Information

19 pages, 1821 KB

Open AccessArticle

Addressing Non-IID with Data Quantity Skew in Federated Learning

by Narisu Cha and Long Chang

Information 2025, 16(10), 861; https://doi.org/10.3390/info16100861 (registering DOI) - 4 Oct 2025

Non-IID is one of the key challenges in federated learning. Data heterogeneity may lead to slower convergence, reduced accuracy, and more training rounds. To address the common Non-IID data distribution problem in federated learning, we propose a comprehensive dynamic optimization approach based on [...] Read more.

Non-IID is one of the key challenges in federated learning. Data heterogeneity may lead to slower convergence, reduced accuracy, and more training rounds. To address the common Non-IID data distribution problem in federated learning, we propose a comprehensive dynamic optimization approach based on existing methods. It leverages MAP estimation of the Dirichlet parameter

β

to dynamically adjust the regularization coefficient

μ

and introduces orthogonal gradient coefficients

Δ_{i}

to mitigate gradient interference among different classes. The approach is compatible with existing federated learning frameworks and can be easily integrated. Achieves significant accuracy improvements in both mildly and severely Non-IID scenarios while maintaining a strong performance lower bound. Full article

45 pages, 5763 KB

Open AccessReview

A Survey of EEG-Based Approaches to Classroom Attention Assessment in Education

by Lijun Wei, Yuanyu Yu, Yuping Qin and Shuang Zhang

Information 2025, 16(10), 860; https://doi.org/10.3390/info16100860 (registering DOI) - 4 Oct 2025

Abstract

In evaluating classroom teaching quality, students’ attention assessment is a critical indicator in education management, as it holds significant practical value for improving teaching methods and instructional quality. Electroencephalogram (EEG) signals can monitor dynamic neural activity in the brain in real time. Their [...] Read more.

In evaluating classroom teaching quality, students’ attention assessment is a critical indicator in education management, as it holds significant practical value for improving teaching methods and instructional quality. Electroencephalogram (EEG) signals can monitor dynamic neural activity in the brain in real time. Their objectivity and non-invasive nature make them particularly suitable for attention assessment in classroom environments. This article first provides a brief overview of existing attention assessment methods, and then presents a comprehensive review of the current research status and methodologies in EEG-based attention assessment, including signal acquisition, preprocessing, feature extraction and selection, classification, and evaluation. Subsequently, the challenges in EEG-based teaching attention assessment are discussed, including the acquisition of high-quality signals, multimodal data fusion, complexity of data, and hardware setups for deep learning method implementation. Finally, a multimodal classroom attention assessment method, which integrates EEG and eye movement signals, is proposed to enhance teaching management. Full article

(This article belongs to the Special Issue Artificial Intelligence in the Era of Omni-Channel Media)

20 pages, 1980 KB

Open AccessReview

Augmented Reality in Engineering Education: A Bibliometric Review

by Georgios Lampropoulos, Antonio del Bosque, Pablo Fernández-Arias and Diego Vergara

Information 2025, 16(10), 859; https://doi.org/10.3390/info16100859 (registering DOI) - 4 Oct 2025

Abstract

The aim of this study is to examine the role and use of augmented reality in engineering education by examining the existing literature. A total of 235 studies from Scopus and Web of Science published during 2011–2025 were examined. The study focused on [...] Read more.

The aim of this study is to examine the role and use of augmented reality in engineering education by examining the existing literature. A total of 235 studies from Scopus and Web of Science published during 2011–2025 were examined. The study focused on analyzing the main characteristics of the studies, identifying the main topics, and exploring the use of augmented reality in engineering education. The study also highlighted current challenges and limitations and suggested future research directions. Based on the results, 7 main topics arose which were related to (i) Immersive technologies in engineering education, (ii) Gamified learning experiences, (iii) Remote and virtual laboratories, (iv) Visualization and 3D modeling, (v) Student motivation, (vi) Collaborative and interactive learning environments, and (vii) User-centered design and user experience. Augmented reality emerged as an effective educational tool that can positively impact engineering education and support both students and teachers. Specifically, physical, remote, and virtual laboratories that can improve students’ learning performance, motivation, creativity, engagement, and satisfaction can be created through augmented reality. Using augmented reality, students can develop their practical skills and knowledge within low-risk and secure learning environments. Additionally, via the realistic and interactive visualization, students’ knowledge acquisition and understanding can be enhanced. Finally, its ability to effectively support collaborative learning and experiential learning arose. Full article

