MAK-Net:一个多尺度的注意力科尔莫戈罗夫-阿诺德网络与BIGRU用于不平衡的心电图失常症分类
Cong Zhao1, Bingwei Lai1, Yongzheng Xu2,3
1Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, China.
Sensors (Basel, Switzerland)
|July 12, 2025
概括
MAK-Net是一种新的深度学习模型,尽管数据不平衡,但它可以准确地分类心电图 (ECG) 信号. 这一框架增强了心律失常的检测,改善了对心律障碍的临床决策.
科学领域:
- 心脏病学 心脏病学
- 人工智能的人工智能
- 生物医学信号处理
背景情况:
- 准确的心电图 (ECG) 分类对于诊断心律失常至关重要.
- 现实世界的心电图数据集经常表现出严重的类不平衡,阻碍了诊断性能.
- 现有的方法在不平衡的数据中扎,影响回忆和F1分数.
研究的目的:
- 引入MAK-Net,这是一个混合深度学习框架,旨在克服ECG信号分类中的类不平衡.
- 为了提高自动心律失常检测的准确性和稳定性.
主要方法:
- 开发了MAK-Net,这是一个混合深度学习框架,集成了多尺度卷积模块,通道注意力,双向封闭循环单元 (BiGRU) 和科尔摩戈罗夫-阿诺德网络 (KAN) 层.
- 使用焦点损失和合成少数人过量采样技术 (SMOTE) 来解决数据不平衡.
- 用MIT-BIH心律失常数据库进行模型评估.
主要成果:
- 在MIT-BIH心律失常数据库上,MAK-Net实现了最先进的性能.
- 实现了高度指标:0.9980准确度,0.9888F1得分,0.9871回忆,0.9905精度和0.9991特异性.
- 与现有方法相比,对不平衡类表现出优越的稳定性.
结论:
- 拟议的MAK-Net框架有效地处理不平衡的ECG数据,以可靠地检测心律失常.
- 多尺度特征融合,注意力引导学习和基于KAN的非线性映射已被验证为自动心律失常诊断.
- MAK-Net为临床可靠的自动心律失常检测提供了一个有前途的解决方案.
相关概念视频
01:22Multi-input and Multi-variable systems
150
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
150
01:25Correlation between ECG and Cardiac Cycle
8.4K
The electrical signals recorded on an electrocardiogram (ECG) occur before the mechanical processes of contraction and relaxation during the cardiac cycle.
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
8.4K
01:25Instrumentation Amplifier
712
An electrocardiography (ECG) machine is an essential piece of medical equipment used to monitor the electrical activity of the heart. It operates by detecting small electrical changes on the skin that result from the depolarization of the heart muscle during each heartbeat. However, these signals are in the microvolt range and can be easily overwhelmed by noise or interference.
To overcome this challenge, an ECG machine utilizes an instrumentation amplifier. This specialized amplifier is...
To overcome this challenge, an ECG machine utilizes an instrumentation amplifier. This specialized amplifier is...
712
01:30Classification of Signals
903
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...
903