Phonocardiogram (PCG) signals hold significant prognostic and diagnostic information about cardiac health. Numerous PCG or heart sound based automated detection algorithms were previously proposed to assist the disease diagnosis process. Most of the previous studies only focused on algorithmic development. This study presents an intelligent, portable, and low-cost embedded system for the classification of cardiac disorders associated with heart murmurs. Different stages corresponding to the developed embedded system implementation are summarized as follows: The first stage consists of the acquisition of PCG signals of both normal and patients from various hospitals with a customized and low-cost stethoscope. The second stage describes the preprocessing, localization of S1 and S2 heart sounds, and the extraction of systole and diastole from a heart signal with an empirical mode decomposition integrated with the self-developed algorithm. In the third stage, discriminant features are extracted to represent various cardiac classes of PCG signals in a compact manner. In the final stage of the algorithm, the k-nearest neighbors classifier is trained and tested to distinguish between normal and four cardiac disorders. The proposed algorithm achieved 94% mean accuracy through comprehensive experimentation. The cardiac disorders classification algorithm is implemented on a RP-based embedded system. Software application with an interactive graphical interface is also designed to assist users. The developed intelligent system is portable, low-cost, and it enables regular patient-monitoring. The proposed system has the potential to be employed at remote locations where the availability of doctors remains challenging.

中文翻译：

---

一种用于心脏疾病检测和分类的新型嵌入式系统设计

心音图 (PCG) 信号包含有关心脏健康的重要预后和诊断信息。先前提出了许多基于 PCG 或心音的自动检测算法来辅助疾病诊断过程。以前的大多数研究只关注算法开发。本研究提出了一种智能、便携和低成本的嵌入式系统，用于对与心脏杂音相关的心脏疾病进行分类。与所开发的嵌入式系统实施相对应的不同阶段总结如下： 第一阶段包括使用定制的低成本听诊器从不同医院采集正常和患者的 PCG 信号。第二阶段描述 S1 和 S2 心音的预处理、定位，结合自主开发的算法，通过经验模态分解从心脏信号中提取收缩期和舒张期。在第三阶段，提取判别特征以紧凑的方式表示各种心脏类别的 PCG 信号。在算法的最后阶段，k-最近邻分类器被训练和测试以区分正常和四种心脏疾病。所提出的算法通过综合实验达到了 94% 的平均准确率。心脏疾病分类算法是在基于 RP 的嵌入式系统上实现的。具有交互式图形界面的软件应用程序也旨在帮助用户。开发的智能系统是便携式的、低成本的，并且可以定期监测病人。