Information

27 pages, 19258 KiB

Open AccessArticle

A Lightweight Multi-Frequency Feature Fusion Network with Efficient Attention for Breast Tumor Classification in Pathology Images

by Hailong Chen, Qingqing Song and Guantong Chen

Information 2025, 16(7), 579; https://doi.org/10.3390/info16070579 (registering DOI) - 6 Jul 2025

Abstract

The intricate and complex tumor cell morphology in breast pathology images is a key factor for tumor classification. This paper proposes a lightweight breast tumor classification model with multi-frequency feature fusion (LMFM) to tackle the problem of inadequate feature extraction and poor classification [...] Read more.

The intricate and complex tumor cell morphology in breast pathology images is a key factor for tumor classification. This paper proposes a lightweight breast tumor classification model with multi-frequency feature fusion (LMFM) to tackle the problem of inadequate feature extraction and poor classification performance. The LMFM utilizes wavelet transform (WT) for multi-frequency feature fusion, integrating high-frequency (HF) tumor details with high-level semantic features to enhance feature representation. The network’s ability to extract irregular tumor characteristics is further reinforced by dynamic adaptive deformable convolution (DADC). The introduction of the token-based Region Focus Module (TRFM) reduces interference from irrelevant background information. At the same time, the incorporation of a linear attention (LA) mechanism lowers the model’s computational complexity and further enhances its global feature extraction capability. The experimental results demonstrate that the proposed model achieves classification accuracies of 98.23% and 97.81% on the BreaKHis and BACH datasets, with only 9.66 M parameters. Full article

(This article belongs to the Section Biomedical Information and Health)

► Show Figures

Figure 1

26 pages, 1170 KiB

Open AccessArticle

Digital Empowerment, Novel Productive Forces, and Regional Green Innovation Efficiency: Causal Inference Based on Spatial Difference-in-Differences and Double Machine Learning Approaches

by Qi Liu, Siyu Liu, Tianning Guan, Luhan Yu, Zemenghong Bao, Yuzhu Wen and Kun Lv

Information 2025, 16(7), 578; https://doi.org/10.3390/info16070578 (registering DOI) - 6 Jul 2025

Abstract

Amidst the dual challenges of escalating ecological environmental pressures and economic transformation globally, green innovation emerges as a pivotal pathway toward achieving high-quality sustainable development. To elucidate how digitalization and novel productive forces synergistically drive the green transition, the research utilizes panel data [...] Read more.

Amidst the dual challenges of escalating ecological environmental pressures and economic transformation globally, green innovation emerges as a pivotal pathway toward achieving high-quality sustainable development. To elucidate how digitalization and novel productive forces synergistically drive the green transition, the research utilizes panel data from 30 provincial-level administrative regions in China spanning 2009 to 2022, constructing a green innovation efficiency measurement frame-work grounded in the Super Slack-Based Measure (Super-SBM)model, alongside a novel productive forces evaluation system based on the triad of laborers, labor objects, and means of production. Employing spatial difference-in-differences and double machine learning methodologies within a quasi-natural experimental design, the research investigates the causal mechanisms through which digital empowerment and novel productive forces influence regional green innovation efficiency. The findings reveal that both digital empowerment and novel productive forces significantly enhance regional green innovation efficiency, exhibiting pronounced positive spatial spillover effects on neighboring regions. Heterogeneity analyses demonstrate that the promotive impacts are more pronounced in eastern provinces compared to central and western counterparts, in provinces participating in carbon trading relative to those that do not, and in innovation-driven provinces versus non-innovative ones. Mediation analysis indicates that digital empowerment operates by fostering the aggregation of innovative talent and elevating governmental ecological attentiveness, whereas new-type productivity exerts its influence primarily through intellectual property protection and the clustering of high-technology industries. The results offer empirical foundations for policymakers to devise coordinated regional green development strategies, refine digital transformation policies, and promote industrial structural optimization. Furthermore, this research provides valuable data-driven insights and theoretical guidance for local governments and enterprises in cultivating green innovation and new-type productivity. Full article

(This article belongs to the Special Issue Carbon Emissions Analysis by AI Techniques)

► Show Figures

Figure 1

25 pages, 849 KiB

Open AccessArticle

Blockchain Adoption or Not? Analysis of Demand Information Sharing in Maritime Supply Chain

by Zongbao Zou, Cong Wang and Lihao Chen

Information 2025, 16(7), 577; https://doi.org/10.3390/info16070577 (registering DOI) - 4 Jul 2025

Abstract

This study examines whether adopting blockchain technology can enhance maritime supply chain performance by improving information sharing in the presence of mismatches between service capacity and demand. We analyze a maritime supply chain with one port and one carrier. Depending on whether the [...] Read more.

