Search Results (243)

Background: The convergence of machine learning (ML), gamification, and critical thinking assessment within adaptive educational platforms has accelerated since 2020, driven by large language models (LLMs) and graph neural networks (GNNs). No prior systematic review has jointly addressed all three dimensions, and Central Asian educational contexts remain underrepresented. Methods: Following PRISMA 2020 guidelines, we searched Scopus (n  =  4396) and OpenAlex (n  =  4152) for publications from 2016 to 2026. Quality assessment used the Mixed Methods Appraisal Tool (MMAT 2018; threshold ≥  2), yielding 82 papers. Five research questions addressed ML personalization (RQ1), gamification and engagement (RQ2), critical thinking assessment tools (RQ3), recommendation algorithms (RQ4), and regional applicability in Kazakhstan and Central Asia (RQ5). Results: Transformer-based and GNN models dominate the recent literature (52% of corpus from 2025), with an accuracy of 91–97% for dropout prediction and learning path recommendation under single-institution conditions. Gamification studies report up to 90% student satisfaction; LLM-based critical thinking assessment shows promise but faces validity concerns. Thirteen papers address Central Asian contexts. Conclusions: Significant gaps persist: no integrated gamification–critical thinking framework exists, recommendation systems lack explainability, and Kazakh-language datasets are severely underrepresented. Future research should prioritize multilingual adaptive systems, explainable algorithms, and privacy-preserving federated learning for low-resource contexts. Full article

With the widespread adoption of intelligent terminals, edge devices, and distributed information systems in the financial domain, financial security sensing data exhibit multisource heterogeneity, dynamic temporal patterns, and high privacy sensitivity. Traditional centralized anomaly detection methods are no longer able to simultaneously satisfy the requirements of cross-institutional or cross-node collaborative modeling, client data privacy protection, and robust monitoring of transaction and system anomalies. To address this challenge, a data-local federated deep anomaly detection framework has been proposed for distributed financial security sensing systems. Initially, a local deep financial security sensing representation module is constructed to perform temporal encoding and attention-based modeling on multisource financial signals, including terminal operation status, network transaction communication, backend server operation, identity authentication, and anomaly alerts, thereby extracting representations relevant to anomalous behaviors. Subsequently, a data-local federated optimization and personalized aggregation mechanism is developed to enable cross-node knowledge sharing without transmitting raw transaction or client data, while local personalized detection heads are employed to adapt to non-independent and identically distributed (non-IID) financial institution data. Furthermore, an adversarially robust security detection and trust-aware aggregation strategy is introduced to enhance model stability under input noise, feature masking, anomaly camouflage, and potential malicious client updates. Experimental results demonstrate that the proposed method achieves an Accuracy of $92.37\%$, a Precision of $89.41\%$, a Recall of $88.26\%$, an F1-score of $88.83\%$, an AUC of $93.06\%$, and a PR-AUC of $89.15\%$ in the primary financial anomaly detection task, significantly outperforming baseline methods such as Isolation Forest, Autoencoder, LSTM, Transformer, FedAvg, FedProx, SCAFFOLD, and MOON. In robustness experiments, the method attains F1-scores of $87.95\%$, $86.42\%$, $86.88\%$, $84.57\%$, $86.73\%$, and $83.91\%$ under Gaussian noise, feature masking, temporal shift, adversarial perturbation, and $20\%$ and $30\%$ malicious client scenarios, respectively. Ablation studies further confirm the effectiveness of local representation learning, personalized federated optimization, adversarial training, and trust-aware aggregation mechanisms. Overall, the proposed approach provides an efficient intelligent anomaly detection solution for financial AI security monitoring scenarios characterized by data localization requirements, node heterogeneity, and attack perturbations. Full article

Process data plays a vital role in diagnosing fault sources in chemical production. However, such data contain rich process information and are often sensitive, making direct analysis infeasible due to privacy concerns. Although federated learning mitigates data leakage risks, the conventional averaging strategy falls short in achieving high fault identification accuracy, especially under non-independent and identically distributed (non-IID) client data. To overcome this challenge, we propose a personalized federated learning framework, in which a Takagi–Sugeno (T–S) fuzzy fusion rule is designed. Then, the personalized model is constructed through a structured procedure: fuzzification of model parameter distances, definition of fuzzy rules, fuzzy inference, and defuzzification. Moreover, layer-wise fusion is employed to enhance the precision of aggregation. Evaluations on the Tennessee Eastman (TE) process demonstrate that our method achieves superior fault identification accuracy. The results validate the efficacy of the proposed Fuzzy Rule-Based Federated Layer-wise Fusion (FedFZ) framework in industrial fault diagnosis under heterogeneous data distributions. Full article

