Reproducibility capsule for FusionNet Lite, a lightweight sequence-fusion deep-learning pipeline for predictive maintenance in industrial IoT systems. The campaign evaluates FusionNet Lite alongside CNN, BiLSTM, MLP, and CNN-LSTM baselines using centralized and FedAvg federated training across five seeds. The capsule includes leakage-safe preprocessing, stratified AI4I splitting, event-aware chronological MetroPT3 splitting with all rows retained, Dirichlet label non-IID client allocation, integrated-gradients analysis, statistical comparisons, publication tables and figures, and a consistency audit. Dataset files are placeholders in this capsule. Full reproducible execution requires attaching the authorised AI4I 2020 and MetroPT3 datasets under /data before selecting full mode.
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without directly exchanging data. However, traditional FL methods often rely on a central server, raising significant privacy concerns, especially when dealing with sensitive data residing on edge devices. This paper proposes a decentralized federated learning framework incorporating differential privacy to mitigate these risks. The core idea is to eliminate the central server and enable collaborative learning directly among edge devices, while simultaneously safeguarding individual data privacy using differential privacy mechanisms. Our approach utilizes a novel decentralized algorithm that leverages local model updates and a privacy-preserving aggregation protocol. We demonstrate the effectiveness of this framework through a theoretical analysis and provide a detailed formulation of the decentralized FL process. The key mathematical formulations related to the algorithm are presented, including the privacy loss budget calculation, local model updates, and the aggregated model update. This work contributes to the development of robust and privacy-preserving FL solutions for edge computing environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Acute lateral ankle sprain is among the most frequent injuries in sports medicine, and its high recurrence rate and propensity toward chronic ankle instability (CAI) constitute a persistent clinical challenge. Conventional risk assessment—relying on subjective questionnaires, physical examination, and clinical experience—captures only part of the complex biomechanical and neuromuscular adaptations that follow an initial sprain. Recent advances in objective biomechanical profiling and machine learning (ML) have opened a new paradigm for individualized recurrence prediction. This review synthesizes the full translational chain from biomechanical marker identification to ML-based risk prediction. We first summarize key markers spanning gait kinetics (ground reaction forces and joint moments), proprioceptive and neuromuscular control deficits, and dynamic postural stability, highlighting the representational advantages of multimodal data fusion. We then compare mainstream ML architectures—including tree-based ensembles, recurrent networks for gait time series, and strategies for small-sample learning—and discuss the role of explainable artificial intelligence (XAI) in linking predictions to injury mechanisms. Evidence indicates that models integrating multimodal biomechanical features outperform conventional clinical scores (e.g., Ankle-GO, AUC 0.70), with few-shot learning systems achieving test accuracies of 0.89 and inertial-sensor-driven recurrent networks estimating ankle kinematics with coefficients of determination up to 0.93. Finally, we evaluate validation strategies, clinical utility in rehabilitation prescription and return-to-sport decisions, and wearable-based long-term monitoring, and we dissect the outstanding challenges of data standardization, model interpretability, annotation scarcity, and ethical governance. Emerging technologies—digital twins, federated learning, and generative AI for data augmentation—offer plausible routes toward a precise, interpretable, and equitable intelligent prevention ecosystem for recurrent ankle sprain.
