FNGLVQ FPGA design for sleep stages classification based on electrocardiogram signal

M. Eka S., M. Fajar, M. Iqbal T., Wisnu Jatmiko, I. Md. Agus

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Commonly sleep stages detection can be done using electroencephalogram (EEG) that is recorded in hospitals using Polysomnography (PSG) systems. PSG not only records brain signal but also electrocardiogram (ECG). In this paper an automatic sleep stages detection using FNGLVQ algorithm based solely on ECG signal is reported. We have compared two neural network algorithms' accuracies and implemented algorithms with the best accuracies into Field Programmable Gate Array. The two algorithms were Generalized Learning Vector Quantization (GLVQ) and Fuzzy Neuro Generalized Learning Vector Quantization (FNGLVQ). The result shows that FNGLVQ is capable in achieving 68% accuracy for MIT-BIH data, and 70% accuracy for Mitra data. The experiment conducted on FPGA also shows similar result.

Original languageEnglish
Title of host publicationProceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012
Pages2711-2716
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2012
Event2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012 - Seoul, Korea, Republic of
Duration: 14 Oct 201217 Oct 2012

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)1062-922X

Conference

Conference2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012
CountryKorea, Republic of
CitySeoul
Period14/10/1217/10/12

Keywords

  • ECG
  • FNGLVQ
  • FPGA
  • GLVQ
  • Neural Networks
  • Sleep Cycles
  • Sleep Stages
  • Vector Quantization

Fingerprint Dive into the research topics of 'FNGLVQ FPGA design for sleep stages classification based on electrocardiogram signal'. Together they form a unique fingerprint.

Cite this