Information

14 pages, 2628 KB

Open AccessArticle

Artificial Intelligence and International Rules in Cyberspace: A Comparative Knowledge-Mapping Analysis

by Yajuan Liu and Zhi Li

Information 2025, 16(10), 842; https://doi.org/10.3390/info16100842 (registering DOI) - 29 Sep 2025

Considering the new technologies, trends, and geopolitical challenges brought about by the globalization of the Internet, research on international rules in cyberspace holds theoretical urgency, practical significance, and provides guidance for real-world applications. A comparative analysis of relevant papers on the international governance [...] Read more.

Considering the new technologies, trends, and geopolitical challenges brought about by the globalization of the Internet, research on international rules in cyberspace holds theoretical urgency, practical significance, and provides guidance for real-world applications. A comparative analysis of relevant papers on the international governance of cyberspace between 1999 and 2020 was conducted using the knowledge mapping tool CiteSpace in Chinese and English databases. The analysis revealed that Chinese research exhibits a stronger focus on national policies, with distinct characteristics at different stages of research. In contrast, English literature demonstrates a clear delineation of the theoretical foundation and maintains a continuous and in-depth exploration of foundational topics. While the field of communication in Chinese has a significantly higher quantity of research compared to English, there exists a structural gap between this field and its foundational theories. In the process of a paradigm shift, it is crucial to emphasize Chinese academic perspectives in this field, pay attention to both domestic and international foundational knowledge and emerging trends, and strengthen theoretical innovation and academic community-building. Full article

(This article belongs to the Special Issue Information Technology in Society)

► Show Figures

Figure 1

14 pages, 1094 KB

Open AccessReview

AI-Based Solutions for Security and Resource Optimization in IoT Environments: A Systematic Review

by Cosmin Alioanei and Nirvana Popescu

Information 2025, 16(10), 841; https://doi.org/10.3390/info16100841 (registering DOI) - 29 Sep 2025

Abstract

Nowadays, the rapid expansion of Internet of Things (IoT) systems has introduced significant challenges related to system management, especially in cybersecurity and resource efficiency areas. This systematic review investigates how AI/ML techniques are being applied to address these challenges, with a particular focus [...] Read more.

Nowadays, the rapid expansion of Internet of Things (IoT) systems has introduced significant challenges related to system management, especially in cybersecurity and resource efficiency areas. This systematic review investigates how AI/ML techniques are being applied to address these challenges, with a particular focus on intrusion detection systems, anomaly detection, and intelligent resource allocation. Using a structured methodology inspired by the PRISMA technique, relevant research articles published between 2018 and 2025 across important databases, including IEEE Xplore, ScienceDirect, SpringerLink, ResearchGate, and Web of Science, were analyzed and compared. The selected studies demonstrate that integrating granular perspectives in AI/ML-based solutions could enhance the resilience of IoT systems. This comprehensive review showed extremely interesting results for AI contributions in real life as well as potential advancements in this area by combining different perspectives in order to improve the security and efficiency of IoT systems. Full article

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

► Show Figures

Figure 1

22 pages, 1066 KB

Open AccessArticle

The Potential of Satellite Internet Technologies for Crisis Management During Urban Evacuation: A Case Study of Starlink in Italy

by Sina Shaffiee Haghshenas, Vittorio Astarita, Sami Shaffiee Haghshenas, Giulia Martino and Giuseppe Guido

Information 2025, 16(10), 840; https://doi.org/10.3390/info16100840 (registering DOI) - 28 Sep 2025

Abstract

This study examines the potential of satellite internet technologies to enhance crisis management in urban evacuation scenarios in Italy, with a specific focus on the Starlink system as a case study. In emergency situations, traditional mobile and WiFi networks often become inaccessible, significantly [...] Read more.

This study examines the potential of satellite internet technologies to enhance crisis management in urban evacuation scenarios in Italy, with a specific focus on the Starlink system as a case study. In emergency situations, traditional mobile and WiFi networks often become inaccessible, significantly impairing timely communication and coordination. Reliable connectivity is therefore imperative for effective rescue operations and public safety. This research analyzes how satellite-based internet can provide robust, uninterrupted connectivity even when conventional infrastructures fail. The study discusses operational advantages such as rapid deployment, broad coverage, and scalability during disasters, as well as key constraints including line-of-sight requirements, environmental sensitivity, and regulatory challenges. Empirical findings from the deployment of Starlink during an actual urban evacuation event in Italy indicate that latency dropped below 200 ms and sustained upload/download speeds averaged approximately 50 Mbps—up to three times faster than ground networks in disrupted zones. By evaluating both benefits and limitations, this paper provides a comprehensive understanding of the integration of satellite internet services within Italian emergency response systems, aiming to improve the performance of urban evacuation strategies. Full article

