TY - JOUR A2 - Goh, Kheng-Lim AU - Zhang, Hongpo AU - He, Renke AU - Dai, Honghua AU - Xu, Mingliang AU - Wang, Zongmin PY - 2020 DA - 20/05/18 TI - SS-SWT and SI-CNN:时频心电信号SP - 7526825 VL - 2020 AB -心房颤动是最常见的心律失常，与中风、心力衰竭、心肌梗死和脑血栓形成的高发病率和死亡率相关。有效、快速地检测心房颤动对降低患者的发病率和死亡率至关重要。快速有效地筛查心房颤动仍然是一项具有挑战性的任务。在本文中，我们提出了SS-SWT和SI-CNN:一个心房颤动时频ECG信号检测框架。首先，利用特定尺度平稳小波变换(SS-SWT)将5 s心电信号分解为8个尺度;我们选择特定尺度的系数作为有效的时频特征，而放弃其他系数。选取的系数作为二维(2D)矩阵反馈给尺度无关的卷积神经网络(SI-CNN)。在SI-CNN中，针对心电信号的时频特性设计了一个卷积核。在卷积过程中，保持各尺度系数之间的独立性，有效提取心电信号的时域和频域特征，最终快速准确地识别出心房颤动信号。 In this study, experiments are performed using the MIT-BIH AFDB data in 5-s data segments. We achieve 99.03% sensitivity, 99.35% specificity, and 99.23% overall accuracy. The SS-SWT and SI-CNN we propose simplify the feature extraction step, effectively extracts the features of ECG, and reduces the feature redundancy that may be caused by wavelet transform. The results shows that the method can effectively detect atrial fibrillation signals and has potential in clinical application. SN - 2040-2295 UR - https://doi.org/10.1155/2020/7526825 DO - 10.1155/2020/7526825 JF - Journal of Healthcare Engineering PB - Hindawi KW - ER -