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

► Show Figures

Figure 1

24 pages, 6042 KB

Open AccessArticle

IncentiveChain: Adequate Power and Water Usage in Smart Farming Through Diffusion of Blockchain Crypto-Ether

by Sukrutha L. T. Vangipuram, Saraju P. Mohanty and Elias Kougianos

Information 2025, 16(10), 858; https://doi.org/10.3390/info16100858 (registering DOI) - 4 Oct 2025

Abstract

The recent advancements in blockchain technology have also expanded its applications to smart agricultural fields, leading to increased research and studies in areas such as supply chain traceability systems and insurance systems. Policies and reward systems built on top of centralized systems face [...] Read more.

The recent advancements in blockchain technology have also expanded its applications to smart agricultural fields, leading to increased research and studies in areas such as supply chain traceability systems and insurance systems. Policies and reward systems built on top of centralized systems face several problems and issues, including data integrity issues, modifications in data readings, third-party banking vulnerabilities, and central point failures. The current paper discusses how farming is becoming a leading cause of water and electricity wastage and introduces a novel idea called IncentiveChain. To keep a limit on the usage of resources in farming, we implemented an application for distributing cryptocurrency to the producers, as the farmers are responsible for the activities in farming fields. Launching incentive schemes can benefit farmers economically and attract more interest and attention. We provide a state-of-the-art architecture and design through distributed storage, which will include using edge points and various technologies affiliated with national agricultural departments and regional utility companies to make IncentiveChain practical. We successfully demonstrate the execution of the IncentiveChain application by transferring crypto-ether from utility company accounts to farmer accounts in a decentralized system application. With this system, the ether is distributed to the farmer more securely using the blockchain, which in turn removes third-party banking vulnerabilities and central, cloud, and blockchain constraints and adds data trust and authenticity. Full article

(This article belongs to the Special Issue Information Systems and Technologies: Foundations, Techniques, and Applications)

23 pages, 5798 KB

Open AccessArticle

Application of Generative AI in Financial Risk Prediction: Enhancing Model Accuracy and Interpretability

by Kai-Chao Yao, Hsiu-Chu Hung, Ching-Hsin Wang, Wei-Lun Huang, Hui-Ting Liang, Tzu-Hsin Chu, Bo-Siang Chen and Wei-Sho Ho

Information 2025, 16(10), 857; https://doi.org/10.3390/info16100857 - 3 Oct 2025

Abstract

This study explores the application of generative artificial intelligence (AI) in financial risk forecasting, aiming to assess its potential in enhancing both the accuracy and interpretability of predictive models. Traditional methods often struggle with the complexity and nonlinearity of financial data, whereas generative [...] Read more.

This study explores the application of generative artificial intelligence (AI) in financial risk forecasting, aiming to assess its potential in enhancing both the accuracy and interpretability of predictive models. Traditional methods often struggle with the complexity and nonlinearity of financial data, whereas generative AI—such as large language models and generative adversarial networks (GANs)—offers novel solutions to these challenges. The study begins with a comprehensive review of current research on generative AI in financial risk prediction, with a focus on its roles in data augmentation and feature extraction. It then investigates techniques such as Generative Adversarial Explanation (GAX) to evaluate their effectiveness in improving model interpretability. Case studies demonstrate the practical value of generative AI in real-world financial forecasting and quantify its contribution to predictive accuracy. Furthermore, the study identifies key challenges—including data quality, model training costs, and regulatory compliance—and proposes corresponding mitigation strategies. The findings suggest that generative AI can significantly improve the accuracy and interpretability of financial risk models, though its adoption must be carefully managed to address associated risks. This study offers insights and guidance for future research in applying generative AI to financial risk forecasting. Full article

(This article belongs to the Special Issue Modeling in the Era of Generative AI)

18 pages, 668 KB

Open AccessArticle

Factors Affecting Human-Generated AI Collaboration: Trust and Perceived Usefulness as Mediators

by Hee-Sung Chae and Cheolho Yoon

Information 2025, 16(10), 856; https://doi.org/10.3390/info16100856 - 3 Oct 2025

Abstract

With the development of generative artificial intelligence (AI) technology, collaboration between humans and AI is expected to improve productivity, efficiency, and safety in various industries. This study presents and empirically analyzes the factors affecting collaboration between humans and AI. This study presents and [...] Read more.

