Information

22 pages, 6612 KB

Open AccessArticle

AI for All: Adaptive, Accessible, and Inclusive Learning Experiences in the Age of Intelligent LMSs

by Athanasios Angeioplastis, Markos Konstantakis, John Aliprantis, Konstantinos Ordoumpozanis, Dimitrios Varsamis and Alkiviadis Tsimpiris

Information 2026, 17(2), 216; https://doi.org/10.3390/info17020216 - 19 Feb 2026

Abstract

Learning Management Systems (LMSs) remain largely static and administrative, often failing to support personalization and inclusive access to learning resources. This paper presents AI for All, a practical approach to building an adaptive, accessible, and inclusive learning experience within a mainstream LMS, [...] Read more.

Learning Management Systems (LMSs) remain largely static and administrative, often failing to support personalization and inclusive access to learning resources. This paper presents AI for All, a practical approach to building an adaptive, accessible, and inclusive learning experience within a mainstream LMS, demonstrated through the PREPARE project (Personalized Education Framework for AI-Enabled Adaptive and AR-Enhanced Learning) implemented in Moodle. PREPARE operationalizes an end-to-end generative AI pipeline that transforms a single authoritative PDF textbook into multimodal learning assets, including chapter summaries, structured notes and slide decks, formative quiz items, video mini-lectures with captions, podcast-style audio, and chapter-level augmented reality (AR) activities. In parallel, the system maintains a hybrid learner model by combining an initial FSLSM/ILS questionnaire with continuous behavior-based profiling derived from Moodle logs. Learner profiles drive non-prescriptive personalization through resource prioritization and recommendations, while preserving learner agency and access to all modalities. We describe the system architecture, Moodle integration mechanisms, and adaptation logic, and report an ongoing mixed-methods evaluation focusing on engagement, interaction diversity, perceived usefulness, and accessibility benefits. The system-level validation and deployment readiness suggest that AI-augmented LMS workflows can reduce instructor authoring effort while improving flexibility and inclusivity, provided that human-in-the-loop validation and privacy-aware analytics are embedded from the outset. Full article

(This article belongs to the Special Issue Human–Computer Interactions and Computer-Assisted Education)

16 pages, 1987 KB

Open AccessArticle

Uncovering eHealth Engagement Patterns Through Latent Class Analysis and SHAP: A Data Mining Perspective on Telehealth Access

by Ning Yang and Xin Yang

Information 2026, 17(2), 215; https://doi.org/10.3390/info17020215 - 19 Feb 2026

Abstract

Understanding how patients engage with digital health technologies is critical for improving the reach and equity of telehealth services. While prior research has largely focused on demographic predictors of telehealth use, this study applies a hybrid data mining approach to uncover behavioral engagement [...] Read more.

Understanding how patients engage with digital health technologies is critical for improving the reach and equity of telehealth services. While prior research has largely focused on demographic predictors of telehealth use, this study applies a hybrid data mining approach to uncover behavioral engagement patterns and evaluate their predictive power. Using data from the 2022 U.S. Health Information Trends Survey (HINTS; N = 3525), we identified four distinct eHealth engagement typologies through Latent Class Analysis (LCA): (1) Highly Digital Engagers, (2) Moderate Digital Users, (3) Social Media and App Enthusiasts, and (4) Wearable and Health App Enthusiasts. We then modeled telehealth utilization as the outcome using multivariable logistic regression and eXtreme Gradient Boosting (XGBoost) with Shapley Additive Explanations (SHAP). Compared to Highly Digital Engagers, Moderate Digital Users had significantly lower odds of telehealth use (OR = 0.52), while the other two classes had higher odds. SHAP analyses confirmed that depression status and geographic region interacted with engagement profiles to shape telehealth access, with a notably negative effect of depression within Class 2. These findings demonstrate the value of integrating behavioral segmentation with interpretable machine learning to characterize heterogeneity in digital health engagement and its association with telehealth utilization. Our study offers a scalable, population-level analytic framework that can inform targeted telehealth planning and outreach strategies aligned with real-world patterns of digital engagement. Full article

(This article belongs to the Special Issue Data Mining and Healthcare Informatics)

► Show Figures

Figure 1

20 pages, 3547 KB

Open AccessArticle

Wild Yak Behavior Recognition Method Based on an Improved Yolov11

by Jun Tie, Basang Dunzhu, Lu Zheng, Jin Xie, Shasha Tian and Shuangyang Li

Information 2026, 17(2), 214; https://doi.org/10.3390/info17020214 - 19 Feb 2026

Abstract

Yak daily behaviors, including feeding, standing, lying down, and walking, are closely related to their health status, making accurate behavior recognition essential for intelligent monitoring and management in yak husbandry. However, real-world grazing environments present significant challenges due to complex backgrounds, occlusions, small [...] Read more.

