Electrocardiogram (ECG) signal transmission and monitoring plays a paramount role in long‐term cardiac monitoring and analysis to provide remote health care in time, especially for the postoperative people and people in remote areas. The accuracy of ECG signals is of fundamental importance in cardiac diagnosis like R‐peak detection. So we need to incorporate analytical methods in existing healthcare systems, to capture more meaningful ECG components and to represent physical cardiac sources more clearly. With this aim, hardware optimized FCAICA (fast confluence adaptive independent component analysis) algorithm is proposed to extract pure ECG components from the ECG mixtures. The extracted signals are then subjected to R‐peak detection for further analysis. The proposed improved fast confluence adaptive independent component analysis (IFCAICA) method occupies less hardware resources, consumes low power, improves accuracy, and sensitivity in R‐peaks detection. In 0.18 nm technology, the IFCAICA consumes 10.13 mW of power and operates with 3.4 MHz operating frequency.

中文翻译：

---

改进的ICA算法用于ECG特征提取和R峰检测

心电图（ECG）信号的传输和监视在长期的心脏监视和分析中发挥着至关重要的作用，以便及时提供远程医疗服务，尤其是对于术后人员和偏远地区的人们。ECG信号的准确性在心脏诊断（例如R峰检测）中至关重要。因此，我们需要将分析方法整合到现有的医疗保健系统中，以捕获更多有意义的ECG组件并更清楚地表示物理心脏源。为此，提出了硬件优化的FCAICA（快速融合自适应独立成分分析）算法，以从ECG混合物中提取纯ECG成分。然后将提取的信号进行R峰检测以进行进一步分析。所提出的改进的快速融合自适应独立分量分析（IFCAICA）方法占用的硬件资源更少，功耗低，提高了准确性，并提高了R峰检测的灵敏度。在0.18 nm技术中，IFCAICA功耗为10.13 mW，工作频率为3.4 MHz。