This study examines whether adopting blockchain technology can enhance maritime supply chain performance by improving information sharing in the presence of mismatches between service capacity and demand. We analyze a maritime supply chain with one port and one carrier. Depending on whether the port and the carrier adopt blockchain technology to share forecast information, we consider two scenarios: neither party adopts the technology, or both the port and the carrier adopt it. We find that when the port’s ex ante expected demand is relatively low, the adoption of blockchain technology not only incentivizes the port to expand its service capacity but also increases the actual demand from the carrier. In addition, when the port has a high forecasting accuracy, it prompts both the port and the carrier to make more stable decisions on the service capacity and freight rates under demand uncertainty. Finally, while the port and the carrier exhibit conflicting incentives to adopt blockchain technology, these tensions can nonetheless be reconciled. This alignment becomes possible due to blockchain’s spillover effect: by enabling information sharing, it facilitates a closer match between the port’s service capacity and the carrier’s realized demand. Full article

17 pages, 246 KiB

Open AccessArticle

The Impact of Information Acquisition on Farmers’ Drought Responses: Evidence from China

by Huiqing Han, Jianqiang Yang and Yingjia Zhang

Information 2025, 16(7), 576; https://doi.org/10.3390/info16070576 (registering DOI) - 4 Jul 2025

Abstract

Climate change presents major challenges to agriculture, especially in economically underdeveloped regions. In these areas, farmers often lack access to resources and timely information, which limits their ability to respond effectively to drought and threatens agricultural sustainability. This study uses survey data from [...] Read more.

Climate change presents major challenges to agriculture, especially in economically underdeveloped regions. In these areas, farmers often lack access to resources and timely information, which limits their ability to respond effectively to drought and threatens agricultural sustainability. This study uses survey data from farmers in underdeveloped regions of China to examine the association between their ability to acquire information and their drought response behaviors. The results indicate that better information acquisition ability is significantly correlated with more effective and scientifically informed decision-making in drought adaptation strategies. To explore the underlying mechanism, we introduce value perception—that is, farmers’ beliefs about the usefulness and benefits of drought adaptation strategies—as a mediating variable. A mechanism model is constructed to test how information acquisition ability relates to behavior indirectly through this perception. We apply a threshold regression model to identify potential nonlinear associations, finding that the relationship between information acquisition ability and drought response behaviors becomes stronger once a certain threshold is surpassed. Additionally, we employ the Item Response Theory (IRT) model to measure the intensity and quality of farmers’ adaptation behaviors more accurately. These findings provide theoretical insights and empirical evidence for enhancing agricultural resilience, while acknowledging that causality cannot be definitively established due to the cross-sectional nature of the data. The study also offers useful guidance for policymakers seeking to strengthen farmers’ access to information, improve value recognition of adaptive actions, and promote sustainable agricultural development in underdeveloped areas. Full article

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

27 pages, 2954 KiB

Open AccessArticle

Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network

by Bo Wang, Qiming Fu, You Lu and Ke Liu

Information 2025, 16(7), 575; https://doi.org/10.3390/info16070575 (registering DOI) - 4 Jul 2025

Abstract

Building energy consumption prediction (BECP) is the essential foundation for attaining energy efficiency in buildings, contributing significantly to tackling global energy challenges and facilitating energy sustainability. However, while data-driven methods have emerged as a crucial method to solving this complex problem, the limited [...] Read more.

Building energy consumption prediction (BECP) is the essential foundation for attaining energy efficiency in buildings, contributing significantly to tackling global energy challenges and facilitating energy sustainability. However, while data-driven methods have emerged as a crucial method to solving this complex problem, the limited availability of data presents a significant challenge to model training. To address this challenge, this paper presents an innovative method, named Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network (LRTL-AtTCN). LRTL-AtTCN integrates the attention mechanism with temporal convolutional network (TCN), improving the ability of extracting global and local dependencies. Moreover, LRTL-AtTCN combines low-rank decomposition, reducing the number of parameters during the transfer learning process with similar buildings, which can achieve better transfer performance in the limited data case. Experimentally, we conduct a comprehensive evaluation across three forecasting horizons—1 week, 2 weeks, and 1 month. Compared to the horizon-matched baseline, LRTL-AtTCN cuts the MAE by 91.2%, 30.2%, and 26.4%, respectively, and lifts the 1-month R² from 0.8188 to 0.9286. On every horizon it also outperforms state-of-the-art transfer-learning methods, confirming its strong generalization and transfer capability in BECP. Full article

