arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.00192cs.LGcs.CV
收藏

优化的混合特征工程用于ECG信号中资源高效的心律失常检测:一种优化框架

Optimized Hybrid Feature Engineering for Resource-Efficient Arrhythmia Detection in ECG Signals: An Optimization Framework

Department of Computer Science and Engineering, Dibrugarh University Institute of Engineering and Technology (DUIET), Dibrugarh University(计算机科学与工程系,迪布加鲁希大学工程技术学院(DUIET),迪布加鲁希大学);Department of Physical Medicine and Rehabilitation, Regional Institute of Medical Sciences(物理医学与康复系,区域医学科学研究所)

Moirangthem Tiken Singh, Manibhushan Yaikhom

AI总结:

本研究提出一种优化的混合特征工程框架,通过结合小波分解和图论描述符,实现资源高效的ECG信号心律失常检测,达到98.44%的准确率和8.54 KB的模型大小。

摘要:

心血管疾病,特别是心律失常,仍然是全球死亡率的主要原因,需要通过互联网医疗物联网(IoMT)进行持续监测。然而,最先进的深度学习方法往往带来不可接受的计算开销,使其不适合资源受限的边缘设备。本研究提出了一种以数据为中心的资源高效框架,优先考虑特征工程而非复杂性。我们的优化流程使复杂的、高维的心律失常数据线性可分。这通过将时频小波分解与图论结构描述符(如PageRank中心性)相结合来实现。这种混合特征空间随后通过互信息和递归消除进行优化,使可解释的、超轻量的线性分类器成为可能。在MIT-BIH和INCART数据集上的验证结果显示出98.44%的诊断准确率,模型大小为8.54 KB。系统在每心跳管程内达到0.46 μs的分类推断延迟,确保了实时操作。这些成果在压缩模型(如KD-Light(25 KB,96.32%准确率))方面提供了数量级的效率提升,推动了无电池心脏传感器的发展。

英文摘要:

Cardiovascular diseases, particularly arrhythmias, remain a leading global cause of mortality, necessitating continuous monitoring via the Internet of Medical Things (IoMT). However, state-of-the-art deep learning approaches often impose prohibitive computational overheads, rendering them unsuitable for resource-constrained edge devices. This study proposes a resource-efficient, data-centric framework that prioritizes feature engineering over complexity. Our optimized pipeline makes the complex, high-dimensional arrhythmia data linearly separable. This is achieved by integrating time-frequency wavelet decompositions with graph-theoretic structural descriptors, such as PageRank centrality. This hybrid feature space, combining wavelet decompositions and graph-theoretic descriptors, is then refined using mutual information and recursive elimination, enabling interpretable, ultra-lightweight linear classifiers. Validation on the MIT-BIH and INCART datasets yields 98.44% diagnostic accuracy with an 8.54 KB model footprint. The system achieves 0.46 $μ$s classification inference latency within a 52 ms per-beat pipeline, ensuring real-time operation. These outcomes provide an order-of-magnitude efficiency gain over compressed models, such as KD-Light (25 KB, 96.32% accuracy), advancing battery-less cardiac sensors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