A new framework using deep auto-encoder and energy spectral density for medical waveform data classification and processing


Karim A. M., Guzel M. S., TOLUN M. R., Kaya H., Celebi F.

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, vol.39, no.1, pp.148-159, 2019 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 39 Issue: 1
  • Publication Date: 2019
  • Doi Number: 10.1016/j.bbe.2018.11.004
  • Journal Name: BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.148-159
  • Keywords: Energy spectral density, Deep auto-encoder, Deep learning, Medical waveform data process, ARTIFICIAL NEURAL-NETWORK, EEG, EPILEPSY
  • Ankara University Affiliated: Yes

Abstract

This paper proposes a new framework for medical data processing which is essentially designed based on deep autoencoder and energy spectral density (ESD) concepts. The main novelty of this framework is to incorporate ESD function as feature extractor into a unique deep sparse auto-encoders (DSAEs) architecture. This allows the proposed architecture to extract more qualified features in a shorter computational time compared with the conventional frameworks.