(This article belongs to the Special Issue AI Applications in Construction and Infrastructure)

18 pages, 3451 KiB

Open AccessArticle

Switched 32-Bit Fixed-Point Format for Laplacian-Distributed Data

by Bojan Denić, Zoran Perić, Milan Dinčić, Sofija Perić, Nikola Simić and Marko Anđelković

Information 2025, 16(7), 574; https://doi.org/10.3390/info16070574 - 4 Jul 2025

Abstract

The 32-bit floating-point (FP32) format has many useful applications, particularly in computing and neural network systems. The classic 32-bit fixed-point (FXP32) format often introduces lower quality of representation (i.e., precision), making it unsuitable for real deployment, despite offering faster computations and reduced computational [...] Read more.

The 32-bit floating-point (FP32) format has many useful applications, particularly in computing and neural network systems. The classic 32-bit fixed-point (FXP32) format often introduces lower quality of representation (i.e., precision), making it unsuitable for real deployment, despite offering faster computations and reduced computational cost, which positively impacts energy efficiency. In this paper, we propose a switched FXP32 format able to compete with or surpass the widely used FP32 format across a wide variance range. It actually proposes switching between the possible values of key parameters according to the variance level of the data modeled with the Laplacian distribution. Precision analysis is achieved using the signal-to-quantization noise ratio (SQNR) as a performance metric, introduced based on the analogy between digital formats and quantization. Theoretical SQNR results provided in a wide range of variance confirm the design objectives. Experimental and simulation results obtained using neural network weights further support the approach. The strong agreement between the experiment, simulation, and theory indicates the efficiency of this proposal in encoding Laplacian data, as well as its potential applicability in neural networks. Full article

(This article belongs to the Special Issue Signal Processing and Machine Learning, 2nd Edition)

► Show Figures

Figure 1

21 pages, 20145 KiB

Open AccessArticle

Analyzing Factors Influencing Learning Motivation in Online Virtual Museums Using the S-O-R Model: A Case Study of the National Museum of Natural History

by Jiaying Li, Lin Zhou and Wei Wei

Information 2025, 16(7), 573; https://doi.org/10.3390/info16070573 - 4 Jul 2025

Abstract

Advances in information technology have enabled virtual museums to transcend traditional physical boundaries and become important tools in education. Despite their growing use, the factors influencing the effectiveness of virtual museums in enhancing students’ learning motivation remain underexplored. This study investigates key factors [...] Read more.

Advances in information technology have enabled virtual museums to transcend traditional physical boundaries and become important tools in education. Despite their growing use, the factors influencing the effectiveness of virtual museums in enhancing students’ learning motivation remain underexplored. This study investigates key factors that promote learning motivation among secondary school students using the National Museum of Nature’s Online Virtual Exhibition as a case study. Grounded in the Stimulus–Organism–Response (S-O-R) theoretical framework, a conceptual model was developed and empirically tested using Structural Equation Modeling (SEM) to examine relationships among stimulus variables, psychological states, and learning motivation. Results reveal that affective involvement, cognitive engagement, and perceived presence significantly enhance learning motivation, while immersion shows no significant effect. Among the stimulus factors, perceived enjoyment strongly promotes affective involvement, perceived interactivity enhances cognitive engagement, and content quality primarily supports cognitive processing. Visual aesthetics contribute notably to immersion, affective involvement, and perceived presence. These findings elucidate the multidimensional mechanisms through which user experience in virtual museums influences learning motivation. The study provides theoretical and practical implications for designing effective and engaging virtual museum educational environments, thereby supporting sustainable digital learning practices. Full article

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

► Show Figures

Figure 1

15 pages, 3328 KiB

Open AccessArticle

Evaluating Interaction Techniques in XR Environments Through the Prism of Four EduGames

by Ilias Logothetis, Vasiliki Eirini Chatzea, Iraklis Katsaris, Alexandros Papadakis, Vasileios Kontoulis, Dimitris Pirpiris, Myron Sfyrakis, Antonios Stamatakis and Nikolaos Vidakis

Information 2025, 16(7), 572; https://doi.org/10.3390/info16070572 - 3 Jul 2025

Abstract

Extended reality (XR) has emerged as a transformative technology, offering innovative ways to visualize and interact with digital content. For educators, XR constitutes a valuable tool that advances pedagogical experience and improves teaching quality and clarity. While the literature highlights case studies and [...] Read more.

