arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.02429eess.SP
收藏

用于呼吸系统疾病分类的谱图失真度

Distortion measure of spectrograms for classification of respiratory diseases

Jeremy Levy, Alexander Naitsat, Yehoshua Y. Zeevi

摘要:

提出了一种新的呼吸系统疾病分类方法。该方法是基于一类新的功能,从肺的声音中提取,通过参数化他们的频谱图表示为表面,并通过利用参考这些表面定义的几何失真。这种方法产生了一组高度描述性的特征,用于肺音记录的分析。此外,通过将这些功能与梅尔频率倒谱系数相结合,我们引入了一个强大的模型,用于自动诊断常见的呼吸道病变。与基线方法相比,我们的模型在常见呼吸道疾病的二进制和多类分类方面取得了优异的结果。我们的新方法的一维信号的分类是适用于其他信号的上下文中,他们的组合空间或流形的表示。

英文摘要:

A new method for the classification of respiratory diseases is presented. The method is based on a novel class of features, extracted from pulmonary sounds, by parameterizing their spectrograms that are represented as surfaces, and by utilizing geometrical distortions defined with reference to these surfaces. This method yields a set of highly descriptive features for the analysis of pulmonary sound recordings. Furthermore, by combining these features with Mel-frequency cepstral coefficients, we introduce a powerful model for the automatic diagnosis of common respiratory pathologies. Compared with baseline methods, our model achieves superior results for binary and multi-class classifications of common respiratory diseases. Our new approach to the classification of one-dimensional signals is applicable to other signals in the context of their representations in combined spaces or manifolds.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