(This article belongs to the Special Issue Feature Papers in Information in 2024–2025)

► Show Figures

Figure 1

12 pages, 4847 KB

Open AccessArticle

Surformer v1: Transformer-Based Surface Classification Using Tactile and Vision Features

by Manish Kansana, Elias Hossain, Shahram Rahimi and Noorbakhsh Amiri Golilarz

Information 2025, 16(10), 839; https://doi.org/10.3390/info16100839 (registering DOI) - 27 Sep 2025

Abstract

Surface material recognition is a key component in robotic perception and physical interaction, particularly when leveraging both tactile and visual sensory inputs. In this work, we propose Surformer v1, a transformer-based architecture designed for surface classification using structured tactile features and Principal Component [...] Read more.

Surface material recognition is a key component in robotic perception and physical interaction, particularly when leveraging both tactile and visual sensory inputs. In this work, we propose Surformer v1, a transformer-based architecture designed for surface classification using structured tactile features and Principal Component Analysis (PCA)-reduced visual embeddings extracted via ResNet 50. The model integrates modality-specific encoders with cross-modal attention layers, enabling rich interactions between vision and touch. Currently, state-of-the-art deep learning models for vision tasks have achieved remarkable performance. With this in mind, our first set of experiments focused exclusively on tactile-only surface classification. Using feature engineering, we trained and evaluated multiple machine learning models, assessing their accuracy and inference time. We then implemented an encoder-only Transformer model tailored for tactile features. This model not only achieves the highest accuracy, but also demonstrated significantly faster inference time compared to other evaluated models, highlighting its potential for real-time applications. To extend this investigation, we introduced a multimodal fusion setup by combining vision and tactile inputs. We trained both Surformer v1 (using structured features) and a Multimodal CNN (using raw images) to examine the impact of feature-based versus image-based multimodal learning on classification accuracy and computational efficiency. The results showed that Surformer v1 achieved 99.4% accuracy with an inference time of 0.7271 ms, while the Multimodal CNN achieved slightly higher accuracy but required significantly more inference time. These findings suggest that Surformer v1 offers a compelling balance between accuracy, efficiency, and computational cost for surface material recognition. The results also underscore the effectiveness of integrating feature learning, cross-modal attention and transformer-based fusion in capturing the complementary strengths of tactile and visual modalities. Full article

(This article belongs to the Special Issue AI-Based Image Processing and Computer Vision)

► Show Figures

Figure 1

22 pages, 671 KB

Open AccessArticle

The Impact of the Organization on the Autonomy of Agents

by Zouheyr Tamrabet, Djamel Nessah, Toufik Marir, Varun Gupta and Farid Mokhati

Information 2025, 16(10), 838; https://doi.org/10.3390/info16100838 (registering DOI) - 27 Sep 2025

Abstract

In multi-agent systems (MAS), autonomy is a fundamental characteristic that enables agents to operate independently and adaptively within complex environments. However, such characteristics may cause the system to fall into undesirable situations. On the one hand, purely autonomous agents are difficult to predict. [...] Read more.

In multi-agent systems (MAS), autonomy is a fundamental characteristic that enables agents to operate independently and adaptively within complex environments. However, such characteristics may cause the system to fall into undesirable situations. On the one hand, purely autonomous agents are difficult to predict. On the other hand, fully controlled agents lose many of their abilities. Therefore, control frameworks have been designed in the form of organizational architectures to help address the need for balance between purely autonomous and fully controlled agents. This paper investigates the impact of organization on the autonomy of the agents. To measure this impact, we propose a set of seven metrics (Behavioral Wealth (BW), Service Wealth (SW), Frequency of Service Searches per Time (FoSST), Frequency of Service Searches per Behavior (FoSSB), Number of Service Searches (NoSS), Number of Service Demands per Behavior (NoSDB), and Number of Provided Services per Demand (NoPSD)) and apply them to a case study implemented in two configurations: with and without organizational aspects. To model organizational aspects, we adopt the Agent–Group–Role (AGR) model, chosen for its structured approach to defining agent responsibilities and interactions. The findings of this study show that the organizational aspects reduce the communication load and enhance the effectiveness of agents. Full article

► Show Figures

Figure 1

20 pages, 6308 KB

Open AccessArticle

An Intelligent Algorithm for the Optimal Deployment of Water Network Monitoring Sensors Based on Automatic Labelling and Graph Neural Network

by Guoxin Shi, Xianpeng Wang, Jingjing Zhang and Xinlei Gao

Information 2025, 16(10), 837; https://doi.org/10.3390/info16100837 (registering DOI) - 27 Sep 2025

Abstract

In order to enhance leakage detection accuracy in water distribution networks (WDNs) while reducing sensor deployment costs, an intelligent algorithm for the optimal deployment of water network monitoring sensors based on the automatic labelling and graph neural network (ALGN) was proposed for the [...] Read more.

