Long-term, flexible therapy strategies are needed for chronic diseases like cardiovascular ailments, diabetes, and chronic kidney disease and they have to deal with patient heterogeneity, changing physiological states and privacy constraints. This research suggests a framework for privacy-preserving and personalized artificial intelligence that combines Federated Learning (FL), a Res-HyperTransformerNet deep prediction model, Personalized Multi-Agent Reinforcement Learning (PMARL) and Explainable Artificial Intelligence (XAI) for adaptive chronic disease management. The framework is structured with two main aims: (i) to create an accurate and privacy-aware predictive model for chronic disease risk using diverse data sources, and (ii) to permit adaptive, individual therapy optimization through multi-agent reinforcement learning. Federated learning is utilized to conduct the training of Res-HyperTransformerNet over distributed Internet of Medical Things (IoMT) nodes without the requirement of transferring raw patient data. The embeddings that are created from patient data are then passed on to a PMARL module, where several agents optimize therapy dimensions like medications, diet, physical activity, and mental health interventions independently. To make the clinical support more understandable, the SHAP-based explainability method is used for both predictive and decision-making parts. The framework is tested using two public datasets—the CDC Chronic Disease dataset and the UCI Chronic Kidney Disease Risk Factor dataset. The performance is measured by employing classification metrics (accuracy, precision, recall, F1-score, MCC) as well as reinforcement learning metrics (reward score, convergence steps, episode return) and federated system metrics (communication overhead, convergence rounds, and training time). The experiments indicate that the proposed framework demonstrated improved performance in terms of predictive accuracy and policy convergence speed compared to the baseline deep learning and reinforcement learning models, and at the same time it is more cost-effective when it comes to communication in a federated setting. This means that the proposed method suggests the potential of being a reproducible and open AI framework for adaptive chronic disease therapy management. The combination of ResNet and Transformer blocks, i.e., Federated Res-HyperTransformerNet, achieved strong performance in both datasets, namely CDC Chronic Disease (Dataset 1) and UCI CKD Risk Factor (Dataset 2). The obtained accuracy for Dataset 1 was 98.61% and for Dataset 2, it was 97.75%, under the conducted experimental settings.
Journal of Reliable and Secure Computing · مجلد 2 (1) · 1-26
The rapid proliferation of smart home IoT devices has introduced unprecedented cybersecurity vulnerabilities, necessitating scalable and privacy-preserving intrusion detection systems (IDS). Federated Learning (FL) offers a promising decentralized approach by training models locally without sharing raw data, but it remains susceptible to poisoning attacks and relies on a vulnerable central aggregator. This paper presents a novel blockchain-enhanced FL framework tailored for smart home IDS, integrating multiple consensus mechanisms—Proof-of-Stake (PoS), Practical Byzantine Fault Tolerance (PBFT), and Proof-of-Authority (PoA)—for the first time in this context. Our approach uniquely combines differential privacy (DP) and secure aggregation (SA) within a blockchain-managed workflow to mitigate gradient inversion and membership inference attacks while ensuring tamper-resistant, decentralized trust. Experimental evaluation using the N-BaIoT dataset demonstrates that the proposed system achieves up to 88.3% detection accuracy with manageable latency (~200 ms/round) and formal privacy guarantees ($\varepsilon$=1.0 DP). The framework introduces 52.8% system overhead compared to vanilla FL—a reasonable trade-off for enhanced security and privacy. This work establishes a robust, transparent, and scalable security infrastructure for smart homes, effectively addressing the limitations of both centralized and conventional FL-based IDS.
Frontiers of Multidisciplinary Research · مجلد 1 (2)
Smart homes utilize Internet of Things (IoT) products to increase convenience and automation, but this also makes them vulnerable to various cybersecurity risks. Traditional centralized Intrusion Detection Systems (IDSs) have limitations, such as single points of failure and issues with privacy, scalability, and accuracy. In this review, we discuss the potential of Federated Learning and blockchain for intrusion detection in smart homes, addressing the limitations of traditional IDSs. A Systematic Literature Review (SLR) was conducted to analyze the use of the blockchain framework, consensus algorithms, and methods for enhancing the framework, such as implementing lightweight frameworks, Edge Computing, model compression, and intelligent contract optimization. The findings of the literature review suggest that the proposed framework improves the system's resistance to attacks, the model's accuracy (>90%), and its integrity through the blockchain's tamper-proof mechanism. However, it also presents challenges in scalability and other areas, so the focus should be on using this framework in the real world to meet the needs of the intrusion detection mechanism in a smart home.
