Quantum-Assisted Federated Edge Intelligence With Authenticated Secure Aggregation for Wearable Arrhythmia Detection in IoMT

Document Type

Article

Source of Publication

IEEE Internet of Things Journal

Publication Date

8-15-2026

Abstract

Continuous wearable electrocardiogram monitoring has transformed cardiac assessment into an Internet of Medical Things problem. Yet, existing learning frameworks remain fragmented - addressing robustness, scalability, and cryptographic security separately while neglecting cross-layer deployment constraints. This article presents a unified cross-layer architecture that jointly designs lightweight wearable representation learning, edge-assisted variational quantum classification, Byzantine-resilient federated optimization, and standardized postquantum authenticated model exchange within a single IoT framework. The proposed system treats communication limits, latency budgets, and adversarial stability as first-class design variables. We establish nonconvex convergence guarantees under robust aggregation, PAC-style generalization bounds under heterogeneous client distributions, and explicit upper bounds on adversarial attack success growth. Evaluation on MIT-BIH with cross-dataset validation on PTB-XL demonstrates consistent macro-F1 gains over centralized and conventional federated baselines while preserving calibration quality and bounded communication cost. The results substantiate a deployment-aware secure cardiac intelligence architecture for next-generation IoT healthcare systems, supported by controlled comparisons against parameter-matched classical heads and measured cryptographic/system overheads. While the current evaluation is conducted under simulated NISQ and resource-constrained IoMT conditions, the framework is designed to support future validation on physical quantum and wearable-edge platforms.

ISSN

2327-4662

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Volume

13

Issue

16

First Page

38119

Last Page

38128

Disciplines

Computer Sciences | Medicine and Health Sciences

Keywords

Calibration, ECG arrhythmia detection, federated learning, Internet of Medical Things, postquantum cryptography, robust aggregation, variational quantum classifier

Scopus ID

105041980746

Indexed in Scopus

yes

Open Access

no

Share

COinS