Big Data and Cognitive Computing

18 pages, 479 KB

Open AccessReview

by Manuel Suárez-Román, Mario Sanz-Rodrigo, Andrés Marín-López and David Arroyo

Big Data Cogn. Comput. 2025, 9(10), 252; https://doi.org/10.3390/bdcc9100252 - 2 Oct 2025

Virtual and digital twins are means of high value to characterize, model and control physical systems, providing the basis for a simulation environment and lab. In the case of a digital twin, it is possible to have a replica of a physical environment [...] Read more.

Virtual and digital twins are means of high value to characterize, model and control physical systems, providing the basis for a simulation environment and lab. In the case of a digital twin, it is possible to have a replica of a physical environment by means of reliable sensor networks and accurate data. In this paper we analyse in detail the threats to the reliability of the information extracted from these sensor networks, along with a set of challenges to guarantee data liveness and trustworthiness. Full article

(This article belongs to the Topic Internet of Things Architectures, Applications, and Strategies: Emerging Paradigms, Technologies, and Advancing AI Integration)

23 pages, 2619 KB

Open AccessArticle

Monitoring of First Responders Biomedical Data During Training with Innovative Virtual Reality Technologies

by Lýdie Leová, Martin Molek, Petr Volf, Marek Sokol, Jan Hejda, Zdeněk Hon, Marek Bureš and Patrik Kutilek

Big Data Cogn. Comput. 2025, 9(10), 251; https://doi.org/10.3390/bdcc9100251 - 30 Sep 2025

Abstract

Traditional training methods for first responders are often limited by time, resources, and safety constraints, which reduces their consistency and effectiveness. This study focused on two main issues: whether exposure to virtual reality training scenarios induces measurable physiological changes in heart rate and [...] Read more.

Traditional training methods for first responders are often limited by time, resources, and safety constraints, which reduces their consistency and effectiveness. This study focused on two main issues: whether exposure to virtual reality training scenarios induces measurable physiological changes in heart rate and heart rate variability, and whether these responses differ between police and firefighter contexts. The aim of this study was to explore the integration of virtual reality technologies into responder training and to evaluate how biomedical monitoring can be used to assess training effectiveness. A pilot measurement was conducted with ten participants who completed systematic crime scene investigation scenarios in both domains. Heart activity was continuously recorded using a wearable sensor and analyzed for heart rate and heart rate variability parameters, while cognitive load and task performance were also assessed. The collected data were statistically evaluated using tests of normality and paired comparisons between baseline and virtual reality phases. The results showed a significant increase in heart rate and a decrease in heart rate variability during virtual reality exposure compared to baseline, with higher cognitive load and success rates in police scenarios compared to firefighter scenarios. These findings indicate that virtual reality scenarios can elicit measurable psychophysiological responses and highlight the potential of combining immersive technologies with biomedical monitoring for the development of adaptive and effective training methods for first responders. Full article

► Show Figures

Figure 1

21 pages, 5954 KB

Open AccessArticle

Exploring the Application and Characteristics of Homomorphic Encryption Based on Pixel Scrambling Algorithm in Image Processing

by Tieyu Zhao

Big Data Cogn. Comput. 2025, 9(10), 250; https://doi.org/10.3390/bdcc9100250 - 30 Sep 2025

Abstract

Homomorphic encryption is well known to researchers, yet its application in image processing is scarce. The diversity of image processing algorithms makes homomorphic encryption implementation challenging. Current research often uses the CKKS algorithm, but it has core bottlenecks in image encryption, such as [...] Read more.

Homomorphic encryption is well known to researchers, yet its application in image processing is scarce. The diversity of image processing algorithms makes homomorphic encryption implementation challenging. Current research often uses the CKKS algorithm, but it has core bottlenecks in image encryption, such as the mismatch between image data and the homomorphic operation mechanism, high 2D-structure-induced costs, noise-related visual quality damage, and poor nonlinear operational support. This study, based on image pixel characteristics, analyzes homomorphic encryption via pixel scrambling algorithms. Using magic square, Arnold, Henon map, and Hilbert curve transformations as starting points, it reveals their homomorphic properties in image processing. This further explores general pixel scrambling algorithm homomorphic encryption properties, offering valuable insights for homomorphic encryption applications in image processing. Full article

(This article belongs to the Topic Applications of Image and Video Processing in Medical Imaging)