federated learningblockchainsmart home securityintrusion detection systems
Network and Communication Technologies · مجلد 10 (1) · 1-1
The rapid expansion of Internet of Things (IoT) devices has fundamentally reshaped traditional homes into highly interconnected smart environments, driving unprecedented convenience while simultaneously exposing critical cybersecurity vulnerabilities. Conventional centralized Intrusion Detection Systems (IDS) are increasingly inadequate for smart homes, owing to inherent privacy issues, latency, and susceptibility to single points of failure. Federated Learning (FL) offers a promising, privacy-preserving paradigm by enabling collaborative model training without the exchange of raw user data; however, FL remains vulnerable to model poisoning and integrity attacks. This comprehensive review systematically examines the integration of blockchain technology as a means to secure FL-based IDS in smart home contexts. We critically evaluate diverse blockchain frameworks, consensus protocols, and enhancement strategies that underpin the development of trustworthy, transparent, and resilient security architectures. Specifically, the review addresses two core research questions: (1) In what ways are blockchain frameworks and consensus mechanisms leveraged to secure FL-based IDS? and (2) What enhancement techniques and hybrid models are implemented to optimize the performance and efficiency of these integrated systems? Our synthesis reveals that permissioned blockchains—particularly those employing Proof of Authority (PoA) and Practical Byzantine Fault Tolerance (PBFT) consensus mechanisms—when combined with edge computing and lightweight architectural designs, deliver robust security while meeting the resource constraints characteristic of IoT devices. This technological synergy not only strengthens the resilience of the FL process but also advances the development of next-generation, secure smart home ecosystems.
The Internet of Things (IoT) consists of physical objects and devices embedded with network connectivity, software, and sensors to collect and transmit data. The development of the Internet of Things (IoT) has led to various security and privacy issues, including distributed denial-of-service (DDoS) attacks. Conventional attack detection methods face significant challenges related to privacy, scalability, and adaptability due to the dynamic nature of IoT environments. To address these limitations, this research proposes GraphFedAI, a novel framework that integrates adaptive session-based graph modeling, Pearson correlation-guided feature selection, interpolation-aware graph neural network (GNN) training, and federated learning to enable robust, scalable, and privacy-preserving DDoS detection in heterogeneous Internet of Things (IoT) networks.The framework represents the IoT network as dynamic graphs where communication patterns among devices are modeled as edges that evolve over time. Graph neural networks are utilized to extract both temporal and structural features from these graphs, thereby enhancing the accuracy of DDoS detection. Federated learning is incorporated to maintain data privacy by training models locally on each device without sharing raw data. This integration also ensures system scalability, as FL adapts training based on localized network topology.The system is evaluated using the CIC-IoT-2023 dataset, demonstrating its effectiveness in achieving high detection accuracy, low false positive rates, and strong resilience under dynamic IoT conditions.
DDoS attack detectionInternet of Things securityfederated learninggraph neural networks
EURASIP Journal on Wireless Communications and Networking · مجلد 2025 (1)
Abstract Dynamic situations and applications are supported by the diverse devices and communication technologies that constitute the Internet of Things concept. Despite this, communication backlogs are common due to rising network demand and insufficient resource allocation. This study provides a way to fix resource allocation problems using Mutable Resource Allocation and Distributed Federated Learning. Inadequacies and backlogs in resources are identified at the edge of the network. As part of this procedure, edge devices are assigned to link resources and users after independently determining which resources cannot be allocated and which shortcomings are linked with them. Adapting to demand and learning suggestions, this allocation is flexible. By classifying resources as sufficient or inadequate, the learning suggestions help avoid backlogs. This enables edge devices to choose between allocation and response, which improves network flexibility by prioritizing inadequate resource allocation. Accordingly, the recommendation factor periodically affects modifications to the edge connection and its interaction with the Internet of Things platform. The suggestion is particularly strong for situations with changing backlogs to ensure that subsequent resource allocations align with preference-based learning. Claiming to improve connection, services, and resource allocation while decreasing backlogs and allocation times, this approach is a hot commodity.