Human activity recognition (HAR) plays a multi-dimensional supporting role in the medical field, providing strong technical support for various aspects such as disease prevention, diagnosis, treatment and rehabilitation. However, the use of traditional federated learning to deploy HAR models on edge devices is not ideal because of the heterogeneity of hardware and data. To solve this problem, this paper introduces a personalized HAR method, which can remove the outlier nodes and cluster hierarchically. In this study, the cosine similarity of local model parameters is calculated, and the clustering of dynamic clients is realized. In the study, the normalized training loss evaluation mechanism is introduced to identify and eliminate outlier nodes, and the robustness of the system is enhanced. In the study, the collaborative training method is adopted to meet the personalized needs of users and improve the generality of the model. The proposed method achieves an average recognition accuracy of 92.94% and an F1 score of 91.28% on four public datasets, demonstrating that the method put forward in this paper can reduce the negative impact of data heterogeneity, improve the efficiency of convergence, and produce good recognition performance for the development of the Internet of Things. Full article

In recent years, the widespread availability of wearable devices and smartphones has enabled the large-scale collection of human activity data, fostering new opportunities for automatic workout recognition and personalized fitness monitoring. However, the centralized storage of video recordings raises critical privacy concerns, particularly when raw data contain identifiable individuals. Federated Machine Learning provides a paradigm designed with the aim of reducing privacy risks; here, models are collaboratively trained across distributed clients without sharing their sensitive data. In this paper, we propose an approach for workout video classification with Federated Machine Learning, enhanced by explainability through Gradient-weighted Class-Activation Mapping. The proposed method is evaluated on a real-world multi-class exercise video dataset, organized into eight biomechanically coherent macro-classes. In the experimental analysis, we consider several federated configurations in terms of the number of clients, the chosen aggregation strategy, and global communication rounds. The obtained results demonstrate that different aggregation strategies achieve comparable overall accuracy, while explainability effectively highlights the discriminative regions associated with exercise execution, revealing meaningful differences in model behavior between aggregation strategies and uncovering misclassifications driven by contextual biases, demonstrating the trustworthiness of the proposed approach for explainable workout video classification. Full article

The rapid growth of the Internet of Things (IoT) has introduced significant cybersecurity challenges in highly distributed, heterogeneous, and privacy-sensitive environments. Traditional centralized intrusion detection approaches and conventional federated learning (FL) frameworks, which rely on single-model aggregation, are often inadequate in the presence of extreme non-IID data and adversarial conditions. This study proposes an Adaptive Multi-Model Hierarchical Federated Learning (AMM-HFL) framework for robust IoT intrusion detection. The framework operates across client, edge, and cloud tiers and introduces a unified integration of similarity-aware clustering, multi-model aggregation, and dynamic client-side model selection. Unlike existing hierarchical FL approaches, AMM-HFL maintains multiple global models, enabling adaptive personalization and improved representation of heterogeneous data distributions. At the edge level, model updates are clustered to isolate anomalous contributions, while the cloud performs meta-aggregation to refine diverse model representations. Experimental evaluation on the IDSIoT2024 dataset demonstrates detection accuracy up to 96.83–97.54% under IID and 95.64–97.52% under non-IID conditions, while maintaining low computational and cryptographic overhead. Full article

The article develops a hybrid multimodal neural network for the automatic prevention of personal digital rights violations, focusing on improving security through anomaly detection and ensuring data confidentiality. The main aim is to integrate several innovative methods, such as federated learning, gating, latent competitive learning, and a variational autoencoder, to improve violation detection accuracy. The key contribution is the development of a training mixture that combines a probabilistic anomaly detector and an autoencoder reconstruction signal, which allows for effective detection of typical incidents and hidden anomalies. The experimental evaluation results showed high-performance indicators, with ROC-AUC at 0.96 and accuracy at 0.94, confirming the system’s effectiveness on anonymized data. The results obtained have a significant practical contribution, as they can be integrated into national information security systems, including SOC and forensic reports, which will ensure a higher level of personal data protection and reduce privacy breach risks. The scope of the proposed system simultaneously covers cybersecurity, personal data protection, national security, SOC systems, and forensic analysis. Full article