33 pages, 20632 KB

Open AccessArticle

A Complex Network Science Perspective on Urban Parcel Locker Placement

by Enrico Corradini, Mattia Mandorlini, Filippo Mariani, Paolo Roselli, Samuele Sacchetti and Matteo Spiga

Big Data Cogn. Comput. 2025, 9(10), 249; https://doi.org/10.3390/bdcc9100249 - 30 Sep 2025

Abstract

The rapid rise of e-commerce is intensifying pressure on last-mile delivery networks, making the strategic placement of parcel lockers an urgent urban challenge. In this work, we adapt multilayer two-mode Social Network Analysis to the parcel-locker siting problem, modeling city-scale systems as bipartite [...] Read more.

The rapid rise of e-commerce is intensifying pressure on last-mile delivery networks, making the strategic placement of parcel lockers an urgent urban challenge. In this work, we adapt multilayer two-mode Social Network Analysis to the parcel-locker siting problem, modeling city-scale systems as bipartite networks linking spatially resolved demand zones to locker locations using only open-source demographic and geographic data. We introduce two new Social Network Analysis metrics, Dual centrality and Coverage centrality, designed to identify both structurally critical and highly accessible lockers within the network. Applying our framework to Milan, Rome, and Naples, we find that conventional coverage-based strategies successfully maximize immediate service reach, but tend to prioritize redundant hubs. In contrast, Dual centrality reveals a distinct set of lockers whose presence is essential for maintaining overall connectivity and resilience, often acting as hidden bridges between user communities. Comparative analysis with state-of-the-art multi-criteria optimization baselines confirms that our network-centric metrics deliver complementary, and in some cases better, guidance for robust locker placement. Our results show that a network-analytic lens yields actionable guidance for resilient last-mile locker siting. The method is reproducible from open data (potential-access weights) and plug-in compatible with observed assignments. Importantly, the path-based results (Coverage centrality) are adjacency-driven and thus largely insensitive to volumetric weights. Full article

(This article belongs to the Special Issue Advances in Graph Learning and Representation Models for Complex Network Analysis)

16 pages, 2125 KB

Open AccessArticle

A Multi-Model Machine Learning Framework for Daily Stock Price Prediction

by Bharatendra Rai and Leili Soltanisehat

Big Data Cogn. Comput. 2025, 9(10), 248; https://doi.org/10.3390/bdcc9100248 - 28 Sep 2025

Abstract

Stock price prediction remains a challenging problem due to the inherent volatility and complexity of financial markets. This study proposes a multi-model machine learning framework for one-day-ahead stock price prediction using thirty-six features derived from technical indicators. Empirical analysis is conducted on data [...] Read more.

Stock price prediction remains a challenging problem due to the inherent volatility and complexity of financial markets. This study proposes a multi-model machine learning framework for one-day-ahead stock price prediction using thirty-six features derived from technical indicators. Empirical analysis is conducted on data from Apple, Tesla, and NVIDIA, employing nine classification algorithms, including support vector machines, random forests, extreme gradient boosting, and logistic regression. Results indicate that momentum-based indicators are the most influential predictors. While support vector machines achieve the highest accuracy for Apple, extreme gradient boosting performed best for NVIDIA and Tesla. In addition, explainable AI techniques are applied to interpret individual model predictions, thereby enhancing transparency and trust in the results. The study contributes to financial analytics research by providing a comparative evaluation of diverse machine learning methods and highlighting key indicators critical for short-term stock price forecasting. Full article

(This article belongs to the Topic Electronic Communications, IOT and Big Data, 2nd Volume)

► Show Figures

Figure 1

24 pages, 817 KB

Open AccessArticle

Leveraging Large Language Models for Sustainable and Inclusive Web Accessibility

by Manuel Andruccioli, Barry Bassi, Giovanni Delnevo and Paola Salomoni

Big Data Cogn. Comput. 2025, 9(10), 247; https://doi.org/10.3390/bdcc9100247 - 26 Sep 2025

Abstract

The increasing complexity of modern web applications, which are composed of dynamic and asynchronous components, poses a significant challenge for digital inclusion. Traditional automated tools typically analyze only the static HTML markup generated by frontend and backend frameworks. Recent advances in Large Language [...] Read more.

