探索使用量子化神经网络实时在设备上ECG生物识别分类的可行性
Martin Berki1, Anton Mateasik1,2, Michal Micjan1
1Institute of Electronics and Photonics, Slovak University of Technology, Bratislava, Slovakia.
Frontiers in digital health
|February 19, 2026
概括
本研究引入了一个嵌入式深度学习系统,用于可穿戴设备上的实时心电图 (ECG) 生物识别分类. 该系统在识别使用心电图模式的个体方面实现了高精度,增强了隐私,并使个性化医疗保健成为可能.
科学领域:
- 生物医学工程 生物医学工程
- 人工智能的人工智能
- 可穿戴技术可穿戴技术
背景情况:
- 持续的个性化医疗监测至关重要.
- 心电图 (ECG) 信号提供了独特的生物识别模式.
- 目前的系统通常依赖于云连接,这引发了隐私和效率方面的担忧.
研究的目的:
- 开发和评估一种概念验证嵌入式深度学习系统,用于可穿戴Holter设备上的实时ECG生物识别分类.
- 减少对ECG分析的持续云连接的依赖.
- 增强数据隐私并减少可穿戴健康监测中的电力消耗.
主要方法:
- 在STM32H7微控制器上部署了一个量子化的卷积神经网络 (CNN).
- 一个初始的信号质量评估阶段被纳入了强大的处理.
- 该系统在PTB诊断心电图数据库上使用特定学科培训进行了评估.
主要成果:
- 嵌入式系统在5秒的心电图段中获得了94.51%的F1分数和94.68%的分类准确性.
- 平均推断时间为1.35秒,在资源有限的硬件上实现实时操作.
- 在设备上的推断证明了数据隐私的改善和数据传输的减少.
结论:
- 嵌入式实现证明了将轻量级ECG生物识别集成到可穿戴系统中的可行性.
- 这种方法增强了隐私,降低了电力消耗,并将数据传输降到最低.
- 未来扩展的潜力包括个性化医疗监测和早期异常检测.
相关概念视频
01:30Pulse rhythm
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...
01:23Holter Monitor: 24-Hour Monitoring
Holter monitoring is a continuous electrocardiography (ECG) recording that tracks the heart's electrical activity over an extended period, generally 24 to 48 hours. This noninvasive diagnostic tool detects irregular heart rhythms that may not be captured during a standard ECG performed in a clinical setting.DeviceThe Holter monitor is a portable, small device connected to several electrodes on the patient's chest. These electrodes detect the heart's electrical signals and transmit them to the...