In order to enhance leakage detection accuracy in water distribution networks (WDNs) while reducing sensor deployment costs, an intelligent algorithm for the optimal deployment of water network monitoring sensors based on the automatic labelling and graph neural network (ALGN) was proposed for the optimal deployment of WDN monitoring sensors. The research aims to develop a data-driven, topology-aware sensor deployment strategy that achieves high leakage detection performance with minimal hardware requirements. The methodology consisted of three main steps: first, the dung beetle optimization algorithm (DBO) was employed to automatically determine optimal parameters for the DBSCAN clustering algorithm, which generated initial cluster labels; second, a customized graph neural network architecture was used to perform topology-aware node clustering, integrating network structure information; finally, optimal pressure sensor locations were selected based on minimum distance criteria within identified clusters. The key innovation lies in the integration of metaheuristic optimization with graph-based learning to fully automate the sensor placement process while explicitly incorporating the hydraulic network topology. The proposed approach was validated on real-world WDN infrastructure, demonstrating superior performance with 93% node coverage and 99.77% leakage detection accuracy, surpassing state-of-the-art methods by 2% and 0.7%, respectively. These results indicate that the ALGN framework provides municipal water utilities with a robust, automated solution for designing efficient pressure monitoring systems that balance detection performance with implementation cost. Full article

► Show Figures

Figure 1

34 pages, 6187 KB

Open AccessArticle

An Automated Domain-Agnostic and Explainable Data Quality Assurance Framework for Energy Analytics and Beyond

by Balázs András Tolnai, Zhipeng Ma, Bo Nørregaard Jørgensen and Zheng Grace Ma

Information 2025, 16(10), 836; https://doi.org/10.3390/info16100836 - 26 Sep 2025

Abstract

Nonintrusive load monitoring (NILM) relies on high-resolution sensor data to disaggregate total building energy into end-use load components, for example HVAC, ventilation, and appliances. On the ADRENALIN corpus, simple NaN handling with forward fill and mean substitution reduced average NMAE from 0.82 to [...] Read more.

Nonintrusive load monitoring (NILM) relies on high-resolution sensor data to disaggregate total building energy into end-use load components, for example HVAC, ventilation, and appliances. On the ADRENALIN corpus, simple NaN handling with forward fill and mean substitution reduced average NMAE from 0.82 to 0.76 for the Bayesian baseline, from 0.71 to 0.64 for BI-LSTM, and from 0.59 to 0.53 for the Time–Frequency Mask (TFM) model, across nine buildings and four temporal resolutions. However, many NILM models still show degraded accuracy due to unresolved data-quality issues, especially missing values, timestamp irregularities, and sensor inconsistencies, a limitation underexplored in current benchmarks. This paper presents a fully automated data-quality assurance pipeline for time-series energy datasets. The pipeline performs multivariate profiling, statistical analysis, and threshold-based diagnostics to compute standardized quality metrics, which are aggregated into an interpretable Building Quality Score (BQS) that predicts NILM performance and supports dataset ranking and selection. Explainability is provided by SHAP and a lightweight large language model, which turns visual diagnostics into concise, actionable narratives. The study evaluates practical quality improvement through systematic handling of missing values, linking metric changes to downstream error reduction. Using random-forest surrogates, SHAP identifies missingness and timestamp irregularity as dominant drivers of error across models. Core contributions include the definition and validation of BQS, an interpretable scoring and explanation framework for time-series quality, and an end-to-end evaluation of how quality diagnostics affect NILM performance at scale. Full article

(This article belongs to the Special Issue Artificial Intelligence and Data Science for Smart Cities)

► Show Figures

Figure 1

27 pages, 1665 KB

Open AccessArticle

Obstacle-Aware Charging Pad Deployment in Large-Scale WRSNs: An Outside-to-Inside Onion-Peeling-like Strategy

by Rei-Heng Cheng, Yuan-Yu Hsu and Chang Wu Yu

Information 2025, 16(10), 835; https://doi.org/10.3390/info16100835 (registering DOI) - 26 Sep 2025

Abstract

This paper addresses the critical challenge of deploying a minimum number of wireless charging pads (WCPs) in obstacle-rich, large-scale Wireless Rechargeable Sensor Networks (WRSNs) to sustain drone operations. We assume a single base station, stationary sensors, convex polygonal obstacles that drones must avoid, [...] Read more.

