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

Karim, Ahmad; Guzel, MEHMET; TOLUN, MEHMET; Kaya, Hilal; Celebi, Fatih

doi:10.1016/j.bbe.2018.11.004

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

Atıf İçin Kopyala

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

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, cilt.39, sa.1, ss.148-159, 2019 (SCI-Expanded)

Yayın Türü: Makale / Tam Makale
Cilt numarası: 39 Sayı: 1
Basım Tarihi: 2019
Doi Numarası: 10.1016/j.bbe.2018.11.004
Dergi Adı: BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
Sayfa Sayıları: ss.148-159
Anahtar Kelimeler: Energy spectral density, Deep auto-encoder, Deep learning, Medical waveform data process, ARTIFICIAL NEURAL-NETWORK, EEG, EPILEPSY
Ankara Üniversitesi Adresli: Evet

Özet

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.