Yak daily behaviors, including feeding, standing, lying down, and walking, are closely related to their health status, making accurate behavior recognition essential for intelligent monitoring and management in yak husbandry. However, real-world grazing environments present significant challenges due to complex backgrounds, occlusions, small or distant targets, and high visual similarity between behavior categories. To address these issues, we propose a problem-driven, multi-scale behavior recognition framework based on an enhanced YOLOv11n architecture specifically designed for outdoor yak monitoring. A dedicated real-world dataset is constructed to capture four fundamental behaviors under diverse natural conditions. Based on this dataset, we develop the DPAP-YOLOv11n model, which incorporates Dynamic Convolution for adaptive feature modulation and Pinwheel-shaped Convolution (PConv) for fine-grained spatial representation. Additionally, a YOLOv7-Aux auxiliary training head is introduced to strengthen intermediate feature learning, and a Focal-PIoU loss function is adopted to improve robustness against hard or ambiguous samples. Experimental results show that DPAP-YOLOv11n outperforms the baseline YOLOv11n, achieving gains of 2.4% in mAP@50 and 2.8% in mAP@50–95. These findings demonstrate the practical potential of the proposed approach for high-precision, real-time yak behavior recognition in complex field environments. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

35 pages, 2049 KB

Open AccessArticle

LightGuardAgents: Secure and Robust Embedded Agents for Internet of Things Devices

by José Caicedo-Ortiz, Juan A. Holgado-Terriza, Pablo Pico-Valencia and Deiber Olivares-Olivares

Information 2026, 17(2), 213; https://doi.org/10.3390/info17020213 - 19 Feb 2026

Abstract

This paper presents a novel architecture for creating light agents embedded on Internet of Things (IoT) devices, specifically addressing challenges such as security, scalability, and adaptability. Despite the increasing adoption of agent-based approaches in IoT systems, security and robustness mechanisms are often treated [...] Read more.

This paper presents a novel architecture for creating light agents embedded on Internet of Things (IoT) devices, specifically addressing challenges such as security, scalability, and adaptability. Despite the increasing adoption of agent-based approaches in IoT systems, security and robustness mechanisms are often treated as external or ad hoc components in many existing solutions. This limits their effectiveness in dynamic environments that transmit sensitive and personal data and are, by nature, potentially untrusted. The proposed architecture applies Pyro4 for efficient communication among agents and implements a multi-level security scheme that combines symmetric, asymmetric, and hybrid encryption with Time-Based One-Time Passwords (TOTP)-based authentication. This ensures the data confidentiality and integrity within dynamic IoT environments. A case study validates the “agent of things” concept by confirming key security mechanisms such as agent authentication, multi-factor access control, secure communication, and fault resilience. Qualitative testing proved the architecture effective in mitigating common vulnerabilities in distributed agent environments, achieving high reliability scores in terms of security and performance. Experimental results show that over 75% of agent operations were completed in under 2 milliseconds, with a success rate above 99%, confirming the architecture’s lightweight execution and real-time readiness of the architecture for IoT environments. Therefore, the proposed architecture is particularly useful for researchers and practitioners working on secure IoT systems, embedded multi-agent architectures, and intelligent edge computing environments. Full article

30 pages, 364 KB

Open AccessArticle

Building Trust in AI: The Role of Technical Capacity, Social Risk, and Corporate Institutional Accountability

by Moonkyoung Jang

Information 2026, 17(2), 212; https://doi.org/10.3390/info17020212 - 19 Feb 2026

Abstract

This study advances understanding of public trust in artificial intelligence (AI) by distinguishing between overall trust in AI as a system and trust in specific AI components, and by disentangling the roles of perceived capacity, risk, and personhood. Drawing on nationally representative survey [...] Read more.

This study advances understanding of public trust in artificial intelligence (AI) by distinguishing between overall trust in AI as a system and trust in specific AI components, and by disentangling the roles of perceived capacity, risk, and personhood. Drawing on nationally representative survey data from 1099 U.S. adults collected in 2023 (AIMS dataset), the study estimates multiple regression models to examine how these evaluations shape trust across technical, organizational, and institutional dimensions. The results show that perceived cognitive capacity is the strongest positive predictor of both overall and component-level trust, while emotional and autonomous capacity primarily enhances trust in specific system components. Perceived social risk consistently undermines trust across all levels, whereas perceived personal risk mainly erodes trust in technical components. Importantly, support for granting AI legal or institutional status significantly increases trust, while moral consideration of AI exhibits limited direct effects, highlighting a critical distinction between institutional accountability and ethical concern. Together, these findings demonstrate that public trust in AI is not a unitary attitude but reflects multidimensional judgments about capability, risk, and governance. The study underscores the importance of institutional accountability and risk mitigation—alongside transparent communication about AI capabilities—for fostering sustainable public trust in AI. Full article

