Currently, the telehealth monitoring field has gained huge attention due to its noteworthy use in day-to-day life. This advancement has led to an increase in the data collection of electrophysiological signals. Due to this advancement, electrocardiogram (ECG) signal monitoring has become a leading task in the medical field. ECG plays an important role in the medical field by analysing cardiac physiology and abnormalities. However, these signals are affected due to numerous varieties of noises, such as electrode motion, baseline wander and white noise etc., which affects the diagnosis accuracy. Therefore, filtering ECG signals became an important task. Currently, deep learning schemes are widely employed in signal-filtering tasks due to their efficient architecture of feature learning. This work presents a deep learning-based scheme for ECG signal filtering, which is based on the deep autoencoder module. According to this scheme, the data is processed through the encoder and decoder layer to reconstruct by eliminating noises. The proposed deep learning architecture uses a modified ReLU function to improve the learning of attributes because standard ReLU cannot adapt to huge variations. Further, a skip connection is also incorporated in the proposed architecture, which retains the key feature of the encoder layer while mapping these features to the decoder layer. Similarly, an attention model is also included, which performs channel and spatial attention, which generates the robust map by using channel and average pooling operations, resulting in improving the learning performance. The proposed approach is tested on a publicly available MIT-BIH dataset where different types of noise, such as electrode motion, baseline water and motion artifacts, are added to the original signal at varied SNR levels.

翻译：当前，远程医疗监测领域因其在日常生活中的显著应用而受到广泛关注。这一进步导致电生理信号数据采集的增加。因此，心电图信号监测已成为医学领域的一项重要任务。心电图通过分析心脏生理和异常在医学领域发挥着重要作用。然而，这些信号受到多种噪声的影响，例如电极运动、基线漂移和白噪声等，从而影响诊断准确性。因此，心电信号滤波成为一项重要任务。目前，深度学习方案因其高效的特征学习架构而被广泛应用于信号滤波任务。本文提出了一种基于深度学习的心电信号滤波方案，该方案基于深度自编码器模块。根据该方案，数据通过编码器和解码器层进行处理，通过消除噪声进行重建。所提出的深度学习架构使用改进的ReLU函数来改善属性学习，因为标准ReLU无法适应巨大变化。此外，在所提出的架构中还引入了跳跃连接，它在将编码器层的关键特征映射到解码器层的同时保留这些特征。类似地，还包含一个注意力模型，该模型执行通道和空间注意力，通过使用通道和平均池化操作生成鲁棒特征图，从而提高学习性能。所提出的方法在公开可用的MIT-BIH数据集上进行了测试，其中在不同信噪比水平下向原始信号添加了不同类型的噪声，例如电极运动、基线漂移和运动伪影。