This paper addresses the critical challenge of deploying a minimum number of wireless charging pads (WCPs) in obstacle-rich, large-scale Wireless Rechargeable Sensor Networks (WRSNs) to sustain drone operations. We assume a single base station, stationary sensors, convex polygonal obstacles that drones must avoid, and that both the base station and WCPs provide unlimited energy. To solve this, we propose the Outside-to-Inside Onion-Peeling (OIOP) strategy, a novel two-stage algorithm that prioritizes the coverage of the most remote sensors first and then refines the deployment by removing redundant pads while strictly adhering to obstacle constraints. Simulation results demonstrate OIOP’s superior efficiency: it reduces the number of required pads by approximately 10.83% ± 1.30% and 12.16% ± 1.59% compared to state-of-the-art methods (SMC and MC) and achieves execution times that are 58.02% ± 2.44% and 72.09% ± 2.88% faster, respectively. The algorithm also exhibits remarkable robustness, showing the smallest performance degradation as obstacle density increases. Full article

(This article belongs to the Special Issue Optimization Algorithms and Their Applications)

► Show Figures

Graphical abstract

19 pages, 5381 KB

Open AccessArticle

Context_Driven Emotion Recognition: Integrating Multi_Cue Fusion and Attention Mechanisms for Enhanced Accuracy on the NCAER_S Dataset

by Merieme Elkorchi, Boutaina Hdioud, Rachid Oulad Haj Thami and Safae Merzouk

Information 2025, 16(10), 834; https://doi.org/10.3390/info16100834 - 26 Sep 2025

Abstract

In recent years, most conventional emotion recognition approaches have concentrated primarily on facial cues, often overlooking complementary sources of information such as body posture and contextual background. This limitation reduces their effectiveness in complex, real-world environments. In this work, we present a multi-branch [...] Read more.

In recent years, most conventional emotion recognition approaches have concentrated primarily on facial cues, often overlooking complementary sources of information such as body posture and contextual background. This limitation reduces their effectiveness in complex, real-world environments. In this work, we present a multi-branch emotion recognition framework that separately processes facial, bodily, and contextual information using three dedicated neural networks. To better capture contextual cues, we intentionally mask the face and body of the main subject within the scene, prompting the model to explore alternative visual elements that may convey emotional states. To further enhance the quality of the extracted features, we integrate both channel and spatial attention mechanisms into the network architecture. Evaluated on the challenging NCAER-S dataset, our model achieves an accuracy of 56.42%, surpassing the state-of-the-art GLAMOUR-Net. These results highlight the effectiveness of combining multi-cue representation and attention-guided feature extraction for robust emotion recognition in unconstrained settings. The findings also highlight the importance of accurate emotion recognition for human–computer interaction, where affect detection enables systems to adapt to users and deliver more effective experiences. Full article

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

► Show Figures

Figure 1

16 pages, 778 KB

Open AccessArticle

A Framework for Evaluating the Reliability of Health Monitoring Technologies Based on Ambient Intelligence

by Mfundo Shakes Scott, Nobert Jere, Khulumani Sibanda and Ibomoiye Domor Mienye

Information 2025, 16(10), 833; https://doi.org/10.3390/info16100833 - 26 Sep 2025

Abstract

The reliability of health monitoring technologies has become increasingly critical as Ambient Intelligence (AmI) becomes integrated into healthcare. However, a significant gap remains in systematically evaluating reliability, particularly in resource-constrained environments. This study addresses this gap by introducing a comprehensive framework specifically designed [...] Read more.

The reliability of health monitoring technologies has become increasingly critical as Ambient Intelligence (AmI) becomes integrated into healthcare. However, a significant gap remains in systematically evaluating reliability, particularly in resource-constrained environments. This study addresses this gap by introducing a comprehensive framework specifically designed to evaluate the reliability of AmI-based health monitoring systems. The proposed framework combines robust simulation-based techniques, including reliability block diagrams (RBDs) and Monte Carlo Markov Chain (MCMC), to evaluate system robustness, data integrity, and adaptability. Validation was performed using real-world continuous glucose monitoring (CGM) and heart rate monitoring (HRM) systems in elderly care. The results demonstrate that the framework successfully identifies critical vulnerabilities, such as rapid initial system degradation and notable connectivity disruptions, and effectively guides targeted interventions that significantly enhance overall system reliability and user trust. The findings contribute actionable insights for practitioners, developers, and policymakers, laying a robust foundation for further advancements in explainable AI, proactive reliability management, and broader applications of AmI technologies in healthcare. Full article

(This article belongs to the Special Issue Artificial Intelligence and Data Science for Health, 2nd Edition)

► Show Figures

Figure 1

16 pages, 3013 KB

Open AccessArticle

Boosting LiDAR Point Cloud Object Detection via Global Feature Fusion

by Xu Zhang, Fengchang Tian, Jiaxing Sun and Yan Liu

Information 2025, 16(10), 832; https://doi.org/10.3390/info16100832 - 26 Sep 2025

Abstract

To address the limitation of receptive fields caused by the use of local convolutions in current point cloud object detection methods, this paper proposes a LiDAR point cloud object detection algorithm that integrates global features. The proposed method employs a Voxel Mapping Block [...] Read more.