dynamic resource allocationdecentralized federated learningedge computingInternet of Things
International Journal of Computational Intelligence Systems · مجلد 18 (1)
Credit risk assessment uses finance-based behavioural patterns for micro-lending purposes and organizations. The repayment behaviour and credit stability patterns are analyzed across varying repayment tenures and financed amounts. Due to limited borrower data and fluctuating financial patterns, micro-lending platforms have substantial hurdles when it comes to effectively evaluating credit risk. This article introduces a Collaborative Filtering Method using Lending Pattern Analysis (CFM-LPA). The proposed method is enhanced through collaborative federated learning, enabling the analysis of these patterns. This approach evaluates the return rate, credit limit, and consumer response behaviours. Federated learning processes one or more of these factors to assess diverse lending patterns. Based on these evaluations, the behavioural factor is updated for each return period, influencing the credit risk for subsequent return periods and supporting the financial stability of micro-lending operations. The model is trained individually on the identified factors, allowing the behavioural factor to be filtered. New credit risks are identified using this filtered factor from the previous return period. These insights help define new behavioural patterns for the specified credit limit. The proposed method enhances risk detection accuracy by 14.03% and improves return rate analysis by 13.28% across financed amounts. The above abstract is also graphically presented.
Epilepsy represents a widespread neurological disorder that causes unexpected seizure occurrences which produce significant obstacles for daily life activities in people worldwide. Real-time seizure detection accuracy stands vital for safeguarding patients while ensuring timely interventions and bettering their quality of life. The present seizure detection methods suffer from multiple limitations including poor applicability across different cases and excessive incorrect alerts and inefficient feature selection procedures. Traditional deep learning algorithms generally fail to detect EEG patterns with both temporal and spatial characteristics thereby producing subpar results in practical settings. This study proposes EpilepNet-LD integrated with federated learning (FL), a novel framework for decentralized EEG analysis that preserves patient privacy while enabling collaborative model training. The framework employs a hybrid harmony search and mutual information (HSA-MI) feature selection technique to identify optimal temporal, spectral, and spatial EEG features, reducing computational overhead. The EpilepNet-LD architecture combines long short-term memory (LSTM) networks to capture temporal dependencies with DenseNet-121 to extract hierarchical spatial features, improving seizure detection performance. Extensive experimental evaluations confirmed the proposed method achieves 99.41% extensive experiments demonstrate that the proposed method achieves 99.41% accuracy and 99.50% sensitivity, outperforming existing state-of-the-art approaches. The integrated FL and HSA-MI approach, coupled with the EpilepNet-LD classifier, enables robust, real-time, and high-precision seizure detection, offering a reliable solution for advanced epilepsy monitoring and management.
epilepsyseizure detectionfederated learningmutual information feature selection
Brain Research Bulletin · مجلد 233 · 111645-111645
Epilepsy is a critical neurological disorder that requires accurate and privacy-preserving diagnostic solutions to enable early detection and effective management. However, existing approaches face key challenges, including reliance on centralized data, poor generalizability across modalities, suboptimal feature extraction, and vulnerability to noise. To address these issues, we propose MultiEpilepsyNet, a novel multimodal seizure detection framework that integrates federated learning with hybrid deep learning models. At its core, the system introduces SeizureFed-Net, a federated architecture that enables collaborative learning from EEG and MRI data while safeguarding patient privacy. For detection, we design SeizureShieldNet, a hybrid model that fuses the temporal learning capabilities of BBIDNet (Boosted BiLSTM Intrusion Detector Network) with the adaptive decision-making of FD-TMS (Fuzzy-DQN Threat Mitigation System) under uncertainty. To further enhance model efficiency, a Jackal-Wolf Hybrid Optimizer (JWHO)-a novel combination of Golden Jackal Optimization and Grey Wolf Optimizer-is employed for optimal feature subset selection. On the imaging side, MRI preprocessing is improved through EpiSkullNet+ +, a modified 3D UNet+ + architecture tailored for precise brain segmentation. Extensive experiments on two benchmark datasets demonstrate the superiority of our approach, achieving 99.36 % accuracy on the CHB-MIT EEG dataset and 99.38 % accuracy on an epilepsy MRI dataset. Beyond accuracy, MultiEpilepsyNet demonstrates improved robustness to missing modalities, reduced training overhead via federated aggregation, and enhanced privacy preservation compared to centralized deep learning models, thereby addressing critical barriers in practical clinical deployment. These outcomes highlight the effectiveness, scalability, and real-world clinical potential of the proposed framework for epilepsy diagnosis and management.