Extended reality (XR) has emerged as a transformative technology, offering innovative ways to visualize and interact with digital content. For educators, XR constitutes a valuable tool that advances pedagogical experience and improves teaching quality and clarity. While the literature highlights case studies and general guidelines for XR content development, there is limited focus on interaction techniques based on a comparative methodology within educational XR games. This study evaluates different interaction techniques from developers and users perspectives to identify strengths and limitations, providing useful insights to guide future developments in the field. Performed analysis determines the context in which each technique is most effective, how different techniques can be combined, and how integration can be improved for optimal impact. Additionally, methods for transitioning from traditional interaction techniques to modern XR approaches utilizing 3D space and interaction requirements are proposed. A theoretical framework for integrating, configuring, and blending interaction techniques in XR environments tailored for educational purposes is introduced to assist developers and educators in selecting and combining techniques to maximize their effectiveness in different educational contexts and challenges. By addressing these critical aspects, this paper contributes to advancing the understanding and design of XR interaction strategies, ultimately fostering better learning experiences and leading to improved educational outcomes. Full article

(This article belongs to the Special Issue Extended Reality: A New Way of Interacting with the World, 2nd Edition)

► Show Figures

Figure 1

23 pages, 372 KiB

Open AccessArticle

Computability of the Zero-Error Capacity of Noisy Channels

by Holger Boche and Christian Deppe

Information 2025, 16(7), 571; https://doi.org/10.3390/info16070571 - 3 Jul 2025

Abstract

The zero-error capacity of discrete memoryless channels (DMCs), introduced by Shannon, is a fundamental concept in information theory with significant operational relevance, particularly in settings where even a single transmission error is unacceptable. Despite its importance, no general closed-form expression or algorithm is [...] Read more.

The zero-error capacity of discrete memoryless channels (DMCs), introduced by Shannon, is a fundamental concept in information theory with significant operational relevance, particularly in settings where even a single transmission error is unacceptable. Despite its importance, no general closed-form expression or algorithm is known for computing this capacity. In this work, we investigate the computability-theoretic boundaries of the zero-error capacity and establish several fundamental limitations. Our main result shows that the zero-error capacity of noisy channels is not Banach–Mazur-computable and therefore is also not Borel–Turing-computable. This provides a strong form of non-computability that goes beyond classical undecidability, capturing the inherent discontinuity of the capacity function. As a further contribution, we analyze the deep connections between (i) the zero-error capacity of DMCs, (ii) the Shannon capacity of graphs, and (iii) Ahlswede’s operational characterization via the maximum-error capacity of 0–1 arbitrarily varying channels (AVCs). We prove that key semi-decidability questions are equivalent for all three capacities, thus unifying these problems into a common algorithmic framework. While the computability status of the Shannon capacity of graphs remains unresolved, our equivalence result clarifies what makes this problem so challenging and identifies the logical barriers that must be overcome to resolve it. Together, these results chart the computational landscape of zero-error information theory and provide a foundation for further investigations into the algorithmic intractability of exact capacity computations. Full article

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

24 pages, 5858 KiB

Open AccessArticle

A YOLO11-Based Method for Segmenting Secondary Phases in Cu-Fe Alloy Microstructures

by Qingxiu Jing, Ruiyang Wu, Zhicong Zhang, Yong Li, Qiqi Chang, Weihui Liu and Xiaodong Huang

Information 2025, 16(7), 570; https://doi.org/10.3390/info16070570 (registering DOI) - 3 Jul 2025

Abstract

With the development of industrialization, the demand for high-performance metal materials has increased, and copper and its alloys have been widely used. The microstructure of these materials significantly affects their performance. To address the issues of subjectivity, low efficiency, and limited quantitative capability [...] Read more.