With the development of generative artificial intelligence (AI) technology, collaboration between humans and AI is expected to improve productivity, efficiency, and safety in various industries. This study presents and empirically analyzes the factors affecting collaboration between humans and AI. This study presents and empirically analyzes a research model based on the antecedents of calculative-based, cognition-based, knowledge-based, and social influence-based trust. A total of 305 valid data points were collected through questionnaires completed by experts, office workers, and graduate students, and were analyzed using structural equation modeling. The analysis showed that all antecedents except familiarity, an antecedent of knowledge-based trust, significantly affected trust. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

32 pages, 4829 KB

Open AccessArticle

Dynamic Energy-Aware Anchor Optimization for Contact-Based Indoor Localization in MANETs

by Manuel Jesús-Azabal, Meichun Zheng and Vasco N. G. J. Soares

Information 2025, 16(10), 855; https://doi.org/10.3390/info16100855 - 3 Oct 2025

Abstract

Indoor positioning remains a recurrent and significant challenge in research. Unlike outdoor environments, where the Global Positioning System (GPS) provides reliable location information, indoor scenarios lack direct line-of-sight to satellites or cellular towers, rendering GPS inoperative and requiring alternative positioning techniques. Despite numerous [...] Read more.

Indoor positioning remains a recurrent and significant challenge in research. Unlike outdoor environments, where the Global Positioning System (GPS) provides reliable location information, indoor scenarios lack direct line-of-sight to satellites or cellular towers, rendering GPS inoperative and requiring alternative positioning techniques. Despite numerous approaches, indoor contexts with resource limitations, energy constraints, or physical restrictions continue to suffer from unreliable localization. Many existing methods employ a fixed number of reference anchors, which sets a hard balance between localization accuracy and energy consumption, forcing designers to choose between precise location data and battery life. As a response to this challenge, this paper proposes an energy-aware indoor positioning strategy based on Mobile Ad Hoc Networks (MANETs). The core principle is a self-adaptive control loop that continuously monitors the network’s positioning accuracy. Based on this real-time feedback, the system dynamically adjusts the number of active anchors, increasing them only when accuracy degrades and reducing them to save energy once stability is achieved. The method dynamically estimates relative coordinates by analyzing node encounters and contact durations, from which relative distances are inferred. Generalized Multidimensional Scaling (GMDS) is applied to construct a relative spatial map of the network, which is then transformed into absolute coordinates using reference nodes, known as anchors. The proposal is evaluated in a realistic simulated indoor MANET, assessing positioning accuracy, adaptation dynamics, anchor sensitivity, and energy usage. Results show that the adaptive mechanism achieves higher accuracy than fixed-anchor configurations in most cases, while significantly reducing the average number of required anchors and their associated energy footprint. This makes it suitable for infrastructure-poor, resource-constrained indoor environments where both accuracy and energy efficiency are critical. Full article

24 pages, 841 KB

Open AccessArticle

Mapping Theoretical Perspectives for Requisite Resilience

by Marion Neukam, Emmanuel Muller and Thierry Burger-Helmchen

Information 2025, 16(10), 854; https://doi.org/10.3390/info16100854 - 3 Oct 2025

Abstract

In increasingly turbulent environments, organizations must go beyond generic robustness and develop Requisite Resilience, the capacity to align internal variety with environmental variety to sustain core functions during crises. This study situates Requisite Resilience within organizational theory and strategic management, assessing how major [...] Read more.