(This article belongs to the Topic Generative AI and Interdisciplinary Applications)

23 pages, 680 KB

Open AccessArticle

The Human Factor: Assessing Ransomware Vulnerability in Developing Nations’ Governments

by Paúl B. Vásquez-Méndez, Diana Carolina Arce Cuesta and Jorge Luis Zambrano-Martinez

Information 2026, 17(2), 211; https://doi.org/10.3390/info17020211 - 19 Feb 2026

Abstract

Ransomware represents a critical and escalating threat to public institutions in developing nations, where cybersecurity is often underprioritized. While technical vulnerabilities are significant, this study investigates the under-explored socio-organizational dimensions of cyber resilience within Latin American local governments. Employing a qualitative exploratory approach, [...] Read more.

Ransomware represents a critical and escalating threat to public institutions in developing nations, where cybersecurity is often underprioritized. While technical vulnerabilities are significant, this study investigates the under-explored socio-organizational dimensions of cyber resilience within Latin American local governments. Employing a qualitative exploratory approach, the research draws on semi-structured interviews with IT officials from Ecuadorian municipalities. The data were analyzed using Braun and Clarke’s thematic framework, applying a hybrid coding strategy that integrated deductive categories (institutional, human, technological) with inductive themes. The findings identify key vulnerability factors, including low risk perception among personnel, insufficient training, a lack of formal security policies, and weak regulatory enforcement. These human and institutional shortcomings often outweigh purely technological weaknesses, with social engineering serving as a predominant attack vector. Despite these challenges, the study also uncovers emergent resilience practices, including internal security committees, micro-training routines, AI-supported filtering, and informal troubleshooting networks. This research provides empirical evidence from a critically understudied context, underscoring the imperative for human-centric and context-sensitive cybersecurity strategies in the public sector. The conclusions establish a foundational understanding for developing adaptive security models, including future AI-driven solutions, tailored to the operational realities of developing nations. The study offers practical insights for policymakers and institutions aiming to bolster holistic cyber defense capabilities that address both human and technical factors. Full article

(This article belongs to the Special Issue Human Factors in Cyber Security: Social Engineering, Behavioural Aspects and Resilience Solutions)

► Show Figures

Figure 1

20 pages, 1864 KB

Open AccessArticle

Improving Construction Site Safety with Large Language Models: A Performance Analysis

by Concetta Manuela La Fata, Gianfranco Barone and Marco Cammarata

Information 2026, 17(2), 210; https://doi.org/10.3390/info17020210 - 17 Feb 2026

Abstract

Hazard recognition on construction sites is crucial for ensuring worker safety. Traditional methods widely rely on expert assessments, on-site inspections, and checklists, which can be time-consuming and susceptible to human error. The integration of multimodal Large Language Models (LLMs), such as GPT-based systems, [...] Read more.

Hazard recognition on construction sites is crucial for ensuring worker safety. Traditional methods widely rely on expert assessments, on-site inspections, and checklists, which can be time-consuming and susceptible to human error. The integration of multimodal Large Language Models (LLMs), such as GPT-based systems, offers a promising opportunity to overcome these limitations. Therefore, this study evaluates the effectiveness of GPT-4o in recognizing workplace hazards from image inputs, with a specific focus on construction sites. The results indicate that the model can serve as a valuable decision-support tool for safety professionals by providing scalable and real-time insights. However, the study also highlights key limitations, including the model’s reliance on general visual features rather than domain-specific safety knowledge, and the continued need for human supervision. Additionally, ethical concerns, including bias in AI-generated hazard assessments, data privacy, and the risk of over-reliance on AI, must be carefully managed to ensure these tools contribute responsibly and effectively to proactive risk management strategies. Full article

(This article belongs to the Special Issue Advancing Smart Systems Through Deep Learning, Generative AI, and Big Data Analytics)

25 pages, 672 KB

Open AccessSystematic Review

Enhancing IIoT Security Using Digital Twins in Industry 5.0: A Systematic Literature Review

by Md Whaiduzzaman, Natasha Tanzila Monalisa, Shinthi Tasnim Himi, Shirin Sultana, Tony Jan and Alistair Barros

Information 2026, 17(2), 209; https://doi.org/10.3390/info17020209 - 17 Feb 2026

Abstract

The rapid advancement of Industry 5.0 and the concurrent growth of the Industrial Internet of Things (IIoT) present significant cybersecurity challenges necessitating advanced solutions. Digital Twin technology, which enables the creation of near-perfect digital replicas of physical systems, offers a promising approach to [...] Read more.

The rapid advancement of Industry 5.0 and the concurrent growth of the Industrial Internet of Things (IIoT) present significant cybersecurity challenges necessitating advanced solutions. Digital Twin technology, which enables the creation of near-perfect digital replicas of physical systems, offers a promising approach to enhancing security and safety. This paper presents a literature review of the existing research to identify the challenges and future directions for integrating DT technology into IIoT from a security perspective. We aim to establish a comprehensive understanding of emerging features, including predictive analytics, real-time threat detection, and cybersecurity management. Additionally, this review highlights critical gaps, including complexity, model fidelity, real-time data processing, and scalability, which hinder the successful deployment of DT technology. Our study will assist researchers, cybersecurity practitioners, and policymakers in understanding the potential, limitations, and future advancements of this crucial area. Full article

(This article belongs to the Special Issue Technoeconomics of the Internet of Things)

18 pages, 1883 KB

Open AccessArticle

A Hybrid Predictive Model for Employee Turnover: Integrating Ensemble Learning and Feature-Driven Insights from IBM HR Analytics

by Muna I. Alyousef, Hamza Wazir Khan and Mian Usman Sattar

Information 2026, 17(2), 208; https://doi.org/10.3390/info17020208 - 17 Feb 2026

Abstract

Employee turnover presents a significant challenge to modern organizations, often resulting in operational disruptions, substantial hiring costs, and a loss of institutional knowledge. While traditional human resource practices have historically been reactive, the emergence of machine learning has introduced a proactive capability to [...] Read more.

Employee turnover presents a significant challenge to modern organizations, often resulting in operational disruptions, substantial hiring costs, and a loss of institutional knowledge. While traditional human resource practices have historically been reactive, the emergence of machine learning has introduced a proactive capability to anticipate and mitigate attrition before it occurs. This research utilizes the IBM HR Analytics dataset, which contains 1470 employee records and 35 distinct features, to develop a hybrid machine learning model designed to enhance the accuracy of turnover predictions. To ensure the model’s effectiveness, the researchers employed a comprehensive preprocessing phase that included eliminating non-informative features, applying label encoding to categorical data, and using StandardScaler to normalize quantitative values. A critical component of the study addressed the common issue of class imbalance within HR data. To resolve this, a hybrid sampling strategy was implemented, combining Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) to create a more balanced learning environment for the algorithms. The core of the predictive engine is a soft voting ensemble that integrates three powerful algorithms: Random Forest, XGBoost, and logistic regression. Evaluated on an 80/20 train–test split, the tuned XGBoost model achieved an impressive 84% accuracy and an Area Under the Curve (AUC) of 0.80. Meanwhile, the logistic regression component contributed the highest F1-score, reinforcing the overall strength and balance of the ensemble approach. These metrics confirm that the hybrid model is both robust and reliable for identifying at-risk employees. Beyond simple prediction, the study prioritized interpretability by using SHapley Additive exPlanations (SHAP) to identify the primary drivers of attrition. The analysis revealed that the most significant variables influencing an employee’s decision to leave include the interaction between job level and experience, frequent overtime, monthly income, current job level, and total years spent at the company. By providing these data-driven insights, the model empowers HR teams to transition from reactive troubleshooting to proactive retention planning, ultimately securing the organization’s talent and stability. Full article

(This article belongs to the Special Issue Machine Learning Approaches for Prediction and Decision Making)

► Show Figures

Figure 1

19 pages, 1381 KB

Open AccessArticle

Mitigating Hallucinations in Knowledge Graph Completion via Embedding-Guided Instruction Tuning

by Pengfei Zhang, Xing Xu, Junying Wu, Xin Lu, Jiahao Shi, Xiaodong Zhang, Dezhi Cui, Xiuxian Peng, Sihao He, Ping Zong, Guoxin Zhang, Zhonghong Ou, Meina Song and Yifan Zhu

Information 2026, 17(2), 207; https://doi.org/10.3390/info17020207 - 16 Feb 2026

Abstract

Real-world Knowledge Graphs (KGs) are inherently incomplete, which hinders effective downstream reasoning. While Large Language Models (LLMs) possess powerful semantic capabilities, directly applying them to Knowledge Graph Completion (KGC) often leads to hallucinations and a lack of structural awareness. To address these challenges, [...] Read more.

Real-world Knowledge Graphs (KGs) are inherently incomplete, which hinders effective downstream reasoning. While Large Language Models (LLMs) possess powerful semantic capabilities, directly applying them to Knowledge Graph Completion (KGC) often leads to hallucinations and a lack of structural awareness. To address these challenges, we propose Embedding-Guided Instruction Tuning (EGIT), a novel framework that synergizes the structural precision of embedding models with the semantic reasoning of LLMs. Our approach operates in three key stages: (1) utilizing pre-trained embedding models to automatically synthesize high-quality, annotation-free instruction data; (2) fine-tuning the LLM with these structure-aware instructions to adapt it to the KGC task; and (3) employing a joint inference mechanism where the embedding model retrieves candidates and the fine-tuned LLM performs the final selection, thereby significantly reducing hallucinations. In extensive experiments, the best variant of EGIT achieves 7.0% and 2.5% improvements in Hits@1 on the FB15k-237 and WN18RR datasets, respectively. Full article