The increasing complexity of modern web applications, which are composed of dynamic and asynchronous components, poses a significant challenge for digital inclusion. Traditional automated tools typically analyze only the static HTML markup generated by frontend and backend frameworks. Recent advances in Large Language Models (LLMs) offer a novel approach to enhance the validation process by directly analyzing the source code. In this paper, we investigate the capacity of LLMs to interpret and reason dynamically generated content, providing real-time feedback on web accessibility. Our findings show that LLMs can correctly anticipate the presence of accessibility violations in the generated HTML code, going beyond the capabilities of traditional validators, also evaluating possible issues due to the asynchronous execution of the web application. However, together with legitimate issues, LLMs also produced a relevant number of hallucinated or redundant violations. This study contributes to the broader effort of employing AI with the aim of improving the inclusivity and equity of the web. Full article

(This article belongs to the Special Issue Generative AI and Large Language Models)

► Show Figures

Figure 1

32 pages, 13081 KB

Open AccessArticle

FedIFD: Identifying False Data Injection Attacks in Internet of Vehicles Based on Federated Learning

by Huan Wang, Junying Yang, Jing Sun, Zhe Wang, Qingzheng Liu and Shaoxuan Luo

Big Data Cogn. Comput. 2025, 9(10), 246; https://doi.org/10.3390/bdcc9100246 - 26 Sep 2025

Abstract

With the rapid development of intelligent connected vehicle technology, false data injection (FDI) attacks have become a major challenge in the Internet of Vehicles (IoV). While deep learning methods can effectively identify such attacks, the dynamic, distributed architecture of the IoV and limited [...] Read more.

With the rapid development of intelligent connected vehicle technology, false data injection (FDI) attacks have become a major challenge in the Internet of Vehicles (IoV). While deep learning methods can effectively identify such attacks, the dynamic, distributed architecture of the IoV and limited computing resources hinder both privacy protection and lightweight computation. To address this, we propose FedIFD, a federated learning (FL)-based detection method for false data injection attacks. The lightweight threat detection model utilizes basic safety messages (BSM) for local incremental training, and the Q-FedCG algorithm compresses gradients for global aggregation. Original features are reshaped using a time window. To ensure temporal and spatial consistency, a sliding average strategy aligns samples before spatial feature extraction. A dual-branch architecture enables parallel extraction of spatiotemporal features: a three-layer stacked Bidirectional Long Short-Term Memory (BiLSTM) captures temporal dependencies, and a lightweight Transformer models spatial relationships. A dynamic feature fusion weight matrix calculates attention scores for adaptive feature weighting. Finally, a differentiated pooling strategy is applied to emphasize critical features. Experiments on the VeReMi dataset show that the accuracy reaches 97.8%. Full article

(This article belongs to the Special Issue Big Data Analytics with Machine Learning for Cyber Security)

► Show Figures

Figure 1

28 pages, 2160 KB

Open AccessArticle

DTS-MixNet: Dynamic Spatiotemporal Graph Mixed Network for Anomaly Detection in Multivariate Time Series

by Chengxun Tan, Jiayi Hu, Jian Li, Minmin Miao, Wenjun Hu and Shitong Wang

Big Data Cogn. Comput. 2025, 9(10), 245; https://doi.org/10.3390/bdcc9100245 - 25 Sep 2025

Abstract

Anomaly detection in multivariate time series (MTS) remains challenging due to the presence of complex and dynamic spatiotemporal dependencies. To address this, we propose the Dynamic Spatiotemporal Graph Mixed Network (DTS-MixNet), which takes a sliding window data as input to predict the next [...] Read more.

Anomaly detection in multivariate time series (MTS) remains challenging due to the presence of complex and dynamic spatiotemporal dependencies. To address this, we propose the Dynamic Spatiotemporal Graph Mixed Network (DTS-MixNet), which takes a sliding window data as input to predict the next time series data and determine its state. The model comprises five blocks. The Temporal Graph Structure Learner (TGSL) generates the attention-weighted graphs via two types of neighbor relationships and the multi-head-attention-based neighbor degrees. Then, the Cross-Temporal Dynamic Encoder (CTDE) aggregates the cross-temporal dependencies from attention-weighted graphs, and encodes them into a proxy multivariate sequence (PMS), which is fed into the proposed Cross-Variable Dynamic Encoder (CVDE). Subsequently, the CVDE captures the sensors-among spatial relationship through multiple local spatial graphs and a global spatial graph, and produces a spatial graph sequence (SGS). Finally, the Spatiotemporal Mixer (TSM) mixes PMS and SGS to build a spatiotemporal mixed sequence (TSMS) for downstream tasks, e.g., classification or prediction. We evaluate on two industrial control datasets and discuss applicability to non-industrial multivariate time series. The experimental results on benchmark datasets show that the proposed DTS-MixNet is encouraging. Full article