With the development of industrialization, the demand for high-performance metal materials has increased, and copper and its alloys have been widely used. The microstructure of these materials significantly affects their performance. To address the issues of subjectivity, low efficiency, and limited quantitative capability in traditional metallographic analysis methods, this paper proposes a deep learning-based approach for segmenting the second phase in Cu-Fe alloys. The method is built upon the YOLO11 framework and incorporates a series of structural enhancements tailored to the characteristics of the secondary-phase microstructure, aiming to improve the model’s detection accuracy and segmentation performance. Specifically, the EIEM module enhances the C3K2 structure to improve edge perception; the CSPSA module is optimized into C2CGA to strengthen multi-scale feature representation; and the RepGFPN and DySample techniques are integrated to construct the GDFPN neck network. Experimental results on the Cu-Fe alloy metallographic image dataset demonstrate that YOLO11 outperforms mainstream semantic segmentation models such as U-Net and DeepLabV3+ in terms of mAP (85.5%), inference speed (208 FPS), and model complexity (10.2 GFLOPs). The improved YOLO11 model achieves an mAP of 89.0%, a precision of 84.6%, and a recall of 81.0% on this dataset, showing significant performance improvements while effectively balancing inference speed and model complexity. Additionally, a quantitative analysis software system for secondary phase uniformity based on this model provides strong technical support for automated metallographic image analysis and demonstrates broad application prospects in materials science research and industrial quality control. Full article

(This article belongs to the Topic Intelligent Image Processing Technology)

► Show Figures

Graphical abstract

18 pages, 17685 KiB

Open AccessArticle

Real-Time Object Detection Model for Electric Power Operation Violation Identification

by Xiaoliang Qian, Longxiang Luo, Yang Li, Li Zeng, Zhiwu Chen, Wei Wang and Wei Deng

Information 2025, 16(7), 569; https://doi.org/10.3390/info16070569 - 3 Jul 2025

Abstract

The You Only Look Once (YOLO) object detection model has been widely applied to electric power operation violation identification, owing to its balanced performance in detection accuracy and inference speed. However, it still faces the following challenges: (1) insufficient detection capability for irregularly [...] Read more.

The You Only Look Once (YOLO) object detection model has been widely applied to electric power operation violation identification, owing to its balanced performance in detection accuracy and inference speed. However, it still faces the following challenges: (1) insufficient detection capability for irregularly shaped objects; (2) objects with low object-background contrast are easily omitted; (3) improving detection accuracy while maintaining computational efficiency is difficult. To address the above challenges, a novel real-time object detection model is proposed in this paper, which introduces three key innovations. To handle the first challenge, an edge perception cross-stage partial fusion with two convolutions (EPC2f) module that combines edge convolutions with depthwise separable convolutions is proposed, which can enhance the feature representation of irregularly shaped objects with only a slight increase in parameters. To handle the second challenge, an adaptive combination of local and global features module is proposed to enhance the discriminative ability of features while maintaining computational efficiency, where the local and global features are extracted respectively via 1D convolutions and adaptively combined by using learnable weights. To handle the third challenge, a parameter sharing of a multi-scale detection heads scheme is proposed to reduce the number of parameters and improve the interaction between multi-scale detection heads. The ablation study on the Ali Tianchi competition dataset validates the effectiveness of three innovation points and their combination. EAP-YOLO achieves the mAP@0.5 of 93.4% and an mAP@0.5–0.95 of 70.3% on the Ali Tianchi Competition dataset, outperforming 12 other object detection models while satisfying the real-time requirement. Full article

(This article belongs to the Special Issue Computer Vision for Security Applications, 2nd Edition)

► Show Figures

Figure 1

47 pages, 1040 KiB

Open AccessSystematic Review

Impact of EU Regulations on AI Adoption in Smart City Solutions: A Review of Regulatory Barriers, Technological Challenges, and Societal Benefits

by Bo Nørregaard Jørgensen and Zheng Grace Ma

Information 2025, 16(7), 568; https://doi.org/10.3390/info16070568 - 2 Jul 2025

Abstract

This review investigates the influence of European Union regulations on the adoption of artificial intelligence in smart city solutions, with a structured emphasis on regulatory barriers, technological challenges, and societal benefits. It offers a comprehensive analysis of the legal frameworks in effect by [...] Read more.

