Shafiq Ghufran, Veluvolu Kalyana C
School of Electronics Engineering, College of IT Engineering, Kyungpook National University, Daegu, South Korea 702-701.
Sci Rep. 2014 May 28;4:5093. doi: 10.1038/srep05093.
Surface chest motion can be easily monitored with a wide variety of sensors such as pressure belts, fiber Bragg gratings and inertial sensors, etc. The current applications of these sensors are mainly restricted to respiratory motion monitoring/analysis due to the technical challenges involved in separation of the cardiac motion from the dominant respiratory motion. The contribution of heart to the surface chest motion is relatively very small as compared to the respiratory motion. Further, the heart motion spectrally overlaps with the respiratory harmonics and their separation becomes even more challenging. In this paper, we approach this source separation problem with independent component analysis (ICA) framework. ICA with reference (ICA-R) yields only desired component with improved separation, but the method is highly sensitive to the reference generation. Several reference generation approaches are developed to solve the problem. Experimental validation of these proposed approaches is performed with chest displacement data and ECG obtained from healthy subjects under normal breathing and post-exercise conditions. The extracted component morphologically matches well with the collected ECG. Results show that the proposed methods perform better than conventional band pass filtering.
使用各种传感器，如压力带、光纤布拉格光栅和惯性传感器等，可以轻松监测胸部表面运动。由于从占主导地位的呼吸运动中分离出心脏运动存在技术挑战，这些传感器目前的应用主要局限于呼吸运动监测/分析。与呼吸运动相比，心脏对胸部表面运动的贡献相对非常小。此外，心脏运动在频谱上与呼吸谐波重叠，它们的分离变得更具挑战性。在本文中，我们使用独立成分分析（ICA）框架来解决这个源分离问题。带参考的ICA（ICA-R）仅产生具有改进分离效果的期望成分，但该方法对参考生成高度敏感。为解决该问题开发了几种参考生成方法。使用从健康受试者在正常呼吸和运动后条件下获得的胸部位移数据和心电图对这些提出的方法进行了实验验证。提取的成分在形态上与收集到的心电图匹配良好。结果表明，所提出的方法比传统的带通滤波性能更好。