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without directly exchanging data. However, traditional FL methods often rely on a central server, raising significant privacy concerns, especially when dealing with sensitive data residing on edge devices. This paper proposes a decentralized federated learning framework incorporating differential privacy to mitigate these risks. The core idea is to eliminate the central server and enable collaborative learning directly among edge devices, while simultaneously safeguarding individual data privacy using differential privacy mechanisms. Our approach utilizes a novel decentralized algorithm that leverages local model updates and a privacy-preserving aggregation protocol. We demonstrate the effectiveness of this framework through a theoretical analysis and provide a detailed formulation of the decentralized FL process. The key mathematical formulations related to the algorithm are presented, including the privacy loss budget calculation, local model updates, and the aggregated model update. This work contributes to the development of robust and privacy-preserving FL solutions for edge computing environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without direct data sharing. However, traditional FL schemes are vulnerable to privacy attacks, particularly model inversion attacks, which can reveal sensitive information about the underlying data. This paper proposes a novel decentralized federated learning framework that integrates secure aggregation and differential privacy to mitigate these risks. The system utilizes secure aggregation techniques, such as homomorphic encryption, to protect individual model updates during the aggregation process. Simultaneously, differential privacy mechanisms are employed to limit the amount of information leaked about individual clients' data. The decentralized nature of the framework enhances robustness and scalability. This approach significantly strengthens the privacy guarantees of FL while maintaining model accuracy and efficiency. The core claim of this work is that enhancing security and privacy is crucial for the wider adoption of federated learning. The proposed mechanism combines secure aggregation and differential privacy in a decentralized federated learning framework.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Residential load forecasting underpins demand response and local energy trading, yet privacy regulations such as the EU GDPR prevent service providers from collecting fine-grained household consumption data. Federated learning (FL) enables collaborative training without raw data exchange, and client clustering widely mitigates accuracy degradation caused by non-IID residential load distributions. However, existing clustering benchmarks only compare grouped schemes against a single global FL model, ignoring household-specific fine-tuning as a strong personalized baseline. This work constructs a personalization-fair benchmark to quantify the true value of client clustering for residential load forecasting. Six FL strategies are evaluated across three data heterogeneity regimes built on two real-world smart meter datasets. Results show clustering reduces forecasting errors by up to 26% at the cluster-model stage, yet after household fine-tuning all methods land within 2% of the global model and deliver nearly identical performance; adaptive re-clustering brings no accuracy improvement over static grouping. The primary merit of clustering lies in communication efficiency, as clustered frameworks converge within one-third of the communication rounds required by the standard global model under highly heterogeneous PV prosumer portfolios. Finally, this paper releases an open Ausgrid benchmark with a temporal out-of-time evaluation protocol for follow-up federated load forecasting research.
Ran Zheng, Sara Barja-Martínez, Mònica Aragüés‐Peñalba et al.· Energy Reports· 0 citations
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without direct data sharing. However, traditional FL schemes are vulnerable to privacy attacks, particularly model inversion attacks, which can reveal sensitive information about the underlying data. This paper proposes a novel decentralized federated learning framework that integrates secure aggregation and differential privacy to mitigate these risks. The system utilizes secure aggregation techniques, such as homomorphic encryption, to protect individual model updates during the aggregation process. Simultaneously, differential privacy mechanisms are employed to limit the amount of information leaked about individual clients' data. The decentralized nature of the framework enhances robustness and scalability. This approach significantly strengthens the privacy guarantees of FL while maintaining model accuracy and efficiency. The core claim of this work is that enhancing security and privacy is crucial for the wider adoption of federated learning. The proposed mechanism combines secure aggregation and differential privacy in a decentralized federated learning framework.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This study examines the theoretical, structural, and empirical applications of Artificial Intelligence (AI) and Machine Learning (ML) architectures within the domain of regulatory compliance (RegTech) and supervisory technology (SupTech) for cross-border digital transactions. The exponential expansion of cross-border financial flows, real-time payment systems, and decentralized financial instruments has amplified regulatory fragmentation, multi-jurisdictional compliance friction, and sophisticated financial crime typologies. Utilizing institutional economics, information asymmetry theory, and computational compliance modeling, this paper analyzes how advanced algorithmic architectures—specifically Graph Neural Networks (GNNs), Natural Language Processing (NLP), and Federated Learning—optimize anti-money laundering (AML), counter-terrorist financing (CFT), and real-time sanctions screening. The findings demonstrate that shifting from legacy rule-based heuristics to adaptive, privacy-preserving AI frameworks significantly compresses false-positive rates, bridges cross-jurisdictional regulatory disparities, and establishes a dynamic, mathematically rigorous paradigm for global financial integrity.
