Knowledge Extraction Based on Wavelets and DNN for Classification of Physiological Signals: Arousals Case

Research output: Chapter in BookChapterResearchpeer-review

2 Citations (Scopus)

Abstract

With a large amount of data collected from studies of sleep quality and based on the physiological signals (PS) that are collected, it is possible to use mechanisms that intelligently detect sleep disorders such as arousals (ARS). In this detection, the triggers can be present in any of the PS or can occur from their combinations. Thus, with the characterization of the PS and with a considerable number of examples, it is possible to generate a model that recognizes ARS zones in new samples. In this way, by segmenting the signals and decomposing them into variable frequency bands, thanks to the application of discrete wavelet transform (DWT), it is possible to characterize the contributions of each PS in time and frequency. The features that are extracted give information about the contributions in frequency and time of each PS. Then these characteristics feed a neural network model that iteratively learns the best non-linear function that approximates the input to its corresponding label. Once the methodology was tested, with less than 3% of the training data, it was possible to reach an Area Under Precision-Recall Curve (AUPRC) of 0.261.

Original languageAmerican English
Title of host publicationComputing in Cardiology Conference, CinC 2018
ISBN (Electronic)9781728109589
DOIs
Publication statusPublished - Sep 2018

Publication series

NameComputing in Cardiology
Volume2018-September
ISSN (Print)2325-8861
ISSN (Electronic)2325-887X

Fingerprint Dive into the research topics of 'Knowledge Extraction Based on Wavelets and DNN for Classification of Physiological Signals: Arousals Case'. Together they form a unique fingerprint.

  • Cite this

    Macias, E., Morell, A., Serrano, J., & Vicario, J. L. (2018). Knowledge Extraction Based on Wavelets and DNN for Classification of Physiological Signals: Arousals Case. In Computing in Cardiology Conference, CinC 2018 [8744021] (Computing in Cardiology; Vol. 2018-September). https://doi.org/10.22489/CinC.2018.230