This review investigates the influence of European Union regulations on the adoption of artificial intelligence in smart city solutions, with a structured emphasis on regulatory barriers, technological challenges, and societal benefits. It offers a comprehensive analysis of the legal frameworks in effect by 2025, including the Artificial Intelligence Act, General Data Protection Regulation, Data Act, and sector-specific directives governing mobility, energy, and surveillance. This study critically assesses how these regulations affect the deployment of AI systems across urban domains such as traffic optimization, public safety, waste management, and energy efficiency. A comparative analysis of regulatory environments in the United States and China reveals differing governance models and their implications for innovation, safety, citizen trust, and international competitiveness. The review concludes that although the European Union’s focus on ethics and accountability establishes a solid basis for trustworthy artificial intelligence, the complexity and associated compliance costs create substantial barriers to adoption. It offers recommendations for policymakers, municipal authorities, and technology developers to align regulatory compliance with effective innovation in the context of urban digital transformation. Full article

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

► Show Figures

Figure 1

24 pages, 6755 KiB

Open AccessArticle

Psychological Network Analysis for Risk and Protective Factors of Problematic Social Media Use

by Suzan M. Doornwaard, Vladimir Hazeleger, Ina M. Koning, Albert Ali Salah, Sven Vos and Regina J. J. M. van den Eijnden

Information 2025, 16(7), 567; https://doi.org/10.3390/info16070567 - 2 Jul 2025

Abstract

Identifying when and which adolescents are at increased risk of developing problematic social media use (PSMU) is critical for effective prevention and early intervention. Previous research has examined risk and protective factors using theory-driven (confirmatory-explanatory) approaches, such as regression models. However, few studies [...] Read more.

Identifying when and which adolescents are at increased risk of developing problematic social media use (PSMU) is critical for effective prevention and early intervention. Previous research has examined risk and protective factors using theory-driven (confirmatory-explanatory) approaches, such as regression models. However, few studies have simultaneously considered personal, peer, and parent characteristics to assess their relative contributions, and none have explored how these factors are structurally interrelated using data-driven (inductive–exploratory) approaches. To address these gaps, this study combines logistic regression and psychological network analysis to examine which personal, parent, and peer factors are most relevant in identifying at-risk/problematic social media use among adolescents. Using three waves of data analyzed cross-sectionally from N = 2441 secondary school students, adolescents were classified as normative (0–1 symptoms) or at-risk/problematic (2+ symptoms) users based on the Social Media Disorder Scale. Logistic regression showed that fear of missing out, impulsivity, depressive symptoms, intensity of meeting with friends, and reactive parental rules uniquely predicted at-risk/problematic use. Psychological network analysis identified self-esteem, attention problems, impulsivity, depressive symptoms, and life satisfaction as central, highly interconnected nodes. These findings show that theory- and data-driven approaches illuminate different aspects of PSMU risk, and that network analysis can generate novel hypotheses about underlying processes. Full article

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

► Show Figures

Figure 1

22 pages, 2434 KiB

Open AccessArticle

Sylph: An Unsupervised APT Detection System Based on the Provenance Graph

by Kaida Jiang, Zihan Gao, Siyu Zhang and Futai Zou

Information 2025, 16(7), 566; https://doi.org/10.3390/info16070566 - 2 Jul 2025

Abstract

Traditional detection methods and security defenses are gradually insufficient to cope with evolving attack techniques and strategies, and have coarse detection granularity and high memory overhead. As a result, we propose Sylph, a lightweight unsupervised APT detection method based on a provenance graph, [...] Read more.

Traditional detection methods and security defenses are gradually insufficient to cope with evolving attack techniques and strategies, and have coarse detection granularity and high memory overhead. As a result, we propose Sylph, a lightweight unsupervised APT detection method based on a provenance graph, which not only detects APT attacks but also localizes APT attacks with a fine event granularity and feeds possible attacks back to system detectors to reduce their localization burden. Sylph proposes a whole-process architecture from provenance graph collection to anomaly detection, starting from the system audit logs, and dividing subgraphs based on time slices of the provenance graph it transforms into to reduce memory overhead. Starting from the system audit logs, the provenance graph it transforms into is divided into subgraphs based on time slices, which reduces the memory occupation and improves the detection efficiency at the same time; on the basis of generating the sequence of subgraphs, the full graph embedding of the subgraphs is carried out by using Graph2Vec to obtain their feature vectors, and the anomaly detection based on unsupervised learning is carried out by using an autoencoder, which is capable of detecting new types of attacks that have not yet appeared. After the experimental evaluation, Sylph can realize the APT attack detection with higher accuracy and achieve an accuracy rate. Full article

(This article belongs to the Special Issue Emerging Research on Neural Networks and Anomaly Detection)

► Show Figures

Figure 1

34 pages, 3185 KiB

Open AccessArticle

A Student-Centric Evaluation Survey to Explore the Impact of LLMs on UML Modeling

by Bilal Al-Ahmad, Anas Alsobeh, Omar Meqdadi and Nazimuddin Shaikh

Information 2025, 16(7), 565; https://doi.org/10.3390/info16070565 - 1 Jul 2025

Abstract

Unified Modeling Language (UML) diagrams serve as essential tools for visualizing system structure and behavior in software design. With the emergence of Large Language Models (LLMs) that automate various phases of software development, there is growing interest in leveraging these models for UML [...] Read more.