Vakhabov Bobur· Zenodo (CERN European Organi...· 0 citations
Achieving strong differential privacy guarantees within the constraints of federated learning, especially when utilizing complex models, remains a significant challenge. This work proposes a novel framework leveraging Lagrangian relaxation to address this issue. The core idea involves incorporating a Lagrangian term directly into the federated learning objective function to formally represent the differential privacy constraint. This allows for an iterative solution of the resulting Lagrangian problem via distributed optimization, providing a controllable mechanism for balancing privacy and model accuracy. The proposed approach offers a more practical and scalable solution compared to existing methods, particularly in scenarios where precise control over the privacy-accuracy trade-off is desired. The effectiveness of this method is demonstrated through theoretical analysis and conceptual discussion, outlining a pathway for future research and implementation.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Modern eCommerce and enterprise systems have become more complex, which has prompted the use of the microservice architecture and sophisticated data integration strategies to provide scalability and resilience, as well as speed in the delivery of features. This chapter consolidates important architectural patterns, integration frameworks and operational models, assesses their advantages and shortcomings, and also provides some future research areas such as AI-based orchestration of microservices, policy-as-code to automate governance, edge-native integration and consistent performance testing suites. These lessons can inform researchers and practitioners on how to develop well-tested and highly scalable networks that can support the changing needs of modern online companies. In the future, the application of transfer learning techniques to generalize models in other application contexts and federated learning schemes to privately share models between organizational units while masking data privacy should be investigated.
Abstract Smart city traffic systems increasingly rely on edge intelligence and distributed learning to coordinate vehicles and infrastructure. However, many existing approaches prioritize system-level optimization while overlooking how humans perceive, interpret, and respond to automated decisions, limiting efficiency and real-world adoption. This paper proposes a human-centric edge intelligence framework that integrates federated reinforcement learning (FRL) with interpretable human–machine interfaces for urban traffic coordination. Vehicles and signalized intersections operate as decentralized learning agents, collaboratively optimizing traffic flow while retaining data locally. Human-centered constraints are embedded directly into the learning process through reward design and action-space restrictions, ensuring that system decisions can be expressed as clear, actionable guidance via augmented reality head-up displays and voice prompts. We present a layered edge architecture and a smart-intersection scenario to demonstrate how sensing, learning, communication, and human interaction are jointly coordinated. A simulation-based evaluation pipeline using SUMO and CARLA is introduced to examine corridor-level traffic dynamics, visual perception scenarios, and human-facing advisory interactions. SUMO is used for microscopic traffic-flow and signal-control modeling, while CARLA supports visual validation of safety-critical events and interface-level driver advisories. A dedicated SUMO–CARLA workflow diagram is provided to clarify how traffic-state generation, FRL decision-making, visual scenario reconstruction, and HMI advisory evaluation are connected. To ground the design in real-world evidence, we additionally report a descriptive trajectory analysis of the public NGSIM Peachtree Street dataset; this analysis characterizes speed, acceleration, and following-headway behavior and motivates the proposed reward and advisory-trigger design, but it is a descriptive/motivational analysis of existing trajectory data rather than an evaluation of the proposed FRL framework. This paper is explicitly positioned as a conceptual and methodological framework contribution: no FRL policy has been trained, no SUMO–CARLA simulation has been executed, and no quantitative comparison or ablation results are reported. These experiments constitute the planned next phase of this research program. Because the framework is part of an ongoing security-sensitive smart-city research effort, deployment-specific control interfaces and protected configuration details are reported at an abstracted level, while the non-sensitive simulation structure, evaluation metrics, and agent-level learning process are described for reproducibility. The proposed framework provides a practical pathway for evaluating intelligent mobility systems that balance decentralized optimization, privacy preservation, interpretability, scalability, and human-aligned operation.
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without directly sharing the data itself. However, this decentralized nature introduces significant vulnerabilities. Malicious participants, known as Byzantine nodes, can inject biased or corrupted models into the training process, compromising the overall model accuracy and potentially introducing harmful biases. This paper proposes a novel decentralized federated learning framework incorporating Byzantine Fault Tolerance (BFT) mechanisms. The core claim is that a BFT-enabled decentralized FL system provides robustness against malicious actors, guaranteeing model convergence even when some nodes are compromised. We outline the system architecture, detailing the BFT protocol integration, aggregation strategies, and communication protocols. The proposed system leverages a verifiable distributed consensus mechanism, allowing for the detection and mitigation of Byzantine behavior. The theoretical analysis demonstrates the system's resilience to arbitrary Byzantine failures and provides a framework for quantifying the impact of malicious participation. This work represents a significant advancement in securing FL deployments, fostering trust and reliability in collaborative learning environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