To address the limitation of receptive fields caused by the use of local convolutions in current point cloud object detection methods, this paper proposes a LiDAR point cloud object detection algorithm that integrates global features. The proposed method employs a Voxel Mapping Block (VMB) and a Global Feature Extraction Block (GFEB) to convert the point cloud data into a one-dimensional long sequence. It then utilizes non-local convolutions to model the entire voxelized point cloud and incorporate global contextual information, thereby enhancing the network’s receptive field and its capability to extract and learn global features. Furthermore, a Voxel Channel Feature Extraction (VCFE) module is designed to capture local spatial information by associating features across different channels, effectively mitigating the spatial information loss introduced during the one-dimensional transformation. The experimental results demonstrate that, compared with state-of-the-art methods, the proposed approach improves the average precision of vehicle, pedestrian, and cyclist targets on the Waymo subset by 0.64%, 0.71%, and 0.66%, respectively. On the nuScenes dataset, the detection accuracy for var targets increased by 0.7%, with NDS and mAP improving by 0.3% and 0.5%, respectively. In particular, the method exhibits outstanding performance in small object detection, significantly enhancing the overall accuracy of point cloud object detection. Full article

► Show Figures

Figure 1

19 pages, 1025 KB

Open AccessArticle

Research on Trade Credit Risk Assessment for Foreign Trade Enterprises Based on Explainable Machine Learning

by Mengjie Liao, Wanying Jiao and Jian Zhang

Information 2025, 16(10), 831; https://doi.org/10.3390/info16100831 - 26 Sep 2025

Abstract

As global economic integration deepens, import and export trade plays an increasingly vital role in China’s economy. To enhance regulatory efficiency and achieve scientific, transparent credit supervision, this study proposes a trade credit risk evaluation model based on interpretable machine learning, incorporating loss [...] Read more.

As global economic integration deepens, import and export trade plays an increasingly vital role in China’s economy. To enhance regulatory efficiency and achieve scientific, transparent credit supervision, this study proposes a trade credit risk evaluation model based on interpretable machine learning, incorporating loss preferences. Key risk features are identified through a comprehensive interpretability framework combining SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), forming an optimal feature subset. Using Light Gradient Boosting Machine (LightGBM) as the base model, a weight adjustment strategy is introduced to reduce costly misclassification of high-risk enterprises, effectively improving their recognition rate. However, this adjustment leads to a decline in overall accuracy. To address this trade-off, a Bagging ensemble framework is applied, which restores and slightly improves accuracy while maintaining low misclassification costs. Experimental results demonstrate that the interpretability framework improves transparency and business applicability, the weight adjustment strategy enhances high-risk enterprise detection, and Bagging balances the overall classification performance. The proposed method ensures reliable identification of high-risk enterprises while preserving overall model robustness, thereby providing strong practical value for enterprise credit risk assessment and decision-making. Full article

► Show Figures

Figure 1

26 pages, 2055 KB

Open AccessArticle

The Role of Sociodemographic Variables in Game Type, Hardware Preference, Awareness and Level of Involvement

by Maica Amador-Marrero and Gonzalo Díaz-Meneses

Information 2025, 16(10), 830; https://doi.org/10.3390/info16100830 - 24 Sep 2025

Viewed by 54

Abstract

Video games have become one of the most influential digital entertainment platforms. They offer advertisers new opportunities through in-game placements. This study examines the relationship between the socio-demographic characteristics of gamers (gender, age, education and income) and the placement of video game advertising. [...] Read more.

Video games have become one of the most influential digital entertainment platforms. They offer advertisers new opportunities through in-game placements. This study examines the relationship between the socio-demographic characteristics of gamers (gender, age, education and income) and the placement of video game advertising. Specifically, it analyses the relationship between these variables on five key dimensions: the type of video games played, the choice of gaming hardware, awareness of advertising placement, the type of advertising perceived and the level of involvement with the brands advertised. Despite the growing relevance of in-game advertising as a non-intrusive and immersive strategy, empirical evidence in this field remains scarce. A non-probability sampling survey was conducted with 317 respondents. Data were analysed using Exploratory Factor Analysis (EFA), Student’s t-tests and ANOVA. The results reveal statistically significant differences by gender, age and education in the types of video games played. Awareness of advertising placement is higher among young people with secondary education. Involvement with the brand increases with age, especially among millennials. No significant differences were found in relation to income, except for the choice of hardware. These findings advance understanding of how socio-demographics shape gamer involvement with in-game advertising. The study provides both theoretical contributions and practical implications for developers, 3D designers and marketers. Full article