► Show Figures

Figure 1

18 pages, 2586 KB

Open AccessArticle

A Comparative Study of X Data About the NHS Using Sentiment Analysis

by Saeed Ur Rehman, Obi Oluchi Blessing and Anwar Ali

Big Data Cogn. Comput. 2025, 9(10), 244; https://doi.org/10.3390/bdcc9100244 - 24 Sep 2025

Abstract

This study investigates sentiment analysis of X data about the National Health Service (NHS) during a politically charged period, using lexicon-based, machine learning, and deep learning approaches, as well as topic modelling and aspect-based sentiment analysis (ABSA). This study is distinct in its [...] Read more.

This study investigates sentiment analysis of X data about the National Health Service (NHS) during a politically charged period, using lexicon-based, machine learning, and deep learning approaches, as well as topic modelling and aspect-based sentiment analysis (ABSA). This study is distinct in its comparative evaluation of sentiment analysis techniques on NHS-related tweets during a politically sensitive period, offering insights into public opinion shaped by political discourse. A dataset of 35,000 tweets collected and analysed using various techniques, including VADER, TextBlob, Naive Bayes, Support Vector Machines, Logistic Regression, Ensemble Learning, and BERT. Unlike previous studies that focus on structured feedback or general sentiment, this research uniquely explores unstructured public discourse during an election period, capturing real-time political sentiment towards NHS policies. The sentiment distribution from lexicon-based methods depicted that the presence of stop words could affect model performance. While all models achieved high accuracy on the validation dataset, challenges such as class imbalance and limited labelled data impacted performance, with signs of overfitting observed. Topic modelling identified nine topic clusters, with “waiting list,” “service,” and “immigration” carrying negative sentiments. At the same time, words like “thank,” “support,” “care,” and “team” had the most positive sentiments, reflecting public delight in these areas. ABSA identified positive sentiments towards aspects like “useful service”. This study contributes a comparative framework for evaluating sentiment analysis techniques in politically contextualised healthcare discourse, offering insights for policymakers and researchers. The study underscores the importance of data quality in sentiment analysis. Future research should consider incorporating multilingual datasets, extending data collection periods, optimising deep learning models, and employing hybrid approaches to enhance performance. Full article

► Show Figures

Figure 1

21 pages, 40457 KB

Open AccessArticle

Interpretable Emotion Estimation in Indoor Remote Work Environments via Environmental Sensor Data

by Yuma Toriyama, Tsumugi Isogami and Nobuyoshi Komuro

Big Data Cogn. Comput. 2025, 9(10), 243; https://doi.org/10.3390/bdcc9100243 - 23 Sep 2025

Abstract

Indoor environmental factors such as CO₂ concentration, temperature, and humidity can significantly influence individuals’ emotional states and productivity. This study continuously collected environmental data using wireless sensors and emotional data from wearable devices in an office-like remote-work setting. Machine learning models, including [...] Read more.

Indoor environmental factors such as CO₂ concentration, temperature, and humidity can significantly influence individuals’ emotional states and productivity. This study continuously collected environmental data using wireless sensors and emotional data from wearable devices in an office-like remote-work setting. Machine learning models, including Random Forest and Gradient Boosting Decision Tree, were developed and interpreted using SHAP (Shapley Additive Explanations). The proposed models achieved estimation accuracies above 85%. SHAP analysis revealed that CO₂ concentration, temperature, and humidity were influential factors in predicting pleasant or unpleasant states. These findings demonstrate the feasibility of real-time, data-driven emotion estimation and provide insights into the design of indoor environments that foster comfort and mental well-being. Full article

► Show Figures

Figure 1

34 pages, 3790 KB

Open AccessArticle

A Critical Analysis of Government Communication via X (Twitter)

by Paulo Rita, Nuno Antonio and Luciana Nassar

Big Data Cogn. Comput. 2025, 9(9), 242; https://doi.org/10.3390/bdcc9090242 - 22 Sep 2025

Abstract

Social media has dramatically impacted all sectors of society, including public communication and governmental relations. Most countries have increasingly incorporated it into their communication strategies. However, there is little research on this subject. This study tackled this gap by analyzing the existing literature [...] Read more.