In increasingly turbulent environments, organizations must go beyond generic robustness and develop Requisite Resilience, the capacity to align internal variety with environmental variety to sustain core functions during crises. This study situates Requisite Resilience within organizational theory and strategic management, assessing how major theories of the firm contribute to its development. The analysis groups these perspectives into foundational/diagnostic theories, which clarify environmental, structural and institutional constraints and correspond to passive resilience frameworks, and enabling/capability-building theories, which emphasize managerial agency, resource orchestration and adaptive learning, corresponding to active resilience frameworks. Findings indicate that while foundational perspectives offer essential diagnostics, they are insufficient on their own to foster Requisite Resilience. A composite configuration provides the strongest fit: co-evolutionary views offer an integrative backbone, dynamic capabilities and organizational learning enhance sensing, seizing and acting, and resource dependence theory informs the design of permeable boundaries. Full article

(This article belongs to the Section Information Applications)

► Show Figures

Figure 1

31 pages, 1144 KB

Open AccessSystematic Review

Smart Contracts, Blockchain, and Health Policies: Past, Present, and Future

by Kenan Kaan Kurt, Meral Timurtaş, Sevcan Pınar, Fatih Ozaydin and Serkan Türkeli

Information 2025, 16(10), 853; https://doi.org/10.3390/info16100853 - 2 Oct 2025

Abstract

The integration of blockchain technology into healthcare systems has emerged as a technical solution for enhancing data security, protecting privacy, and improving interoperability. Blockchain-based smart contracts offer reliability, transparency, and efficiency in healthcare services, making them a focal point of many studies. However, [...] Read more.

The integration of blockchain technology into healthcare systems has emerged as a technical solution for enhancing data security, protecting privacy, and improving interoperability. Blockchain-based smart contracts offer reliability, transparency, and efficiency in healthcare services, making them a focal point of many studies. However, challenges such as scalability, regulatory compliance, and interoperability continue to limit their widespread adoption. This study conducts a comprehensive literature review to assess blockchain-driven health data management, focusing on the classification of blockchain-based smart contracts in health policy and the health protocols and standards applicable to blockchain-based smart contracts. This review includes 80 core studies published between 2019 and 2025, identified through searches in PubMed, Scopus, and Web of Science using the PRISMA method. Risk of bias and methodological quality were assessed using the Joanna Briggs Institute tool. The findings highlight the potential of blockchain-enabled smart contracts in health policy management, emphasizing their advantages, limitations, and implementation challenges. Additionally, the research underscores their transformative impact on digital health policies in ensuring data integrity, enhancing patient autonomy, and fostering a more resilient healthcare ecosystem. Recent advancements in quantum technologies are also considered as they present both novel opportunities and emerging threats to the future security and design of healthcare blockchain systems. Full article

(This article belongs to the Special Issue Advancements in Healthcare Data Science: Innovations, Challenges and Applications)

► Show Figures

Figure 1

18 pages, 24741 KB

Open AccessArticle

Cross-Domain Residual Learning for Shared Representation Discovery

by Baoqi Zhao, Jie Pan, Zhijie Zhang and Fang Yang

Information 2025, 16(10), 852; https://doi.org/10.3390/info16100852 - 2 Oct 2025

Abstract

In order to solve the problem of inconsistent data distribution in machine learning, domain adaptation based on feature representation methods extracts features from the source domain, and transfers them to the target domain for classification. The existing feature representation-based methods mainly solve the [...] Read more.

In order to solve the problem of inconsistent data distribution in machine learning, domain adaptation based on feature representation methods extracts features from the source domain, and transfers them to the target domain for classification. The existing feature representation-based methods mainly solve the problem of inconsistent feature distribution between the source domain data and the target domain data, but only a few methods analyze the correlation of cross-domain features between the original space and shared latent space, which reduces the performance of domain adaptation. To this end, we propose a domain adaptation method with a residual module, the main ideas of which are as follows: (1) transfer the source domain data features to the target domain data through the shared latent space to achieve features sharing; (2) build a cross-domain residual learning model using the latent feature space as the residual connection of the original feature space, which improves the propagation efficiency of features; (3) use a regular feature space to sparse feature representation, which can improve the robustness of the model; and (4) give an optimization algorithm, and the experiments on the public visual datasets (Office31, Office-Caltech, Office-Home, PIE, MNIST-UPS, COIL20) results show that our method achieved 92.7% accuracy on Office-Caltech and 83.2% on PIE and achieved the highest recognition accuracy in three datasets, which verify the effectiveness of the method. Full article

(This article belongs to the Special Issue Machine Learning in Image Processing and Computer Vision)