(This article belongs to the Section Information and Communications Technology)

► Show Figures

Graphical abstract

15 pages, 1591 KB

Open AccessArticle

Mathematical Analysis of Page Fault Minimization for Virtual Memory Systems Using Working Set Strategy

by Aslanbek Murzakhmetov, Gaukhar Borankulova, Arseniy Bapanov and Gabit Altybayev

Information 2025, 16(10), 829; https://doi.org/10.3390/info16100829 - 24 Sep 2025

Viewed by 47

Abstract

Poor code locality in virtual memory systems significantly contributes to page faults, leading to degraded system performance. Although many solutions aim to minimize page faults, most rely on clustering techniques that do not quantify the approximation error relative to the optimal solution. In [...] Read more.

Poor code locality in virtual memory systems significantly contributes to page faults, leading to degraded system performance. Although many solutions aim to minimize page faults, most rely on clustering techniques that do not quantify the approximation error relative to the optimal solution. In this work, we develop a novel mathematical model based on the Working Set strategy combined with a geometric interpretation of the computational process via a Hasse diagram. This approach enables the reduction of the problem dimensionality and facilitates identification of critical control states under realistic constraints. We formalize the minimization of expected page faults as a discrete optimization problem with well-defined functionals and constraints. Experimental evaluation demonstrates that our model achieves lower average page faults and execution times compared to classical algorithms, especially under poor code locality conditions. Our method also provides a foundation for obtaining ε-optimal solutions and paves the way for designing efficient and cost-effective page replacement algorithms with provable guarantees. These contributions establish both theoretical and practical advances in virtual memory management. Full article

► Show Figures

Figure 1

26 pages, 2781 KB

Open AccessArticle

Iterative Optimization of Structural Entropy for Enhanced Network Fragmentation Analysis

by Fatih Ozaydin, Vasily Lubashevskiy and Seval Yurtcicek Ozaydin

Information 2025, 16(10), 828; https://doi.org/10.3390/info16100828 - 24 Sep 2025

Viewed by 47

Abstract

Identifying and ranking influential nodes is central to tasks such as targeted immunization, misinformation containment, and resilient design. Structural entropy (SE) offers a principled, community-aware scoring rule, yet the one-shot (static) use of SE may become suboptimal after each intervention, as the residual [...] Read more.

Identifying and ranking influential nodes is central to tasks such as targeted immunization, misinformation containment, and resilient design. Structural entropy (SE) offers a principled, community-aware scoring rule, yet the one-shot (static) use of SE may become suboptimal after each intervention, as the residual topology and its modular structure change. We introduce iterative structural entropy (ISE), a simple yet powerful modification that recomputes SE on the residual graph before every removal, thus turning node targeting into a sequential, feedback-driven policy. We evaluate SE and ISE on seven benchmark networks using (i) cumulative structural entropy (CSE), (ii) cumulative sum of largest connected component sizes (LCCs), and (iii) dynamic panels that track average shortest-path length and diameter within the residual LCC together with a near-threshold percolation proxy (expected outbreak size). Across datasets, ISE consistently fragments earlier and more decisively than SE; on the Netscience network, ISE reduces the cumulative LCC size by

43 %

(RLCCs

= 0.567

). In parallel, ISE achieves perfect discriminability (monotonicity

M = 1.0

) among positively scored nodes on all benchmarks, while SE and degree-based baselines display method-dependent ties. These results support ISE as a practical, adaptive alternative to static SE when sequential decisions matter, delivering sharper rankings and faster structural degradation under identical measurement protocols. Full article

(This article belongs to the Special Issue Optimization Algorithms and Their Applications)

► Show Figures

Figure 1

16 pages, 4919 KB

Open AccessArticle

SCRATCH-AI: A Tool to Predict Honey Wound Healing Properties

by Simona Martinotti, Stefania Montani, Elia Ranzato and Manuel Striani

Information 2025, 16(10), 827; https://doi.org/10.3390/info16100827 - 24 Sep 2025

Viewed by 67

Abstract

In this work, we propose SCRATCH-AI, a tool which relies on interpretable machine learning (ML) methods (namely, Bayesian networks and decision trees) to classify honey samples into wound healing categories. Classification explores the impact of botanical origins (i.e., honey type) and key chemical–biological [...] Read more.