Social media has dramatically impacted all sectors of society, including public communication and governmental relations. Most countries have increasingly incorporated it into their communication strategies. However, there is little research on this subject. This study tackled this gap by analyzing the existing literature and comprehending the objectives, determinant factors, and consequences of social media use by governments. It investigated the practice of such measures on Portuguese governmental communication to understand the low levels of engagement identified through the research. The governmental accounts were subjected to two types of analysis to achieve a practical means of classification. The exploratory analysis of the @govpt account data (18,071) tweets used various methods specific to user-generated content. Fourteen public agencies’ tweets (39,965) underwent the transparency, participation, collaboration, and comfort (TPCC) index computations, developing four factors to calculate the public sector’s digital communication success. The TPCC Index results revealed the lowest development rates, with participation and collaboration being the least developed factors. Only 107 mentions were found across 59,036 tweets, and explicit co-creation terms appeared 303 times. Furthermore, the analyzed accounts did not progress to the deeper stages of connection with governments’ possible exploration n. This research’s main achievements and contributions consist of contemplating the Portuguese case study while proposing and validating the TPCC Index metrics’ modifications for X data analysis. Full article

► Show Figures

Figure 1

41 pages, 7528 KB

Open AccessArticle

PROTECTION: A BPMN-Based Data-Centric Process-Modeling-Managing-and-Mining Framework for Pandemic Prevention and Control

by Alfredo Cuzzocrea, Islam Belmerabet, Carlo Combi, Enrico Franconi and Paolo Terenziani

Big Data Cogn. Comput. 2025, 9(9), 241; https://doi.org/10.3390/bdcc9090241 - 22 Sep 2025

Abstract

The recent COVID-19 pandemic outbreak has demonstrated all the limitations of modern healthcare information systems in preventing and controlling pandemics, especially following an unexpected event. Existing approaches often fail to integrate real-time data and adaptive learning mechanisms, leading to inefficient response [...] Read more.

The recent COVID-19 pandemic outbreak has demonstrated all the limitations of modern healthcare information systems in preventing and controlling pandemics, especially following an unexpected event. Existing approaches often fail to integrate real-time data and adaptive learning mechanisms, leading to inefficient response strategies and resource allocation challenges. To address this gap, in this paper, we propose PROTECTION, an innovative data-centric process-modeling-managing-and-mining framework for pandemic control and prevention that is based on the new paradigm that we name Knowledge-, Decision- and Data-Intensive (KDDI) processes. PROTECTION adopts Business Process Model and Notation (BPMN) as a standardized approach to model and manage complex healthcare workflows, enhancing interoperability and formal process representation. PROTECTION introduces a structured methodology that integrates Big Data Analytics, Process Mining and Adaptive Learning Mechanisms to dynamically update healthcare processes in response to evolving pandemic conditions. The framework enables real-time process optimization, predictive analytics for outbreak detection, and automated decision support for healthcare. Through case studies and experimental validation, we demonstrate how PROTECTION can effectively deal with the complex domain of pandemic control and prevention. Full article

► Show Figures

Figure 1

23 pages, 5880 KB

Open AccessArticle

Offline Knowledge Base and Attention-Driven Semantic Communication for Image-Based Applications in ITS Scenarios

by Yan Xiao, Xiumei Fan, Zhixin Xie and Yuanbo Lu

Big Data Cogn. Comput. 2025, 9(9), 240; https://doi.org/10.3390/bdcc9090240 - 18 Sep 2025

Abstract

Communications in intelligent transportation systems (ITS) face explosive data growth from applications such as autonomous driving, remote diagnostics, and real-time monitoring, imposing severe challenges on limited spectrum, bandwidth, and latency. Reliable semantic image reconstruction under noisy channel conditions is critical for ITS perception [...] Read more.

