Children Heart Sound - Normal & Abnormal
收藏资源简介：
Paper Title: A Wireless Electronic Stethoscope to Classify Children Heart Sound Abnormalities: DOI: 10.1109/ICCIT48885.2019.9038406 Children's Heart Sound Data: Normal-30 & Abnormal-30 Abstract: In this research paper, a wireless stethoscope has been introduced that can communicate with a smartphone to receive children’s heart sound. Along with an automated method that recognizes children's heart sound abnormalities. That isolation of heart sounds is based on time-frequency characteristics. Where it is preceded using Mel-frequency Cepstral Coefficients (MFCCs) signal processing method. The processed sounds are extracted using five feature extraction algorithms. Then it is classified using four support vector machines (SVM) kernel. Total 60 heart sounds were collected, where 30 sounds having abnormalities and rest 30 sounds containing normal heart sound. Though massive measures of action have already been taken in this area, still the necessity of more bearable cost devices and accurate methods is present. Here, the submitted apparatus cost is approximately 18 USD, which is the cheapest than most other devices used in previous work. Simultaneously it is lightweight and bearable to use in rural and underprivileged areas. With RBF kernel of SVM, the proposed method shows 94.12% accuracy which is the highest.
论文题目：一款用于儿童心音异常分类的无线电子听诊器，DOI：10.1109/ICCIT48885.2019.9038406 儿童心音数据集：正常样本30例，异常样本30例 摘要：本研究提出一款可与智能手机通信以采集儿童心音的无线听诊器，同时配套一种可自动识别儿童心音异常的算法。心音分离基于时频特征实现，预处理环节采用梅尔频率倒谱系数（Mel-frequency Cepstral Coefficients，MFCCs）信号处理方法。通过五种特征提取算法提取经预处理后的心音特征，随后采用四种支持向量机（Support Vector Machine, SVM）核函数完成分类。本次研究共收集60组心音样本，其中异常样本30组，正常样本30组。尽管该领域已有大量相关研究，但仍亟需成本更低廉、识别更精准的设备与方法。本研究所提出的设备成本仅约18美元，相较于此前多数同类设备更为低廉；同时该设备轻便易用，适用于农村及欠发达地区。采用支持向量机径向基核（Radial Basis Function, RBF）时，本方法的分类准确率可达94.12%，为所有测试方案中的最高值。
