Efficient sleep spindle detection algorithm with decision tree

Duman F., Erdamar A., Erogul O., Telatar Z., Yetkin S.

Expert Systems with Applications, vol.36, no.6, pp.9980-9985, 2009 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 36 Issue: 6
  • Publication Date: 2009
  • Doi Number: 10.1016/j.eswa.2009.01.061
  • Journal Name: Expert Systems with Applications
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.9980-9985
  • Keywords: EEG, MUSIC algorithm, Short Time Fourier Transform, Sleep spindle detection, Wavelet Transform
  • Ankara Yıldırım Beyazıt University Affiliated: Yes


In this study, an efficient sleep spindle detection algorithm based on decision tree is proposed. After analyzing the EEG waveform, the decision algorithm determines the exact location of sleep spindle by evaluating the outputs of three different methods namely: Short Time Fourier Transform (STFT), Multiple Signal Classification (MUSIC) algorithm and Teager Energy Operator (TEO). The EEG records collected from patients used in this study have been recorded at the Sleep Research Center in Department of Psychiatry of Gülhane Military Medicine Academy. The obtained results are in agreement with the visual analysis of EEG evaluated by expert physicians. The method is applied to 16 distinct patients, 420,570 minutes long EEG records and the performance of the algorithm was assessed for the sleep spindles detection with 96.17% sensitivity and 95.54% specificity. As a result, it is found that the proposed sleep spindle detection algorithm is an efficient method to detect sleep spindles on EEG records. © 2009 Elsevier Ltd. All rights reserved.