In this work, we propose SCRATCH-AI, a tool which relies on interpretable machine learning (ML) methods (namely, Bayesian networks and decision trees) to classify honey samples into wound healing categories. Classification explores the impact of botanical origins (i.e., honey type) and key chemical–biological characteristics such as antioxidant activity on healing, assessed through wound recovery metrics. The obtained classification performance results are very encouraging. Moreover, the models provide non-trivial insights about the causal dependencies of some specific honey features on wound healing properties and show the effect of different honey types (other than the well known Manuka) on cicatrization. The tool is inherently interpretable (due to the chosen ML techniques) and made user-friendly by a carefully designed graphical interface. We believe that the information provided by our tool will allow biologists and clinicians to better utilize honey, with the ultimate goal of leveraging honey capability to accelerate healing and reduce infection risks in clinical practice. Full article

(This article belongs to the Special Issue Artificial Intelligence and Decision Support Systems)

► Show Figures

Graphical abstract

21 pages, 1308 KB

Open AccessArticle

A Record–Replay-Based State Recovery Approach for Variants in an MVX System

by Xu Zhong, Xinjian Zhao, Bo Zhang, June Li, Yifan Wang and Yu Li

Information 2025, 16(10), 826; https://doi.org/10.3390/info16100826 - 24 Sep 2025

Viewed by 51

Abstract

Multi-variant execution (MVX) is an active defense technique that can detect unknown attacks by comparing the outputs of redundant program variants. Despite notable progress in MVX techniques in recent years, current approaches for recovery of abnormal variants still face fundamental challenges, including state [...] Read more.

Multi-variant execution (MVX) is an active defense technique that can detect unknown attacks by comparing the outputs of redundant program variants. Despite notable progress in MVX techniques in recent years, current approaches for recovery of abnormal variants still face fundamental challenges, including state inconsistency, low recovery efficiency, and service disruption of an MVX system. Therefore, a record–replay-based state recovery approach for variants in MVX systems is proposed in this paper. First, a Syscall Coordinator (SSC), composed of a recording module, a classification module, and a replay module, is designed to enable state recovery of variants. Then, a synchronization and voting algorithm is presented. When an anomaly is identified through voting, the abnormal variant is handed over to the SSC for state recovery, while the Synchronization Queue is updated accordingly. Furthermore, to ensure uninterrupted system service, we introduce a parallel grouped recovery mechanism, which enables the execution of normal variants and the recovery of abnormal variants to run in parallel. Experimental results on SPEC CPU 2006 benchmark and server applications show that the proposed approach achieves low overhead in both the recording and replay phases while maintaining high state recovery accuracy and supports uninterrupted system service. Full article

(This article belongs to the Section Information Systems)

► Show Figures

Figure 1

24 pages, 1175 KB

Open AccessArticle

EU Digital Communication in Times of Hybrid Warfare: The Case of Russia and Ukraine on X

by Raquel Ruiz-Incertis and Jorge Tuñón-Navarro

Information 2025, 16(10), 825; https://doi.org/10.3390/info16100825 - 24 Sep 2025

Viewed by 61

Abstract

Russia’s full-scale invasion of Ukraine in late February 2022 triggered a series of dramatic events with both humanitarian and informational repercussions. In this context, social media became saturated with rhetorical strategies and narrative framing from civil society, European media, and EU institutions alike. [...] Read more.

Russia’s full-scale invasion of Ukraine in late February 2022 triggered a series of dramatic events with both humanitarian and informational repercussions. In this context, social media became saturated with rhetorical strategies and narrative framing from civil society, European media, and EU institutions alike. This paper examines how the European Union communicated institutionally during the first year of the war, focusing on the online activity of the three main EU bodies—the European Commission, the European Parliament, and the European Council—and their respective presidents: Ursula von der Leyen, Roberta Metsola, and Charles Michel. The study centres on their use of the social media platform X (formerly Twitter), analysing the content of their posts related to the conflict. In addition, several in-depth interviews were conducted with experts in EU institutional communication and disinformation on social media to complement the analysis and offer a broader perspective on the communicative strategies employed. Full article

(This article belongs to the Special Issue Digital Technologies for Communication in the Age of AI)

► Show Figures

Figure 1

17 pages, 7481 KB

Open AccessArticle

A Real-Time Advisory Tool for Supporting the Use of Helmets in Construction Sites

by Ümit Işıkdağ, Handan Aş Çemrek, Seda Sönmez, Yaren Aydın, Gebrail Bekdaş and Zong Woo Geem

Information 2025, 16(10), 824; https://doi.org/10.3390/info16100824 - 24 Sep 2025

Viewed by 62

Abstract

In the construction industry, occupational health and safety plays a critical role in preventing occupational accidents and increasing productivity. In recent years, computer vision and artificial intelligence-based systems have made significant contributions to improving these processes through automatic detection and tracking of objects. [...] Read more.