Communications in intelligent transportation systems (ITS) face explosive data growth from applications such as autonomous driving, remote diagnostics, and real-time monitoring, imposing severe challenges on limited spectrum, bandwidth, and latency. Reliable semantic image reconstruction under noisy channel conditions is critical for ITS perception tasks, since noise directly impacts the recognition of both static infrastructure and dynamic obstacles. Unlike traditional approaches that aim to transmit all image data with equal fidelity, effective ITS communication requires prioritizing task-relevant dynamic elements such as vehicles and pedestrians while filtering out largely static background features such as buildings, road signs, and vegetation. To address this, we propose an Offline Knowledge Base and Attention-Driven Semantic Communication (OKBASC) framework for image-based applications in ITS scenarios. The proposed framework performs offline semantic segmentation to build a compact knowledge base of semantic masks, focusing on dynamic task-relevant regions such as vehicles, pedestrians, and traffic signals. At runtime, precomputed masks are adaptively fused with input images via sparse attention to generate semantic-aware representations that selectively preserve essential information while suppressing redundant background. Moreover, we introduce a further Bi-Level Routing Attention (BRA) module that hierarchically refines semantic features through global channel selection and local spatial attention, resulting in improved discriminability and compression efficiency. Experiments on the VOC2012 and nuPlan datasets under varying SNR levels show that OKBASC achieves higher semantic reconstruction quality than baseline methods, both quantitatively via the Structural Similarity Index Metric (SSIM) and qualitatively via visual comparisons. These results highlight the value of OKBASC as a communication-layer enabler that provides reliable perceptual inputs for downstream ITS applications, including cooperative perception, real-time traffic safety, and incident detection. Full article

► Show Figures

Graphical abstract

25 pages, 3025 KB

Open AccessArticle

QiGSAN: A Novel Probability-Informed Approach for Small Object Segmentation in the Case of Limited Image Datasets

by Andrey Gorshenin and Anastasia Dostovalova

Big Data Cogn. Comput. 2025, 9(9), 239; https://doi.org/10.3390/bdcc9090239 - 18 Sep 2025

Abstract

The paper presents a novel probability-informed approach to improving the accuracy of small object semantic segmentation in high-resolution imagery datasets with imbalanced classes and a limited volume of samples. Small objects imply having a small pixel footprint on the input image, for example, [...] Read more.

The paper presents a novel probability-informed approach to improving the accuracy of small object semantic segmentation in high-resolution imagery datasets with imbalanced classes and a limited volume of samples. Small objects imply having a small pixel footprint on the input image, for example, ships in the ocean. Informing in this context means using mathematical models to represent data in the layers of deep neural networks. Thus, the ensemble Quadtree-informed Graph Self-Attention Networks (QiGSANs) are proposed. New architectural blocks, informed by types of Markov random fields such as quadtrees, have been introduced to capture the interconnections between features in images at different spatial resolutions during the graph convolution of superpixel subregions. It has been analytically proven that quadtree-informed graph convolutional neural networks, a part of QiGSAN, tend to achieve faster loss reduction compared to convolutional architectures. This justifies the effectiveness of probability-informed modifications based on quadtrees. To empirically demonstrate the processing of real small data with imbalanced object classes using QiGSAN, two open datasets of synthetic aperture radar (SAR) imagery (up to

0.5

m per pixel) are used: the High Resolution SAR Images Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD). The results of QiGSAN are compared to those of the transformers SegFormer and LWGANet, which constitute a new state-of-the-art model for UAV (Unmanned Aerial Vehicles) and SAR image processing. They are also compared to convolutional neural networks and several ensemble implementations using other graph neural networks. QiGSAN significantly increases the

F_{1}

-score values by up to

63.93 %

,

48.57 %

, and

9.84 %

compared to transformers, convolutional neural networks, and other ensemble architectures, respectively. QiGSAN outperformed the base segmentors with the mIOU (mean intersection-over-union) metric too: the highest increase was

35.79 %

. Therefore, our approach to knowledge extraction using mathematical models allows us to significantly improve modern computer vision techniques for imbalanced data. Full article

(This article belongs to the Special Issue Recent Advances in Machine Learning Methods for Imperfect Large-Scale Data)

► Show Figures

Figure 1

21 pages, 3917 KB

Open AccessArticle

Federated Learning with Adversarial Optimisation for Secure and Efficient 5G Edge Computing Networks

by Saniya Zafar, Jonathan White and Phil Legg

Big Data Cogn. Comput. 2025, 9(9), 238; https://doi.org/10.3390/bdcc9090238 - 17 Sep 2025

Abstract

With the evolution of 5G edge computing networks, privacy-aware applications are gaining significant attention due to their decentralised processing capabilities. However, these networks face substantial challenges to ensure privacy and security, specifically in a Federated Learning (FL) setup, where adversarial attacks can potentially [...] Read more.

With the evolution of 5G edge computing networks, privacy-aware applications are gaining significant attention due to their decentralised processing capabilities. However, these networks face substantial challenges to ensure privacy and security, specifically in a Federated Learning (FL) setup, where adversarial attacks can potentially influence the model integrity. Conventional privacy-preserving FL mechanisms are often susceptible to such attacks, leading to degraded model performance and severe security vulnerabilities. To address this issue, we propose FL with adversarial optimisation framework to improve adversarial robustness in 5G edge computing networks while ensuring privacy preservation. The proposed framework considers two models; a classifier model and an adversary model, where the classifier model is integrated with the adversary model, trained jointly considering Fast Gradient Sign Method (FGSM) for generation of adversarial perturbations. This adversarial optimisation enhances classifier’s resilience to attacks, thereby improving both privacy preservation and model accuracy. Experimental analysis reveals that the proposed model achieves up to

99.44 %

accuracy on adversarial test data, while improving robustness and sustaining high precision and recall across varying client scenarios. The experimental results further ensure the effectiveness of the proposed model in terms of communication efficiency and computational efficiency while reducing inference time and FLOPs making it ideal for secure 5G edge computing applications. Full article

(This article belongs to the Special Issue Application of Cloud Computing in Industrial Internet of Things)

► Show Figures

Figure 1

25 pages, 441 KB

Open AccessReview

A Meta-Survey of Generative AI in Education: Trends, Challenges, and Research Directions

by Sirine Bouguettaya, Francesco Pupo, Min Chen and Giancarlo Fortino

Big Data Cogn. Comput. 2025, 9(9), 237; https://doi.org/10.3390/bdcc9090237 - 16 Sep 2025

Abstract

Education is experiencing a paradigm shift, evolving from traditional learning methods to computer-tool-based education, and now toward the integration of Generative Artificial Intelligence. While classical methods offer structured and standardized learning, they often do not fully address individual learner needs and accessibility. The [...] Read more.

Education is experiencing a paradigm shift, evolving from traditional learning methods to computer-tool-based education, and now toward the integration of Generative Artificial Intelligence. While classical methods offer structured and standardized learning, they often do not fully address individual learner needs and accessibility. The rise of digital technologies introduced adaptive learning platforms, online classrooms, and interactive educational tools, expanding the reach and flexibility of educational systems. Today, Generative Artificial Intelligence tools are redefining the education landscape by personalized learning experiences, automating content generation, and providing real-time feedback. Intelligent tutoring systems and personalized assessments empower students with customized learning pathways that enhance engagement and academic performance. This paper presents a meta-survey that systematically examines the role of Generative Artificial Intelligence in education, following PRISMA guidelines to analyze trends, frameworks, and research outcomes across a curated body of academic literature. Special attention is given to the emergence of commercial Generative Artificial Intelligence tools, which are increasingly embedded in learning environments. A structured comparison framework and research questions guide the review, offering insights into how Generative Artificial Intelligence technologies are shaping pedagogical practices, influencing assessment, and raising new ethical and technical challenges. The paper also explores future directions, highlighting how Generative Artificial Intelligence is driving the emergence of new learning models. Full article

► Show Figures

Figure 1

25 pages, 1028 KB

Open AccessArticle

Characterizing User Archetypes and Discussions on Social Hypernetworks

by Andrea Failla, Salvatore Citraro, Giulio Rossetti and Francesco Cauteruccio

Big Data Cogn. Comput. 2025, 9(9), 236; https://doi.org/10.3390/bdcc9090236 - 16 Sep 2025

Abstract

In recent years, the proliferation of social platforms has drastically transformed how individuals interact, organize, and share information. In this scenario, there has been an unprecedented increase in the scale and complexity of interactions and, at the same time, little to no research [...] Read more.

