# Automatic Feature Extraction for Heartbeat Anomaly Detection

arXiv: https://arxiv.org/abs/2102.12289 · HTML: https://mlsanity.com/paper/2102.12289/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 24 Feb 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection](https://mlsanity.com/paper/1801.08322/) (2018)
- [Deep Learning in Cardiology](https://mlsanity.com/paper/1902.11122/) (2019)

## Abstract (arXiv)

We focus on automatic feature extraction for raw audio heartbeat sounds, aimed at anomaly detection applications in healthcare. We learn features with the help of an autoencoder composed by a 1D non-causal convolutional encoder and a WaveNet decoder trained with a modified objective based on variational inference, employing the Maximum Mean Discrepancy (MMD). Moreover we model the latent distribution using a Gaussian chain graphical model to capture temporal correlations which characterize the encoded signals. After training the autoencoder on the reconstruction task in a unsupervised manner, we test the significance of the learned latent representations by training an SVM to predict anomalies. We evaluate the methods on a problem proposed by the PASCAL Classifying Heart Sounds Challenge and we compare with results in the literature.