(This article belongs to the Section Artificial Intelligence)

39 pages, 1783 KB

Open AccessArticle

Safety, Acceptability, and Usability of Immersive Gamification System for Use in Rehabilitation Management of Pediatric Patients with Cerebral Palsy and with Mobility Limitations (Phase 1 Trial)

by Maria Eliza R. Aguila, Cherica A. Tee, Josiah Cyrus R. Boque, Juan Raphael M. Gonzales, Isabel Teresa O. Salido, Bryan Andrei C. Galecio, Ben Anthony A. Lopez, Christian Alfredo K. Cruz, Michael L. Tee, Veeda Michelle M. Anlacan, Roland Dominic G. Jamora and Jaime D. L. Caro

Information 2026, 17(2), 206; https://doi.org/10.3390/info17020206 - 16 Feb 2026

Abstract

Virtual reality (VR) is increasingly integrated into the rehabilitation of children with cerebral palsy (CP). However, evidence to substantiate its potential as part of standard care remains limited. This Phase 1 study aimed to evaluate a VR-based immersive gamification technology system (ImGTS) for [...] Read more.

Virtual reality (VR) is increasingly integrated into the rehabilitation of children with cerebral palsy (CP). However, evidence to substantiate its potential as part of standard care remains limited. This Phase 1 study aimed to evaluate a VR-based immersive gamification technology system (ImGTS) for use in CP rehabilitation based on its safety, acceptability, and usability in healthy children. The system included software and hardware designs informed by discussions with CP rehabilitation and VR development experts (e.g., developmental pediatricians, physical therapists) and tailored to the local context, tested with two setups: the head-mounted display (HMD) and the semi-cave automatic virtual environment (semi-CAVE). We describe the experience of 30 healthy children aged 6–12 years using the ImGTS (Mission to Planet Axel version 1.0) using either the HMD (n = 15) or semi-CAVE (n = 15) setup. Descriptive and thematic analyses of data from semi-structured interviews based on questionnaires for safety and acceptability, as well as observations of behaviors for the usability dimensions of effectiveness, efficiency, and satisfaction, indicated that participants were engaged and motivated with the ImGTS, with low incidence and severity of VR-related symptoms for both setups and high acceptance of the ImGTS, based on perceptions of the environment and feelings of presence. Usability was also high. These findings suggest that the ImGTS is safe, acceptable, and usable for healthy children. This trial provides initial evidence to guide the methods of subsequent trials testing the safety, acceptability, usability, and clinical effectiveness of the ImGTS in children with cerebral palsy, and, eventually, to guide its deployment. Full article

(This article belongs to the Special Issue Advances in Human-Centered Artificial Intelligence)

21 pages, 1722 KB

Open AccessArticle

Cyberbullying Detection Based on Hybrid Neural Networks and Multi-Feature Fusion

by Junkuo Cao, Yunpeng Xiong, Weiquan Wang and Guolian Chen

Information 2026, 17(2), 205; https://doi.org/10.3390/info17020205 - 16 Feb 2026

Abstract

Cyberbullying demonstrates notable metaphorical and contextual traits, characterized by a high-dimensional sparse semantic space and dynamic evolution. Pre-trained models utilize extensive textual data for learning and employ transformer-based word vector generation techniques to accurately capture intricate semantics and nuanced syntax in text. However, [...] Read more.

Cyberbullying demonstrates notable metaphorical and contextual traits, characterized by a high-dimensional sparse semantic space and dynamic evolution. Pre-trained models utilize extensive textual data for learning and employ transformer-based word vector generation techniques to accurately capture intricate semantics and nuanced syntax in text. However, although a single pre-trained model demonstrates strong performance in contextual modeling, it still faces challenges including inadequate feature representation and limited generalization capability in classifying cyberbullying texts. This study proposes a cyberbullying detection model employing BERT-BiGRU-CNN (BBGC) to address this issue. The BBGC model initially employs BERT to produce word embeddings, subsequently inputs them into a BiGRU layer to acquire sequence features, and finally utilizes a CNN for the extraction of local features. The features derived from BERT, BiGRU, and CNN are integrated, followed by the application of the softmax function to yield the final outcome of cyberbullying detection. Experimental findings indicate that the BBGC fusion model surpasses individual pre-trained models in the task of detecting cyberbullying text. Furthermore, in comparison to hybrid neural network models utilizing RoBERTa, ALBERT, DistilBERT and other pre-trained models, the BBGC model demonstrates considerable advantages. Full article

(This article belongs to the Special Issue Artificial Intelligence, Generative AI and Large Language Models: Transforming Technology and Society)

9 pages, 622 KB

Open AccessArticle

Adolescents’ Experience with a Conversational Agent for Depression

by Alanna Testerman, Arjun Roshik Bharat, Tyrique Patterson and Eduardo Bunge

Information 2026, 17(2), 204; https://doi.org/10.3390/info17020204 - 16 Feb 2026

Abstract

Conversational Agents have been showing promise for depression in adults in the short-term. Although, there has been little research done for conversational agents (CAs) with depression in adolescents. This study aimed to determine adolescents’ user experience with Athenabot, a behavioral activation CA for [...] Read more.

Conversational Agents have been showing promise for depression in adults in the short-term. Although, there has been little research done for conversational agents (CAs) with depression in adolescents. This study aimed to determine adolescents’ user experience with Athenabot, a behavioral activation CA for depression. The study included 66 participants who interacted with Athenabot. Participants were aged 13 to 18 (mean = 14.12) and predominantly identified as female (56.1%). Participants’ confidence in the CA’s utility to improve mood significantly increased from baseline to post-intervention (p < 0.001). Adolescents provided an acceptable Net Promoter Score of 6.73. Positive themes from feedback included the CA being helpful and favorably viewed, while negative themes included its perceived audience-dependency and impersonal nature. Recommendations for improvement included reducing repetitive questions and enhancing personalization. Adolescents significantly preferred multiple-choice questions over typed response questions (p < 0.05). However, there were no significant differences in preference for emojis, memes, or GIFs. Adolescents reported an increased confidence that the CA could improve their mood. While the CAs received acceptable support, feedback highlighted a need for improved engagement and personalization. Adolescents favored multiple-choice button questions over typed responses and preferred GIFs over memes and emojis, with no significant demographic differences. Full article

(This article belongs to the Special Issue Information Technology for Smart Healthcare)

► Show Figures

Figure 1

23 pages, 635 KB

Open AccessArticle

Generative AI Recommendations for Environmental Sustainability: A Hybrid SEM–ANN Analysis of Gen Z Users in the Philippines

by Victor James C. Escolano, Yann-Mey Yee, Wei-Jung Shiang, Alexander A. Hernandez and Do Van Nang

Information 2026, 17(2), 203; https://doi.org/10.3390/info17020203 - 15 Feb 2026

Abstract

Generative AI offers promising potential to promote environmental sustainability through personalized recommendations that influence individual behavior. This study examines the factors influencing the adoption and actual use of generative AI recommendations for environmental sustainability among Gen Z users in the Philippines by integrating [...] Read more.

Generative AI offers promising potential to promote environmental sustainability through personalized recommendations that influence individual behavior. This study examines the factors influencing the adoption and actual use of generative AI recommendations for environmental sustainability among Gen Z users in the Philippines by integrating the Theory of Planned Behavior (TPB) and the Technology–Environmental, Economic, and Social Sustainability Theory (T-EESST) with key generative AI attributes, together with trust and perceived risk. Survey data were collected from 531 Gen Z users in higher education institutions in the National Capital Region (NCR), Philippines, and analyzed using a hybrid SEM and ANN approach. Results from SEM indicate that key AI attributes, namely perceived anthropomorphism, perceived intelligence, and perceived animacy, significantly influenced users’ attitude towards generative AI recommendations. Attitude, perceived behavioral control, and trust emerged as significant predictors of behavioral intention, which have an eventual positive relation to actual use and environmental sustainability outcomes. In contrast, subjective norms and perceived risk did not significantly affect behavioral intention, which may suggest that Gen Z users’ engagement with generative AI for environmental sustainability is primarily driven by internal evaluations, perceived capability, and trust rather than social pressure or risk concerns. Complementing these findings, the ANN analysis identified perceived behavioral control, attitude, and trust as the most important factors, reinforcing the robustness of the SEM results. Overall, this study integrates existing sustainability and technology-adoption literature by demonstrating how generative AI recommendations can support environmental sustainability among Gen Z users by combining behavioral theory, sustainability theory, and AI attributes through a hybrid SEM–ANN approach in the context of a developing country. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies for Sustainable Development)

► Show Figures

Figure 1

31 pages, 3309 KB

Open AccessArticle

DK-PRACTICE: An Intelligent Platform for Knowledge Tracing and Educational Content Recommendation: A Case Study in Higher Education

by Marina Delianidi, Konstantinos Diamantaras, Georgios Kokkonis, Antonis Sidiropoulos, Georgios Evangelidis and Dimitrios Karapiperis

Information 2026, 17(2), 202; https://doi.org/10.3390/info17020202 - 15 Feb 2026

Abstract

This paper introduces DK-PRACTICE, an intelligent educational platform that combines Knowledge Tracing (KT) and recommendation systems to support personalized learning in higher education. The platform utilizes a novel Paired Bipolar Bag-of-Words (PB-BoW) model to assess students’ knowledge states, forecast performance, and offer targeted [...] Read more.

This paper introduces DK-PRACTICE, an intelligent educational platform that combines Knowledge Tracing (KT) and recommendation systems to support personalized learning in higher education. The platform utilizes a novel Paired Bipolar Bag-of-Words (PB-BoW) model to assess students’ knowledge states, forecast performance, and offer targeted recommendations. To test its effectiveness in real-world settings, DK-PRACTICE was implemented in the “Computer Organization and Architecture” undergraduate course, involving 138 students in Pre-Test and 106 in Post-Test. Empirical analysis of benchmark datasets and a newly created course dataset showed that the PB-BoW model outperformed an RNN-based KT model in predictive accuracy. Student surveys indicated high levels of satisfaction with usability, relevance of recommendations, and overall learning support, with most participants expressing willingness to reuse the platform in other courses. These results demonstrate the potential of DK-PRACTICE as a scalable and adaptable tool for improving personalized learning and bridging the gap between AI-driven KT research and classroom implementation. Full article

(This article belongs to the Special Issue Personalized AI: Machine Learning for Tailored Interventions in Medicine and Education)

23 pages, 3200 KB

Open AccessArticle

Trustworthy Federated Learning with Blockchain-Based Consensus for Mitigating Poisoning Attacks in Healthcare Systems

by Raghad Hamed Alhamrani, Fatmah Omar Bamashmoos and Enas Fawzi Khairallah

Information 2026, 17(2), 201; https://doi.org/10.3390/info17020201 - 14 Feb 2026

Abstract

This paper presents a framework that integrates blockchain-enabled Federated Learning (FL) with consensus mechanisms to mitigate poisoning attacks in healthcare environments. The framework incorporates blockchain consensus mechanisms, with Proof-of-Work (PoW) used as a baseline and Proof-of-Stake (PoS) adopted as the proposed approach; both [...] Read more.

This paper presents a framework that integrates blockchain-enabled Federated Learning (FL) with consensus mechanisms to mitigate poisoning attacks in healthcare environments. The framework incorporates blockchain consensus mechanisms, with Proof-of-Work (PoW) used as a baseline and Proof-of-Stake (PoS) adopted as the proposed approach; both are evaluated independently within the same Secure Multiparty Computation (SMPC)-enabled federated learning architecture for privacy preservation. The proposed system is evaluated on the OCTMNIST and TissueMNIST datasets under both centralized and federated settings, including poisoning scenarios with 10% and 50% malicious clients. Results show that consensus-aware aggregation reduces the influence of unreliable client updates and improves the robustness of the global model under poisoning conditions. In addition, the framework prioritizes trustworthy client contributions during aggregation, supporting reliable model sharing in collaborative healthcare learning environments. Unlike prior blockchain-based federated learning defenses that introduce heavy cryptographic overhead, the proposed PoS-based aggregation explicitly balances robustness and computational efficiency, enabling practical deployment under high poisoning ratios. Full article

(This article belongs to the Special Issue IoT, AI, and Blockchain: Applications, Security, and Perspectives)

► Show Figures

Figure 1

19 pages, 1562 KB

Open AccessArticle

Vox2Face: Speech-Driven Face Generation via Identity-Space Alignment and Diffusion Self-Consistency

by Qiming Ma, Yizhen Wang, Xiang Sun, Jiadi Liu, Gang Cheng, Jia Feng, Rong Wang and Fanliang Bu

Information 2026, 17(2), 200; https://doi.org/10.3390/info17020200 - 14 Feb 2026

Abstract

Speech-driven face generation aims to synthesize a face image that matches a speaker’s identity from speech alone. However, existing methods typically trade identity fidelity for visual quality and rely on large end-to-end generators that are difficult to train and tune. We propose Vox2Face, [...] Read more.

Speech-driven face generation aims to synthesize a face image that matches a speaker’s identity from speech alone. However, existing methods typically trade identity fidelity for visual quality and rely on large end-to-end generators that are difficult to train and tune. We propose Vox2Face, a speech-driven face generation framework centered on an explicit identity space rather than direct speech-to-image mapping. A pretrained speaker encoder first extracts speech embeddings, which are distilled and metric-aligned to the ArcFace hyperspherical identity space, transforming cross-modal regression into a geometrically interpretable speech-to-identity alignment problem. On this unified identity representation, we reused an identity-conditioned diffusion model as the generative backbone and synthesized diverse, high-resolution faces in the Stable Diffusion latent space. To better exploit this prior, we introduce a discriminator-free diffusion self-consistency loss that treats denoising residuals as an implicit critique of speech-predicted identity embeddings and updates only the speech-to-identity mapping and lightweight LoRA adapters, encouraging speech-derived identities to lie on the high-probability identity manifold of the diffusion model. Experiments on the HQ-VoxCeleb dataset show that Vox2Face improves the ArcFace cosine similarity from 0.295 to 0.322, boosts R@10 retrieval accuracy from 29.8% to 32.1%, and raises the VGGFace Score from 18.82 to 23.21 over a strong diffusion baseline. These results indicate that aligning speech to a unified identity space and reusing a strong identity-conditioned diffusion prior is an effective method to jointly improve identity fidelity and visual quality. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

18 pages, 5196 KB

Open AccessArticle

Design and Assessment of an Immersive Hydraulic Transmission Teaching Laboratory

by Chunxue Wei, Zhuoxian Chen, Anran Leng, Jiuxiang Song and Baowei Zhang

Information 2026, 17(2), 199; https://doi.org/10.3390/info17020199 - 14 Feb 2026

Abstract

Traditional hydraulic transmission education is often hindered by the subject’s theoretical complexity and abstract nature. To address these challenges, this study introduces the Immersive Hydraulic Transmission Laboratory (IHTL), a virtual teaching system designed to enhance practical learning and theoretical comprehension. The IHTL comprises [...] Read more.

Traditional hydraulic transmission education is often hindered by the subject’s theoretical complexity and abstract nature. To address these challenges, this study introduces the Immersive Hydraulic Transmission Laboratory (IHTL), a virtual teaching system designed to enhance practical learning and theoretical comprehension. The IHTL comprises three key modules: hydraulic components, disassembly experiments, and hydraulic circuits. The system’s effectiveness was evaluated through a comparative study of 80 mechanical engineering students. Results showed that the experimental group exhibited a 20% higher rate of inquiry and achieved average test scores 20.475 points higher than the control group. Statistical analysis confirms that the IHTL significantly outperforms traditional teaching methods in both stimulating student interest and improving learning outcomes. Full article

(This article belongs to the Special Issue Trends in Artificial Intelligence-Supported E-Learning)

► Show Figures

Figure 1

22 pages, 2071 KB

Open AccessArticle

An Empirical Study of Transformer-Based Neural Machine Translation for English to Arabic

by Fares Alrashidi and Hassan I. Mathkour

Information 2026, 17(2), 198; https://doi.org/10.3390/info17020198 - 14 Feb 2026

Abstract

Neural machine translation (NMT) performance is strongly influenced by tokenization strategies, particularly for morphologically rich languages such as Arabic. Despite the importance of tokenization, there is a lack of controlled, reproducible studies examining its impact under low-resource conditions, which limits our understanding of [...] Read more.

Neural machine translation (NMT) performance is strongly influenced by tokenization strategies, particularly for morphologically rich languages such as Arabic. Despite the importance of tokenization, there is a lack of controlled, reproducible studies examining its impact under low-resource conditions, which limits our understanding of how different methods affect translation quality and training dynamics. This paper presents a controlled experimental study analyzing the impact of different tokenization methods on English → Arabic (EN → AR) translation using a Tiny Transformer model under low-resource conditions. The study aims to provide a systematic and reproducible comparison that isolates the effect of tokenization choices under fixed modeling and training constraints. Experiments are conducted with identical architecture, training steps, decoding procedure, and evaluation pipeline to ensure reproducibility. Translation quality is assessed using multiple metrics including BLEU, ChrF++, TER, and BERTScore, revealing substantial divergences and demonstrating empirically, in the context of low-resource Arabic NMT, that BLEU alone is insufficient for reliable evaluation. While the limitations of BLEU are known in general, our results provide new evidence showing that, under low-resource conditions and across different tokenization strategies, reliance on BLEU can lead to misleading conclusions about translation quality. Training dynamics are analyzed using TensorBoard, linking tokenization strategies to differences in convergence, saturation, and stability. For validation, a small-scale English → German (EN → DE) experiment confirms that the Tiny Transformer setup reproduces expected behavior. The contribution of this work lies in establishing controlled empirical evidence and practical insights, rather than absolute performance gains, for low-resource Arabic NMT. Our results provide controlled evidence that tokenization choice critically affects both translation quality and optimization dynamics, offering practical guidance for low-resource Arabic NMT research. Overall, byte-pair encoding (BPE) achieves the strongest balance across surface-level and semantic metrics under controlled low-resource conditions (BLEU: 8.57, ChrF++: 18.56, TER: 97.38, BERTScore-F1: 0.785). Character-level tokenization yields higher semantic similarity than subword-based methods, as reflected by BERTScore, but remains weaker in structural fidelity and surface-form accuracy, while SentencePiece exhibits intermediate behavior, favoring semantic adequacy over exact n-gram matching. These results confirm that tokenization choice critically influences both evaluation outcomes and optimization behavior, and that BLEU alone is insufficient for assessing Arabic translation quality. Full article

(This article belongs to the Special Issue Human and Machine Translation: Recent Trends and Foundations)

► 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