Home energy management systems (HEMS) aim to provide intelligent control of the thermal comfort inside smart buildings with the minimum energy cost, while satisfying the energy consumption requests and increasing the use of energy from renewable sources. The capabilities of these intelligent HEMS agents are restricted due to the personalized observability of the environment, resulting in limited knowledge gathering and potentially sub-optimal decisions. Furthermore, several buildings have recently been organized into small energy communities, with the ultimate goal of sharing intelligence between agents in federated learning schemes.In this context, we propose a personalized federated deep reinforcement learning method using Moreau envelopes (pFedMe) for joint energy cost and household comfort optimization in energy communities that consist of multiple smart homes. Specifically, a Twin-Delayed Deep Deterministic Policy Gradient (TD3) actor–critic model is introduced, dynamically observing the state of the smart home environment and suggesting control actions on the operation of the Energy Storage System and on the regulation of the indoor temperature. The TD3 actor–critic model leads to improved policy performance in the continuous control of these systems, mitigating the overestimation bias and improving the training stability of the intelligent agents. The efficiency of the proposed method is verified via simulations based on real data, achieving a beneficial trade-off between the energy cost and the thermal comfort compared to FedAvg and Fedprox baselines. The results show that the proposed pFedMe framework consistently outperforms FedAvg and FedProx in both convergence speed and overall reward, achieving an energy cost reduction of approximately 10% compared to the other schemes, while exhibiting marginal thermal comfort behavior. Full article

Sixth-generation (6G) networks are expected to provide ubiquitous connectivity, AI-native orchestration, and seamless integration across terrestrial and non-terrestrial infrastructures. However, these capabilities introduce new privacy challenges related to the classification and protection of personal, quasi-personal, and non-personal data in complex data-driven environments. This paper presents a systematic review of 78 peer-reviewed studies published between 2019 and 2025. Following a PRISMA-based methodology, this review analyzes privacy-enhancing technologies (PETs), regulatory compliance frameworks, and architectural patterns for privacy preservation in 6G networks. The findings show that differential privacy (DP) and federated learning (FL) dominate current research, accounting for nearly 52% of the reviewed studies. Blockchain auditing and zero-knowledge proofs (ZKPs) collectively represent approximately 30%, while the remaining mechanisms, including physical-layer security (PLS), trusted execution environments (TEEs), homomorphic encryption (HE), secure multi-party computation (SMPC), and anonymization, account for roughly 18%. These mechanisms exhibit varying levels of privacy strength, utility preservation, latency, and energy cost. At the same time, evolving regulatory frameworks, including GDPR, PDPL, CCPA/CPRA, LGPD, and PIPL, increasingly extend privacy obligations to quasi-personal and aggregated data. Building on these findings, this paper proposes a unified taxonomy that clarifies the boundary between personal and non-personal data. It also provides a cross-layer mapping between PETs and compliance requirements across the Core/SBA, RAN, Edge/MEC, and NTN layers. Finally, this paper presents a forward-looking roadmap for 2025–2030, highlighting hybrid PET pipelines, post-quantum auditability, and AI-driven compliance automation as key directions for privacy-preserving 6G standardization. Full article

Medical image federated learning has emerged as a practical solution for multi-center collaboration without centralizing sensitive data. However, the dominant source of heterogeneity in medical imaging is often not merely at the statistical level but also at the mechanism level, arising from scanner vendors, acquisition protocols, reconstruction pipelines, and annotation styles. Such heterogeneity encourages models to rely on site-specific shortcuts rather than pathology-relevant signals, which leads to poor external-site generalization. To address this problem, we propose CarPe-FL, which is a causal representation-based personalized federated learning framework for medical imaging. CarPe-FL maps images into a latent factor space, estimates client-specific latent causal structures under server-side management, clusters institutions according to structural similarity, and constructs cluster-wise global causal backbones. These backbones are then injected into federated representation learning through structure-aligned masking and edge-wise personalization, while personalized heads capture institution-specific prediction behavior. In this way, CarPe-FL aims to suppress shortcut-dependent pathways while preserving clinically meaningful local adaptation. The proposed framework is expected to provide a principled solution for robust, personalized, and interpretable federated learning in multi-center medical imaging. Full article

Tomato leaf diseases represent a persistent threat to global food security, causing annual crop losses of 20% to 40%. Although deep learning models achieve accuracies exceeding 95% in centralized settings, their deployment across distributed farms is constrained by data privacy concerns, communication bottlenecks, and heterogeneous data quality. This paper proposes Personalized, Clustered, and Communication-Efficient Federated Learning (PCE-FL), a framework that integrates three synergistic components: (1) server-side client clustering to group farms with similar data distributions for personalized model training; (2) federated knowledge distillation to reduce communication overhead by over 91%; and (3) reputation-based aggregation to ensure robustness against unreliable contributions. Extensive experiments on realistic non-IID simulations of the PlantVillage tomato dataset Dirichlet($\alpha \in \{1.0,0.5,0.1\}$) demonstrate that PCE-FL achieves 89.1% accuracy under extreme heterogeneity ($\alpha =0.1$), surpassing FedAvg by 10.9 and IFCA by 4.8 percentage points, while maintaining a 91% reduction in communication cost. All improvements are statistically significant ($p<0.001$). These results advance the practical deployment of privacy-preserving collaborative AI in resource-constrained agricultural environments. Full article