Unified Modeling Language (UML) diagrams serve as essential tools for visualizing system structure and behavior in software design. With the emergence of Large Language Models (LLMs) that automate various phases of software development, there is growing interest in leveraging these models for UML diagram generation. This study presents a comprehensive empirical investigation into the effectiveness of GPT-4-turbo in generating four fundamental UML diagram types: Class, Deployment, Use Case, and Sequence diagrams. We developed a novel rule-based prompt-engineering framework that transforms domain scenarios into optimized prompts for LLM processing. The generated diagrams were then synthesized using PlantUML and evaluated through a rigorous survey involving 121 computer science and software engineering students across three U.S. universities. Participants assessed both the completeness and correctness of LLM-assisted and human-created diagrams by examining specific elements within each diagram type. Statistical analyses, including paired t-tests, Wilcoxon signed-rank tests, and effect size calculations, validate the significance of our findings. The results reveal that while LLM-assisted diagrams achieve meaningful levels of completeness and correctness (ranging from 61.1% to 67.7%), they consistently underperform compared to human-created diagrams. The performance gap varies by diagram type, with Sequence diagrams showing the closest alignment to human quality and Use Case diagrams exhibiting the largest discrepancy. This research contributes a validated framework for evaluating LLM-generated UML diagrams and provides empirically-grounded insights into the current capabilities and limitations of LLMs in software modeling education. Full article

► Show Figures

Figure 1

23 pages, 552 KiB

Open AccessArticle

A Lightweight Variant of Falcon for Efficient Post-Quantum Digital Signature

by Aigerim Kerimbayeva, Maksim Iavich, Yenlik Begimbayeva, Sergiy Gnatyuk, Sakhybay Tynymbayev, Zhanerke Temirbekova and Olga Ussatova

Information 2025, 16(7), 564; https://doi.org/10.3390/info16070564 - 1 Jul 2025

Abstract

Conventional public-key cryptographic systems are increasingly threatened by advances in quantum computing, accelerating the need for robust post-quantum cryptographic solutions. Among these, Falcon, a compact lattice-based digital signature scheme, has emerged as a leading candidate in the NIST post-quantum standardization process due to [...] Read more.

Conventional public-key cryptographic systems are increasingly threatened by advances in quantum computing, accelerating the need for robust post-quantum cryptographic solutions. Among these, Falcon, a compact lattice-based digital signature scheme, has emerged as a leading candidate in the NIST post-quantum standardization process due to its efficiency and theoretical security grounded in hard lattice problems. This work introduces Falcon-M, a modified version of the Falcon algorithm that significantly reduces implementation complexity. It does so by replacing Falcon’s intricate trapdoor-based key-generation mechanism with a simplified approach that utilizes randomized polynomial Gaussian sampling and fast Fourier transform (FFT) operations. Falcon-M incorporates SHA-512 hashing and discrete Gaussian sampling to preserve cryptographic soundness and statistical randomness while maintaining the core structure of Falcon’s signing and verification processes. We formally specify the Falcon-M algorithm, provide an updated pseudocode, and offer a comparative analysis with the original Falcon in terms of algorithmic complexity, security assumptions, and implementation overhead. Additionally, we present formal lemmas and theorems to ensure correctness and define theoretical bounds on forgery resistance. Although Falcon-M does not rely on a formal cryptographic trapdoor, we demonstrate that it achieves strong practical security based on assumptions related to the Short Integer Solution (SIS) problem. Falcon-M is thus well-suited for lightweight post-quantum applications, particularly in resource-constrained environments, such as embedded systems and Internet-of-Things (IoT) platforms. Full article

15 pages, 12607 KiB

Open AccessArticle

On the Capacity of V2X Communication Networks to Support the Delivery of Emerging C-ITS Services: A Case Study on an Irish Motorway

by Arif Hossan, Md Noor-a-Rahim, Cormac J. Sreenan, Piraba Navaratnam, Shobanraj Navaratnarajah, Thomas Allen, David Laoide-Kemp and Aisling O’Driscoll

Information 2025, 16(7), 563; https://doi.org/10.3390/info16070563 - 30 Jun 2025

Abstract

Roadside communication networks with Cooperative Intelligent Transport Systems (C-ITSs) offer services that aim to enhance traffic management and road safety.This paper presents a comprehensive scalability study of C-ITSs to support a deployment of Day 1 advisory services on the busiest Irish motorway. Specifically, [...] Read more.