► Show Figures

Figure 1

31 pages, 1105 KB

Open AccessArticle

MoCap-Impute: A Comprehensive Benchmark and Comparative Analysis of Imputation Methods for IMU-Based Motion Capture Data

by Mahmoud Bekhit, Ahmad Salah, Ahmed Salim Alrawahi, Tarek Attia, Ahmed Ali, Esraa Eldesouky and Ahmed Fathalla

Information 2025, 16(10), 851; https://doi.org/10.3390/info16100851 - 1 Oct 2025

Abstract

Motion capture (MoCap) data derived from wearable Inertial Measurement Units is essential to applications in sports science and healthcare robotics. However, a significant amount of the potential of this data is limited due to missing data derived from sensor limitations, network issues, and [...] Read more.

Motion capture (MoCap) data derived from wearable Inertial Measurement Units is essential to applications in sports science and healthcare robotics. However, a significant amount of the potential of this data is limited due to missing data derived from sensor limitations, network issues, and environmental interference. Such limitations can introduce bias, prevent the fusion of critical data streams, and ultimately compromise the integrity of human activity analysis. Despite the plethora of data imputation techniques available, there have been few systematic performance evaluations of these techniques explicitly for the time series data of IMU-derived MoCap data. We address this by evaluating the imputation performance across three distinct contexts: univariate time series, multivariate across players, and multivariate across kinematic angles. To address this limitation, we propose a systematic comparative analysis of imputation techniques, including statistical, machine learning, and deep learning techniques, in this paper. We also introduce the first publicly available MoCap dataset specifically for the purpose of benchmarking missing value imputation, with three missingness mechanisms: missing completely at random, block missingness, and a simulated value-dependent missingness pattern simulated at the signal transition points. Using data from 53 karate practitioners performing standardized movements, we artificially generated missing values to create controlled experimental conditions. We performed experiments across the 53 subjects with 39 kinematic variables, which showed that discriminating between univariate and multivariate imputation frameworks demonstrates that multivariate imputation frameworks surpassunivariate approaches when working with more complex missingness mechanisms. Specifically, multivariate approaches achieved up to a 50% error reduction (with the MAE improving from 10.8 ± 6.9 to 5.8 ± 5.5) compared to univariate methods for transition point missingness. Specialized time series deep learning models (i.e., SAITS, BRITS, GRU-D) demonstrated a superior performance with MAE values consistently below 8.0 for univariate contexts and below 3.2 for multivariate contexts across all missing data percentages, significantly surpassing traditional machine learning and statistical methods. Notable traditional methods such as Generative Adversarial Imputation Networks and Iterative Imputers exhibited a competitive performance but remained less stable than the specialized temporal models. This work offers an important baseline for future studies, in addition to recommendations for researchers looking to increase the accuracy and robustness of MoCap data analysis, as well as integrity and trustworthiness. Full article

(This article belongs to the Section Information Processes)

27 pages, 4522 KB

Open AccessArticle

Speaking like Humans, Spreading like Machines: A Study on Opinion Manipulation by Artificial-Intelligence-Generated Content Driving the Internet Water Army on Social Media

by Jinghong Zhou, Dandan Zhang, Jiawei Zhu, Fan Wang and Chongwu Bi

Information 2025, 16(10), 850; https://doi.org/10.3390/info16100850 - 1 Oct 2025

Abstract

This study focuses on the evolution of the Internet Water Army on social media, identifying a novel form known as artificial-intelligence-generated-content-enhanced social bots (AESBs), and compares their structural influence with traditional social bots in the context of public opinion guidance. Based on 3 [...] Read more.

This study focuses on the evolution of the Internet Water Army on social media, identifying a novel form known as artificial-intelligence-generated-content-enhanced social bots (AESBs), and compares their structural influence with traditional social bots in the context of public opinion guidance. Based on 3 years of real-world data from Weibo, this study develops a comprehensive framework integrating bot account detection, AESB content identification, and quantitative assessments of opinion guidance. A large-scale opinion propagation network is constructed to examine the structural roles of traditional social bots and AESB across three analytical levels: the node, community, and overall network. The results reveal substantial differences between AESB and traditional social bots. Social bots play a limited guiding role but help maintain network connectivity. In contrast, AESBs produce highly consistent and human-like content that demonstrates a significant capacity to reinforce topic focus, amplify emotional homogeneity, and deepen diffusion pathways, indicating a shift toward strategic content manipulation. These results suggest that AESBs are not merely passive generators but active agents of structural opinion control, capable of combining human mimicry with machine-level efficiency. This study advances theoretical understanding of IWA manipulation mechanisms, provides a replicable methodological approach, and offers practical implications for platform governance. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Graphical abstract

22 pages, 1669 KB

Open AccessArticle

Adaptive Multi-Objective Optimization for UAV-Assisted Wireless Powered IoT Networks

by Xu Zhu, Junyu He and Ming Zhao

Information 2025, 16(10), 849; https://doi.org/10.3390/info16100849 - 1 Oct 2025

Abstract

This paper studies joint data collection and wireless power transfer in a UAV-assisted IoT network. A rotary-wing UAV follows a fly–hover–communicate cycle. At each hover, it simultaneously receives uplink data in full-duplex mode while delivering radio-frequency energy to nearby devices. Using a realistic [...] Read more.

This paper studies joint data collection and wireless power transfer in a UAV-assisted IoT network. A rotary-wing UAV follows a fly–hover–communicate cycle. At each hover, it simultaneously receives uplink data in full-duplex mode while delivering radio-frequency energy to nearby devices. Using a realistic propulsion-power model and a nonlinear energy-harvesting model, we formulate trajectory and hover control as a multi-objective optimization problem that maximizes the aggregate data rate and total harvested energy while minimizing the UAV’s energy consumption over the mission. To enable flexible trade-offs among these objectives under time-varying conditions, we propose a dynamic, state-adaptive weighting mechanism that generates environment-conditioned weights online, which is integrated into an enhanced deep deterministic policy gradient (DDPG) framework. The resulting dynamic-weight MODDPG (DW-MODDPG) policy adaptively adjusts the UAV’s trajectory and hover strategy in response to real-time variations in data demand and energy status. Simulation results demonstrate that DW-MODDPG achieves superior overall performance and a more favorable balance among the three objectives. Compared with the fixed-weight baseline, our algorithm increases total harvested energy by up to 13.8% and the sum data rate by up to 5.4% while maintaining comparable or even lower UAV energy consumption. Full article

(This article belongs to the Section Internet of Things (IoT))

► Show Figures

Figure 1

31 pages, 14024 KB

Open AccessArticle

SAM-Based Input Augmentations and Ensemble Strategies for Image Segmentation

by Lorenzo Carisi, Francesco Chiereghin, Carlo Fantozzi and Loris Nanni

Information 2025, 16(10), 848; https://doi.org/10.3390/info16100848 - 30 Sep 2025

Abstract

Despite the remarkable progress of deep learning in image segmentation, models often struggle with generalization across diverse datasets. This study explores novel input augmentation techniques and ensemble strategies to improve image segmentation performance. We investigate how the Segment Anything Model (SAM) can produce [...] Read more.

Despite the remarkable progress of deep learning in image segmentation, models often struggle with generalization across diverse datasets. This study explores novel input augmentation techniques and ensemble strategies to improve image segmentation performance. We investigate how the Segment Anything Model (SAM) can produce relevant information for model training. We believe that SAM offers a promising source of prior information that can be exploited to improve robustness and accuracy. Building on this, we propose input augmentation techniques that integrate SAM information directly into the images, enhancing the learning process of segmentation models. Each proposed augmentation method comes with its unique advantages; therefore, to leverage the strengths of each approach, we introduce AuxMix, a model trained with a combination of SAM-based augmentation methods. We conduct experiments on different state-of-the-art segmentation models, evaluating the effects of each method independently and within an ensemble framework. The results show that our ensemble strategy, combining complementary information from each augmentation, leads to robust and improved segmentation performance in a large set of datasets. We use only publicly available datasets in our experiments, and all the code developed to reproduce our results is available online on GitHub. Full article

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

27 pages, 2395 KB

Open AccessArticle

Revealing Short-Term Memory Communication Channels Embedded in Alphabetical Texts: Theory and Experiments

by Emilio Matricciani

Information 2025, 16(10), 847; https://doi.org/10.3390/info16100847 - 30 Sep 2025

Abstract

The aim of the present paper is to further develop a theory on the flow of linguistic variables making a sentence, namely, the transformation of (a) characters into words; (b) words into word intervals; and (c) word intervals into sentences. The relationship between [...] Read more.

The aim of the present paper is to further develop a theory on the flow of linguistic variables making a sentence, namely, the transformation of (a) characters into words; (b) words into word intervals; and (c) word intervals into sentences. The relationship between two linguistic variables is studied as a communication channel whose performance is determined by the slope of their regression line and by their correlation coefficient. The mathematical theory is applicable to any field/specialty in which a linear relationship holds between two variables. The signal-to-noise ratio Γ is a figure of merit of a channel being “deterministic”, i.e., a channel in which the scattering of the data around the regression line is negligible. The larger Γ is, the more the channel is “deterministic”. In conclusion, humans have invented codes whose sequences of symbols that make words cannot vary very much when indicating single physical or mental objects of their experience (larger Γ). On the contrary, large variability (smaller Γ) is achieved by introducing interpunctions to make word intervals, and word intervals make sentences that communicate concepts. This theory can inspire new research lines in cognitive science research. Full article

34 pages, 3162 KB

Open AccessArticle

AI-Based Digital Twins of Students: A New Paradigm for Competency-Oriented Learning Transformation

by Igor Kabashkin

Information 2025, 16(10), 846; https://doi.org/10.3390/info16100846 - 30 Sep 2025

Abstract

Universities face growing pressure to deliver personalized learning that prepares students with adaptable, future-ready competencies. Traditional static curricula are often unable to meet these demands. This paper introduces a novel framework based on AI-enhanced digital twins of students (DTS) as dynamic virtual representations [...] Read more.

Universities face growing pressure to deliver personalized learning that prepares students with adaptable, future-ready competencies. Traditional static curricula are often unable to meet these demands. This paper introduces a novel framework based on AI-enhanced digital twins of students (DTS) as dynamic virtual representations integrating academic performance, competency attainment, learning preferences, career objectives, and engagement patterns. The DTS framework employs artificial intelligence algorithms, semantic ontologies spanning educational and career domains, and real-time feedback mechanisms for personalized learning pathway orchestration. To demonstrate the framework’s potential, a simulation study was conducted using synthetic student data. Results compared DTS-guided adaptive pathways with traditional static approaches and showed improvements in competency attainment, engagement, learning efficiency, and reduced dropout risk. Full article

► Show Figures

Graphical abstract

29 pages, 2351 KB

Open AccessArticle

Innovations in IT Recruitment: How Data Mining Is Redefining the Search for Best Talent (A Case Study of IT Recruitment in Morocco)

by Zakaria Rouaine, Soukaina Abdallah-Ou-Moussa and Martin Wynn

Information 2025, 16(10), 845; https://doi.org/10.3390/info16100845 - 30 Sep 2025

Abstract

The massive volumes of data and the intensification of digital transformation are reshaping recruitment practices within organizations, particularly for specialized information technology (IT) profiles. However, existing studies have often remained conceptual, focused on developed economies, or limited to a narrow set of factors, [...] Read more.

The massive volumes of data and the intensification of digital transformation are reshaping recruitment practices within organizations, particularly for specialized information technology (IT) profiles. However, existing studies have often remained conceptual, focused on developed economies, or limited to a narrow set of factors, thereby leaving important gaps in emerging contexts. Moreover, there are few studies that critically assess how Data Mining is impacting the IT recruitment process, and none that assess this in the context of Morocco. This study employs an extensive literature review to explore the role of Data Mining in facilitating the recruitment of top IT candidates, focusing on its ability to improve selection quality, reduce costs, and optimize decision-making procedures. The study provides empirical evidence from the Moroccan aeronautical and digital services sectors, an underexplored context where IT talent scarcity and rapid technological change pose critical challenges. Primary data comes from a survey of 200 IT recruitment professionals operating in these sectors in Morocco, allowing an assessment of the impact of Data Mining on IT talent acquisition initiatives. The findings reveal that a range of capabilities resulting from the application of Data Mining significantly and positively influences the success of IT recruitment processes. The novelty of the article lies in integrating six key determinants of algorithmic recruitment into a unified framework and demonstrating their empirical significance through binary logistic regression. The focus on the Moroccan context adds value to the international discussion and extends the literature on HR analytics beyond its conventional geographical and theoretical boundaries. The article thus contributes to the emerging literature on the role of digital technologies in IT recruitment that will be of interest to industry practitioners and other researchers in this field. Full article

(This article belongs to the Special Issue Machine Learning and Data Mining: Innovations in Big Data Analytics, 2nd Edition)

► Show Figures

Figure 1

24 pages, 5484 KB

Open AccessArticle

TFI-Fusion: Hierarchical Triple-Stream Feature Interaction Network for Infrared and Visible Image Fusion

by Mingyang Zhao, Shaochen Su and Hao Li

Information 2025, 16(10), 844; https://doi.org/10.3390/info16100844 - 30 Sep 2025

Abstract

As a key technology in multimodal information processing, infrared and visible image fusion holds significant application value in fields such as military reconnaissance, intelligent security, and autonomous driving. To address the limitations of existing methods, this paper proposes the Hierarchical Triple-Feature Interaction Fusion [...] Read more.

As a key technology in multimodal information processing, infrared and visible image fusion holds significant application value in fields such as military reconnaissance, intelligent security, and autonomous driving. To address the limitations of existing methods, this paper proposes the Hierarchical Triple-Feature Interaction Fusion Network (TFI-Fusion). Based on a hierarchical triple-stream feature interaction mechanism, the network achieves high-quality fusion through a two-stage, separate-model processing approach: In the first stage, a single model extracts low-rank components (representing global structural features) and sparse components (representing local detail features) from source images via the Low-Rank Sparse Decomposition (LSRSD) module, while capturing cross-modal shared features using the Shared Feature Extractor (SFE). In the second stage, another model performs fusion and reconstruction: it first enhances the complementarity between low-rank and sparse features through the innovatively introduced Bi-Feature Interaction (BFI) module, realizes multi-level feature fusion via the Triple-Feature Interaction (TFI) module, and finally generates fused images with rich scene representation through feature reconstruction. This separate-model design reduces memory usage and improves operational speed. Additionally, a multi-objective optimization function is designed based on the network’s characteristics. Experiments demonstrate that TFI-Fusion exhibits excellent fusion performance, effectively preserving image details and enhancing feature complementarity, thus providing reliable visual data support for downstream tasks. Full article

► Show Figures

Figure 1

23 pages, 1167 KB

Open AccessArticle

Integrating RAG for Smarter Animal Certification Platforms

by Pedro Bilar Montero, Jonas Bulegon Gassen, Glênio Descovi, Tais Oltramari Barnasque, Gabriel Rodrigues da Silva, Felipe Amadori Machado, Gabriel Vieira Casanova, Vinícius Maran and Alencar Machado

Information 2025, 16(10), 843; https://doi.org/10.3390/info16100843 - 30 Sep 2025

Abstract

Large Language Models (LLMs) encounter significant challenges when applied in specialized domains that require precise and localized information. This problem is particularly critical in regulatory sectors, such as the animal health sector in Brazil, where professionals depend on complex and constantly updated legal [...] Read more.

Large Language Models (LLMs) encounter significant challenges when applied in specialized domains that require precise and localized information. This problem is particularly critical in regulatory sectors, such as the animal health sector in Brazil, where professionals depend on complex and constantly updated legal norms to perform their work. The generic knowledge encapsulated in traditional LLMs is often insufficient to provide reliable support in these contexts, which can lead to inaccurate or outdated responses. To address this gap, this work presents a practical implementation of a Retrieval-Augmented Generation (RAG) system. We detail the integration of this system with the Plataforma de Defesa Sanitária Animal do Rio Grande do Sul (PDSA-RS), a real platform used for animal production certification. Our solution connects an LLM to an external knowledge base containing specific Brazilian legislation, allowing the model to retrieve relevant legal texts in real time to generate its responses. The principal objective is to demonstrate how this approach can produce accurate and contextually grounded answers for professionals in the veterinary field, assisting in decision-making processes for sanitary certification. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Graphical abstract

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