Journal of Circuits Systems and Computers · مجلد 35 (07)
Current developments on the Internet of Things (IoT) have completely changed the landscape of Consumer Electronics (CE), enabling next-generation gadgets to be highly intelligent, networked and capable of utilizing large models. In addition to improving data accessibility, this improved connectivity between sensors, actuators and appliances allows autonomous control inside CE networks. Although deep learning models are highly effective in analyzing large amounts of data, controlling the intricacy of deep learning-based intrusion detection in low-latency IoT networks continues to be a formidable task. This paper presents a deep learning-based intrusion detection technique inspired by federated learning (FL), specifically designed for SDN-enabled CE networks. The application of the approach involves stringent training and testing protocols. In order to improve performance and handle the very complicated training data, the Pearson correlation coefficient (PCC) approach of feature selection (FS) is used in this work. Based on the UNSW-NB15 attack detection dataset, the results show that this approach performs better than other current security solutions, making it a promising option for next-generation smart CE networks. Comprehensive experimental evaluations demonstrated the value of the suggested intrusion detection system (IDS), which demonstrated exceptional intrusion detection accuracy in every domain under investigation.
intrusion detectionfederated learningInternet of Things securitysmart home networks
The number of people with kidney disease rises every day for many reasons. Many existing machine-learning-enabled mechanisms for processing kidney disease suffer from long delays and consume much more resources during processing. In this paper, the study shows how federated and reinforcement learning schemes can be used to develop the best delay scheme. The scheme must optimize both the internal and external states of reinforcement learning and the federated learning fog cloud network. This work presents the Adaptive Federated Reinforcement Learning-Enabled System (AFRLS) for Internet of Things (IoT) consumers’ kidney disease image processing. The main relationship between IoT consumers and kidney image is that the data is collected from different IoT consumer sources, such as ultrasound and X-rays in healthcare clinics. In healthcare applications, kidney urinary tasks reduce the time it takes to preprocess federated learning datasets for training and testing and run them on different fog and cloud nodes. AFRLS decides the scheduling on other nodes and improves constraints based on the decision tree. Based on the simulation results, AFRLS is a new strategy that reduces the time tasks need to be delayed compared to other machine learning methods used in fog cloud networks. The AFRLS improved the delay among nodes by 55%, the delay among internal states by 40%, and the training and testing delay by 51%.
The traditional single-context recommendation algorithm is constrained by the sparse connection between users and items and a user/item cold start problem. Based on the review, the text-based cross-context recommendation algorithm extracts user/item comment information in the auxiliary context to alleviate the target context’s data sparsity problem and improve recommendation accuracy. A cross-context recommendation strategy based on self-attention-based federated learning (SAFL) is suggested in this work. In contrast to current algorithms, SAFL fully mixes the target and auxiliary background information. Federated learning addresses crucial challenges including data privacy, data security, data access rights, and access to heterogeneous data by allowing several players to develop a single, strong machine learning model without sharing data. To begin, self-attention mechanism is introduced to model the user’s preference information; then, the information from one field is used to improve the recommendation accuracy of another area; and finally, the information from the two contexts is integrated into the knowledge fusion module and the score prediction module to predict the score. Experiments on the Amazon dataset indicate that MAE and MSE values of SAFL are higher when compared to the current cross-context recommendation model, MAE values rose by 8.4%, 13.2%, and 19.4% across three cross-context datasets.
IEEE Transactions on Computational Social Systems · مجلد 10 (4) · 1722-1731
Traditional classification algorithms struggle to categorize hypertensive retinopathy (HR) lesions correctly because they lack obvious characteristics. A regional IoT-enabled federated learning-based HR categorization approach (IoT-FHR) incorporating global and local attributes is suggested as a solution to this issue. The local feature arterial and venous nicking (AVN) classification model is fused with the overall IoT-FHR classification model to enhance the effect of the classification of IoT-FHR. The AVN classification model’s local lesion characteristics and the IoT-FHR classification model’s global lesion characteristics were combined using feature mean. After that, the results of the global IoT-FHR classification model are averaged with the results of the local AVN classification model. An easy neural network receives its input from the final outcome. The probability value of IoT-FHR in the fundus image is output by the sigmoid classifier after the neural network’s two fully connected and one dropout layer. The AVN classification makes a new kind of intersection detection algorithm suggestion. To determine the intersection points, the algorithm applies a logical AND operation to the classified arteries and veins. It takes HR fundus pictures and extracts AVN image blocks using the region of interest extraction approach. The accuracy, sensitivity, and specificity of the suggested fusion model are 93.50%, 69.83%, and 98.33%, respectively, when tested on a private dataset. It is clear from the experiments and results that the suggested model leads the currently used methods when the single-stage classification model is compared with them.
hypertensive retinopathyretinal lesion classificationfederated learningInternet of Things