Advancing athlete health requires a shift from reactive sports medicine toward proactive, personalized, and longitudinal care. This article presents a conceptual framework for an Interdisciplinary AI Center for Longevity and Well-Being designed to integrate Artificial Intelligence of Things (AIoT), wearable sensing, and multimodal analytics into a unified athlete health ecosystem. The manuscript contextualizes the proposed framework with relevant literature across key technical domains and presents a reference edge–fog–cloud architecture together with a proof-of-concept dashboard pipeline to illustrate technical feasibility. Within this framework, heterogeneous data streams from wearable physiological sensors, biomechanical devices, non-invasive biomarker monitors, and environmental trackers are organized to support multimodal analysis and individualized performance intelligence. The paper outlines five target application domains: real-time health monitoring, injury risk assessment, performance optimization, holistic well-being evaluation, and longevity-oriented health management. Privacy-preserving and interpretable AI components, including federated learning, differential privacy, and explainability-oriented design considerations, are presented as key architectural priorities, while several elements are explicitly identified as future development directions. Rather than claiming full real-world validation, this work provides an interdisciplinary blueprint and prototype-informed foundation for future research and implementation at the intersection of computer science, biomedical engineering, and sports science. Full article

The safety of workers in industrial settings is ensured through the correct use of Personal Protective Equipment (PPE). The use of such equipment can be monitored using Deep Learning (DL). Federated Machine Learning (FML) is a technique that can be used in this context to preserve the privacy of sensitive information and provide explainability for the models adopted. Explainability techniques are an essential resource for interpreting the classification performed by the model. In this regard, this study aims to evaluate, through the adoption of specific similarity indices, the robustness and consistency of the explainability algorithms adopted to identify the areas of the images that are decisive for PPE classification. The dataset consists of 1600 real images representing work environments, in which staff are portrayed both with and without Personal Protective Equipment; specifically, there are workers wearing helmets, workers wearing reflective vests, workers wearing both devices and, finally, workers without any PPE. SSIM, VIF and SCC are the most relevant indices involved in the study. In the experimental phase, their mean values stand at 0.99, 0.96 and 0.96 for the intra-client study, and 0.96, 0.91 and 0.71 in the inter-client analysis. Full article

Plant disease diagnosis in real-world agricultural environments is challenged by data scarcity, domain shift, privacy constraints, and limited edge-device resources. This paper proposes FMEL-FSDA, a Federated Multimodal Edge Learning framework with Few-Shot Domain Adaptation for robust field-based plant disease recognition. The framework integrates attention-based RGB–text feature fusion, privacy-preserving federated learning, rapid few-shot personalization, and uncertainty-aware inference within an edge-efficient architecture. Federated training enables collaborative learning across distributed farms without sharing raw data, while few-shot adaptation allows fast deployment to new regions using only 1–10 labeled samples per class. Experiments on the PlantWild in-the-wild dataset show that FMEL-FSDA outperforms centralized, federated, and few-shot baselines, achieving 93.78% accuracy, 93.33% F1-score, and 0.97 AUC. The model maintains strong performance under privacy mechanisms such as gradient perturbation and secure aggregation, reduces communication overhead by up to 4×, and supports low-latency edge inference. Uncertainty estimation and Grad-CAM-based explainability further enhance reliability by identifying low-confidence cases and highlighting disease-relevant regions. Overall, FMEL-FSDA offers a scalable, privacy-aware, and field-ready solution for intelligent plant disease diagnosis in precision agriculture. Full article

Understanding user behavior on the web is considered essential for personalization, recommendation, and anomaly detection. Centralized analytics approaches raise significant privacy risks and regulatory concerns, particularly when large volumes of interaction data are collected in the cloud. Federated learning offers a decentralized alternative but faces challenges in handling heterogeneous, Non-Independently and Identically Distributed (non-IID) web interaction data. This paper presents FogLearn-Web, a fog computing-based federated learning framework for privacy-preserving web user behavior analytics. The architecture employs hierarchical aggregation in which browser-embedded models train locally, fog nodes perform behavior-aware regional aggregation, and the cloud maintains a global model with formal differential privacy guarantees. A key contribution is the behavioral sketch, a compact representation of local interaction distributions that enables attention-weighted federated averaging without exposing raw data. Experiments on benchmark and real-world datasets show that FogLearn-Web achieves within 2.3% of centralized accuracy while reducing data transmission by 89% and improving convergence under non-IID settings by 34% over standard FedAvg. Full article