 1

19 pages, 670 KiB

Open AccessArticle

Quantifying Gender Bias in Large Language Models Using Information-Theoretic and Statistical Analysis

by Imran Mirza, Akbar Anbar Jafari, Cagri Ozcinar and Gholamreza Anbarjafari

Information 2025, 16(5), 358; https://doi.org/10.3390/info16050358 - 29 Apr 2025

Abstract

Large language models (LLMs) have revolutionized natural language processing across diverse domains, yet they also raise critical fairness and ethical concerns, particularly regarding gender bias. In this study, we conduct a systematic, mathematically grounded investigation of gender bias in four leading LLMs—GPT-4o, Gemini [...] Read more.

Large language models (LLMs) have revolutionized natural language processing across diverse domains, yet they also raise critical fairness and ethical concerns, particularly regarding gender bias. In this study, we conduct a systematic, mathematically grounded investigation of gender bias in four leading LLMs—GPT-4o, Gemini 1.5 Pro, Sonnet 3.5, and LLaMA 3.1:8b—by evaluating the gender distributions produced when generating “perfect personas” for a wide range of occupational roles spanning healthcare, engineering, and professional services. Leveraging standardized prompts, controlled experimental settings, and repeated trials, our methodology quantifies bias against an ideal uniform distribution using rigorous statistical measures and information-theoretic metrics. Our results reveal marked discrepancies: GPT-4o exhibits pronounced occupational gender segregation, disproportionately linking healthcare roles to female identities while assigning male labels to engineering and physically demanding positions. In contrast, Gemini 1.5 Pro, Sonnet 3.5, and LLaMA 3.1:8b predominantly favor female assignments, albeit with less job-specific precision. These findings demonstrate how architectural decisions, training data composition, and token embedding strategies critically influence gender representation. The study underscores the urgent need for inclusive datasets, advanced bias-mitigation techniques, and continuous model audits to develop AI systems that are not only free from stereotype perpetuation but actively promote equitable and representative information processing. Full article

(This article belongs to the Special Issue Fundamental Problems of Information Studies)

► Show Figures

Figure 1

15 pages, 5001 KiB

Open AccessArticle

Research on Tongue Image Segmentation and Classification Methods Based on Deep Learning and Machine Learning

by Bin Liu, Zeya Wang, Kang Yu, Yunfeng Wang, Haiying Zhang, Tingting Song and Hao Yang

Information 2025, 16(5), 357; https://doi.org/10.3390/info16050357 - 29 Apr 2025

Abstract

Tongue diagnosis is a crucial method in traditional Chinese medicine (TCM) for obtaining information about a patient’s health condition. In this study, we propose a tongue image segmentation method based on deep learning and a pixel-level tongue color classification method utilizing machine learning [...] Read more.

Tongue diagnosis is a crucial method in traditional Chinese medicine (TCM) for obtaining information about a patient’s health condition. In this study, we propose a tongue image segmentation method based on deep learning and a pixel-level tongue color classification method utilizing machine learning techniques such as support vector machine (SVM) and ridge regression. These two approaches together form a comprehensive framework that spans from tongue image acquisition to segmentation and analysis. This framework provides an objective and visualized representation of pixel-wise classification and proportion distribution within tongue images, effectively assisting TCM practitioners in diagnosing tongue conditions. It mitigates the reliance on subjective observations in traditional tongue diagnosis, reducing human bias and enhancing the objectivity of TCM diagnosis. The proposed framework consists of three main components: tongue image segmentation, pixel-wise classification, and tongue color classification. In the segmentation stage, we integrate the Segment Anything Model (SAM) into the overall segmentation network. This approach not only achieves an intersection over union (IoU) score above 0.95 across three tongue image datasets but also significantly reduces the labor-intensive annotation process required for training traditional segmentation models while improving the generalization capability of the segmentation model. For pixel-wise classification, we propose a lightweight pixel classification model based on SVM, achieving a classification accuracy of 92%. In the tongue color classification stage, we introduce a ridge regression model that classifies tongue color based on the proportion of different pixel categories. Using this method, the classification accuracy reaches 91.80%. The proposed approach enables accurate and efficient tongue image segmentation, provides an intuitive visualization of tongue color distribution, and objectively analyzes and quantifies the proportion of different tongue color categories. In the future, this framework holds potential for validation and optimization in clinical practice. Full article

► Show Figures

Figure 1

Journal Description

Information

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI