arXiv:2611.16648 · v1

GNN-Enhanced TCN Algorithms for ECG Anomaly Detection

首次提交 2026-11-12 19:24

版本更新 2026-11-12 19:24

雷达观测 2026-11-13 14:15

摘要

To a time series can be also given the structure of directed graph, opening the doors to the usage of graph neural networks (GNNs) in this context. In this paper we develop a new pipeline involving novel geometric deep learning models that merge the capabilities of ordinary TCNs with the ones of GNNs to solve an anomaly detection problem on electrocardiogram signals.

作者备注：Follow-up to arXiv:2310.02774, which introduced a pipeline for an industrial dataset. A shortened version of that earlier paper appeared in the GSI 2025 proceedings. Here we extend the theoretical analysis and develop a pipeline tested on a benchmark dataset. Research conducted in 2025. Under journal peer review