基于时间-频率双域注意力融合的PPG信号失常的多重分类模型
Yubo Sun1, Keyu Meng2, Shipan Lang3
1College of Electronic Information Engineering, Changchun University, Changchun 130022, China.
Sensors (Basel, Switzerland)
|October 16, 2025
概括
一个新的深度学习模型,Fusion-DMA-Net,使用光电显微镜 (PPG) 信号准确检测心律失常. 这种非侵入性方法可以提高心血管疾病的早期诊断.
科学领域:
- 生物医学工程 生物医学工程
- 心脏病学 心脏病学
- 人工智能的人工智能
背景情况:
- 心律失常是心脏突然死亡的主要原因,需要早期检测和持续监测.
- 摄影电位图 (PPG) 信号提供了一种非侵入性,低成本的方法来评估心脏活动,但它们的非静止性和个体间的变化使心律失常的分类复杂化.
- 现有的方法与PPG信号的复杂性和可变性作斗争,以准确检测心律失常.
研究的目的:
- 开发一种先进的深度学习模型,使用PPG信号准确地分类心律失常.
- 为了应对PPG信号非静止性和个体间变异所带来的挑战.
- 通过加强PPG信号分析,改善心血管疾病的早期诊断和监测.
主要方法:
- 提出了一种新的融合深度多域注意网络 (融合-DMA-Net),采用跨度剩余注意结构.
- 实施了融合策略,使用交互式注意力,自我注意力和封闭机制来整合时间和频率域特征.
- 评估了模型在使用单通道PPG数据对四种主要类型的心律不整进行分类方面的表现.
主要成果:
- 融合-DMA-Net实现了卓越的分类性能,总体准确率为99.05%.
- 该模型在识别心律不整时表现出高精度 (99.06%) 和F1得分 (99.04%).
- 实验结果验证了该模型在从单通道PPG信号分类心律失常方面的有效性.
结论:
- 融合-DMA-Net模型是可行的,并且非常有效地使用PPG信号对心律失常进行分类.
- 这种方法有助于早期诊断和治疗心血管疾病.
- 这些发现支持可穿戴健康技术的发展,用于持续的心脏监测.
相关概念视频
Dysrhythmias II: Classification of Tachyarrhythmias
491
Tachyarrhythmias are a type of dysrhythmia where the heart rate exceeds 100 beats per minute. Here are some common types of tachyarrhythmias:Sinus TachycardiaSinus tachycardia originates from increased impulses from the sinus node, leading to an elevated heart rate. It is often triggered by stress, fever, or exercise.Patients may experience palpitations, a sensation of a racing heart, dizziness, and chest discomfort.Causes and Risk Factors: Common causes include physical exertion, emotional...
491
Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K