Roadside communication networks with Cooperative Intelligent Transport Systems (C-ITSs) offer services that aim to enhance traffic management and road safety.This paper presents a comprehensive scalability study of C-ITSs to support a deployment of Day 1 advisory services on the busiest Irish motorway. Specifically, the performance of the two standardized C-ITS short-range communication technologies, namely ITS-G5 and C-V2X, are quantified. Both technologies are evaluated while considering different market penetration rates (MPRs), real-world vehicle densities during daily time periods, and data traffic demands linked to real world C-ITS services. The simulation results show that ITS-G5 performs slightly better at shorter distances, and C-V2X performs marginally better at medium and longer distances, benefiting from technology that supports better signal quality and communication robustness. Full article

(This article belongs to the Special Issue Internet of Everything and Vehicular Networks)

► Show Figures

Figure 1

28 pages, 1081 KiB

Open AccessArticle

Machine Learning with Self-Assessment Manikin Valence Scale for Fine-Grained Sentiment Analysis

by Lindung Parningotan Manik, Harry Susianto, Arawinda Dinakaramani, R. Niken Pramanik and Totok Suhardijanto

Information 2025, 16(7), 562; https://doi.org/10.3390/info16070562 - 30 Jun 2025

Abstract

Traditional sentiment analysis methods use lexicons or machine learning models to classify text as positive or negative. These approaches are unable to capture nuance or intensity in short or informal texts. We propose a novel method that uses the Self-Assessment Manikin (SAM) valence [...] Read more.

Traditional sentiment analysis methods use lexicons or machine learning models to classify text as positive or negative. These approaches are unable to capture nuance or intensity in short or informal texts. We propose a novel method that uses the Self-Assessment Manikin (SAM) valence scale, which provides a continuous measurement of sentiment, ranging from extremely positive to extremely negative. We describe the development of a lexicon of emotion-laden words with SAM valence scales and investigate its application to fine-grained sentiment analysis. We also propose a lexicon-based polarity approach to complement textual features in machine learning models trained to predict a numerical sentiment label for a given text. This method is evaluated using a new dataset of short texts with sentiment labels based on expert ratings, which are predicted using various machine learning fusion mechanisms. The lexicon-based polarity method is found to provide improvements of 0.250, 0.999, and 0.261 in the mean squared error for classical machine learning, RNN, and transformer-based architectures, respectively. Full article

► Show Figures

Figure 1

14 pages, 4561 KiB

Open AccessArticle

DBDST-Net: Dual-Branch Decoupled Image Style Transfer Network

by Na Su, Jingtao Wang, Jingjing Zhang, Ying Li and Yun Pan

Information 2025, 16(7), 561; https://doi.org/10.3390/info16070561 - 30 Jun 2025

Abstract

The image style transfer task aims to apply the style characteristics of a reference image to a content image, generating a new stylized result. While many existing methods focus on designing feature transfer modules and have achieved promising results, they often overlook the [...] Read more.

The image style transfer task aims to apply the style characteristics of a reference image to a content image, generating a new stylized result. While many existing methods focus on designing feature transfer modules and have achieved promising results, they often overlook the entanglement between content and style features after transfer, making effective separation challenging. To address this issue, we propose a Dual-Branch Decoupled Image Style Transfer Network (DBDST-Net) to better disentangle content and style representations. The network consists of two branches: a Content Feature Decoupling Branch, which captures fine-grained content structures for more precise content separation, and a Style Feature Decoupling Branch, which enhances sensitivity to style-specific attributes. To further improve the decoupling performance, we introduce a dense-regressive loss that minimizes the discrepancy between the original content image and the content reconstructed from the stylized output, thereby promoting the independence of content and style features while enhancing image quality. Additionally, to mitigate the limited availability of style data, we employ the Stable Diffusion model to generate stylized samples for data augmentation. Extensive experiments demonstrate that our method achieves a better balance between content preservation and style rendering compared to existing approaches. Full article

► Show Figures

Figure 1

Journal Description

Information

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI