期刊
FRONTIERS IN MEDICINE
卷 8, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fmed.2021.655084
关键词
phonocardiogram analysis; auto-encoder; data density; unsupervised learning; abnormality detection
资金
- National Neural Science Foundation of China (NSFC) [62001038]
- Fundamental Research Funds for the Central Universities [2019XD-A05]
This study proposes two methods based on estimating the density of vectors in the latent space to improve the performance of PCG analysis systems, showing that these methods outperform VAE-based methods; in addition, the representation of normal PCG signals in the latent space is investigated, with DBAE introducing Gaussian-like models for normal PCG representation.
This paper proposes an unsupervised way for Phonocardiogram (PCG) analysis, which uses a revised auto encoder based on distribution density estimation in the latent space. Auto encoders especially Variational Auto-Encoders (VAEs) and its variant beta-VAE are considered as one of the state-of-the-art methodologies for PCG analysis. VAE based models for PCG analysis assume that normal PCG signals can be represented by latent vectors that obey a normal Gaussian Model, which may not be necessary true in PCG analysis. This paper proposes two methods DBVAE and DBAE that are based on estimating the density of latent vectors in latent space to improve the performance of VAE based PCG analysis systems. Examining the system performance with PCG data from the a single domain and multiple domains, the proposed systems outperform the VAE based methods. The representation of normal PCG signals in the latent space is also investigated by calculating the kurtosis and skewness where DBAE introduces normal PCG representation following Gaussian-like models but DBVAE does not introduce normal PCG representation following Gaussian-like models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据