In recent years, the proliferation of social platforms has drastically transformed how individuals interact, organize, and share information. In this scenario, there has been an unprecedented increase in the scale and complexity of interactions and, at the same time, little to no research about certain fringe social platforms. In this paper, we present a multi-dimensional framework for characterizing nodes and hyperedges in social hypernetworks, with a focus on the understudied alt-right platform Scored.co. Our approach integrates the possibility of studying higher-order interactions, thanks to the hypernetwork representation, and various node features such as user activity, sentiment, and toxicity, with the aim of defining distinct user archetypes and understanding their roles within the network. Utilizing a comprehensive dataset from Scored.co, consisting of more than 4.4 M posts and 36.9 M comments, we analyze the dynamics of these archetypes over time and explore their interactions and influence within the community. We identify eight archetypes, with the largest group comprising over 15,000 users, and observe that 44% of interactions involve at least five participants, highlighting the importance of higher-order modeling. Furthermore, we find significant archetype transitions and stable yet locally dense interaction patterns, with users exposed to roughly 1000 unique peers on average. The framework’s versatility allows for detailed analysis of both individual user behaviors and broader social structures. Our findings highlight the importance of higher-order interactions and node features in understanding social dynamics, and offer new insights into the roles and behaviors that emerge in complex online environments. Full article

► Show Figures

Figure 1

26 pages, 3558 KB

Open AccessArticle

Application of Inverse Optimization Algorithms in Neural Network Models for Short-Term Stock Price Forecasting

by Ekaterina Gribanova, Roman Gerasimov and Elena Viktorenko

Big Data Cogn. Comput. 2025, 9(9), 235; https://doi.org/10.3390/bdcc9090235 - 9 Sep 2025

Abstract

This paper introduces novel inverse optimization algorithms (RC and DC) for neural network training in stock price forecasting in an attempt to overcome the traditional gradient descent limitation of local minima convergence. The key novelty is a stochastic algorithm for inverse problems adapted [...] Read more.

This paper introduces novel inverse optimization algorithms (RC and DC) for neural network training in stock price forecasting in an attempt to overcome the traditional gradient descent limitation of local minima convergence. The key novelty is a stochastic algorithm for inverse problems adapted to neural network training, where target function values decrease iteratively through selective weight modification. Experimental analysis used closing price data from 40 Russian companies, comparing traditional activation functions (linear, sigmoid, tanh) with specialized functions (sincos, cloglogm, mish) across perceptrons and single-hidden-layer networks. Key findings show the superiority of the DC method for single-layer networks, while RC proves most effective for hidden-layer networks. The linear activation function with the RC algorithm delivered optimal results in most experiments, challenging conventional nonlinear activation preferences. The optimal architecture, namely, a single hidden layer with two neurons, achieved the best prediction accuracy in 70% of cases. The research confirms that inverse optimization algorithms can provide higher training efficiency than classical gradient methods, offering practical improvements for financial forecasting. Full article

► Show Figures

Figure 1

18 pages, 1041 KB

Open AccessArticle

Hierarchical Discourse-Semantic Modeling for Zero Pronoun Resolution in Chinese

by Tingxin Wei, Jiabin Li, Xiaoling Ye and Weiguang Qu

Big Data Cogn. Comput. 2025, 9(9), 234; https://doi.org/10.3390/bdcc9090234 - 9 Sep 2025

Abstract

Understanding discourse context is fundamental to human language comprehension. Despite the remarkable progress achieved by Large Language Models, they still struggle with discourse-level anaphora resolution, particularly in Chinese. One major challenge is zero anaphora, a prevalent linguistic phenomenon in which referential elements are [...] Read more.

Understanding discourse context is fundamental to human language comprehension. Despite the remarkable progress achieved by Large Language Models, they still struggle with discourse-level anaphora resolution, particularly in Chinese. One major challenge is zero anaphora, a prevalent linguistic phenomenon in which referential elements are omitted, increasing complexity and ambiguity for computational models. To address this issue, we introduce CDAMR (Chinese Discourse Abstract Meaning Representation), a novel annotated corpus that systematically labels zero pronouns across diverse syntactic positions along with their discourse-level coreference chains. In addition, we present a hierarchical discourse-semantic enhanced model that separately encodes local discourse semantics and global discourse semantics, and models their interactions via structured multi-attention mechanisms. Experiments on both CDAMR and OntoNotes demonstrate the approach’s cross-corpus generalizability and effectiveness, achieving F1 scores of 59.86% and 60.54%, respectively. Ablation studies further confirm that discourse-level semantics significantly enhance zero pronoun resolution. These findings highlight the value of cognitively inspired discourse modeling and the importance of comprehensive discourse annotations for languages with limited explicit syntactic cues such as Chinese. Full article

(This article belongs to the Special Issue Natural Language Processing Applications in Big Data)

► Show Figures

Graphical abstract

Journal Description

Big Data and Cognitive Computing

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Further Information

Guidelines

MDPI Initiatives

Follow MDPI