In the construction industry, occupational health and safety plays a critical role in preventing occupational accidents and increasing productivity. In recent years, computer vision and artificial intelligence-based systems have made significant contributions to improving these processes through automatic detection and tracking of objects. The aim of this study was to fine-tune object detection models and integrate them with Large Language Models for (i). accurate detection of personal protective equipment (PPE) by specifically focusing on helmets and (ii). providing real-time recommendations based on the detections for supporting the use of helmets in construction sites. For achieving the first objective of the study, large YOLOv8/v11/v12 models were trained using a helmet dataset consisting of 16,867 images. The dataset was divided into two classes: “Head (No Helmet)” and “Helmet”. The model, once trained, was able to analyze an image from a construction site and detect and count the people with and without helmets. A tool with the aim of providing advice to workers in real time was developed to fulfil the second objective of the study. The developed tool provides the counts of the people based on video feeds or analyzing a series of images and provides recommendations on occupational safety (based on the detections from the video feed and images) through an OpenAI GPT-3.5-turbo Large Language Model and with a Streamlit-based GUI. The use of YOLO enables quick and accurate detections; in addition, the use of the OpenAI model API serves the exact same purpose. The combination of the YOLO model and OpenAI model API enables near-real-time responses to the user over the web. The paper elaborates on the fine tuning of the detection model with the helmet dataset and the development of the real-time advisory tool. Full article

► Show Figures

Figure 1

18 pages, 531 KB

Open AccessReview

The Black Box Paradox: AI Models and the Epistemological Crisis in Motor Control Research

by Nuno Dias, Liliana Pinho, Sandra Silva, Marta Freitas, Vânia Figueira and Francisco Pinho

Information 2025, 16(10), 823; https://doi.org/10.3390/info16100823 - 24 Sep 2025

Viewed by 63

Abstract

The widespread adoption of deep learning (DL) models in neuroscience research has introduced a fundamental epistemological paradox: while these models demonstrate remarkable performance in pattern recognition and prediction tasks, their inherent opacity contradicts neuroscience’s foundational goal of understanding biological mechanisms. This review article [...] Read more.

The widespread adoption of deep learning (DL) models in neuroscience research has introduced a fundamental epistemological paradox: while these models demonstrate remarkable performance in pattern recognition and prediction tasks, their inherent opacity contradicts neuroscience’s foundational goal of understanding biological mechanisms. This review article examines the growing trend of using DL models to interpret neural dynamics and extract insights about brain function, arguing that the black box nature of these models fundamentally undermines their utility for mechanistic understanding. We explore the distinction between computational performance and scientific explanation, analyze the limitations of current interpretability techniques, and discuss the implications for neuroscience research methodology. We propose that the field must critically evaluate whether DL models can genuinely contribute to our understanding of neural processes or whether they merely provide sophisticated curve-fitting tools that obscure rather than illuminate the underlying biology. Full article

► Show Figures

Figure 1

22 pages, 1250 KB

Open AccessArticle

Entity Span Suffix Classification for Nested Chinese Named Entity Recognition

by Jianfeng Deng, Ruitong Zhao, Wei Ye and Suhong Zheng

Information 2025, 16(10), 822; https://doi.org/10.3390/info16100822 - 23 Sep 2025

Viewed by 183

Abstract

Named entity recognition (NER) is one of the fundamental tasks in building knowledge graphs. For some domain-specific corpora, the text descriptions exhibit limited standardization, and some entity structures have entity nesting. The existing entity recognition methods have problems such as word matching noise [...] Read more.

Named entity recognition (NER) is one of the fundamental tasks in building knowledge graphs. For some domain-specific corpora, the text descriptions exhibit limited standardization, and some entity structures have entity nesting. The existing entity recognition methods have problems such as word matching noise interference and difficulty in distinguishing different entity labels for the same character in sequence label prediction. This paper proposes a span-based feature reuse stacked bidirectional long short term memory network (BiLSTM) nested named entity recognition (SFRSN) model, which transforms the entity recognition of sequence prediction into the problem of entity span suffix category classification. Firstly, character feature embedding is generated through bidirectional encoder representation of transformers (BERT). Secondly, a feature reuse stacked BiLSTM is proposed to obtain deep context features while alleviating the problem of deep network degradation. Thirdly, the span feature is obtained through the dilated convolution neural network (DCNN), and at the same time, a single-tail selection function is introduced to obtain the classification feature of the entity span suffix, with the aim of reducing the training parameters. Fourthly, a global feature gated attention mechanism is proposed, integrating span features and span suffix classification features to achieve span suffix classification. The experimental results on four Chinese-specific domain datasets demonstrate the effectiveness of our approach: SFRSN achieves micro-F1 scores of 83.34% on ontonotes, 73.27% on weibo, 96.90% on resume, and 86.77% on the supply chain management dataset. This represents a maximum improvement of 1.55%, 4.94%, 2.48%, and 3.47% over state-of-the-art baselines, respectively. The experimental results demonstrate the effectiveness of the model in addressing nested entities and entity label ambiguity issues. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Information, Volume 16, Issue 10 (October 2025) – 21 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI