Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain.
作者： Thiago L. T. da Silveira , Alice J. Kozakevicius , Cesar R. Rodrigues
DOI: 10.1007/S11517-016-1519-4
关键词:
摘要: The main objective of this study was to enhance the performance sleep stage classification using single-channel electroencephalograms (EEGs), which are highly desirable for many emerging technologies, such as telemedicine and home care. proposed method consists decomposing EEGs by a discrete wavelet transform computing kurtosis, skewness variance its coefficients at selected levels. A random forest predictor is trained classify each epoch into one Rechtschaffen Kales’ stages. By performing comprehensive set tests on 106,376 epochs available from Physionet public database, it demonstrated that use these three statistical moments has enhanced when compared their application in time domain. Furthermore, chosen features advantage exhibiting stable all scoring systems, i.e., 2- 6-state stability feature confirmed with ReliefF show reduction any individual removed, suggesting group cannot be further reduced. accuracies kappa yield higher than 90 % 0.8, respectively, cases.
springer.com
sci-hub.se 参考文章(34)
Gabriel Peyré, S. G. Mallat, A Wavelet Tour of Signal Processing : The Sparse Way Elsevier/Academic Press. ,(2008)
James Franklin, The elements of statistical learning : data mining, inference,and prediction The Mathematical Intelligencer. ,vol. 27, pp. 83- 85 ,(2005) , 10.1007/BF02985802
Mark A. Hall, Ian H. Witten, Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques ,(1999)
Doris Moser, Peter Anderer, Georg Gruber, Silvia Parapatics, Erna Loretz, Marion Boeck, Gerhard Kloesch, Esther Heller, Andrea Schmidt, Heidi Danker-Hopfe, Bernd Saletu, Josef Zeitlhofer, Georg Dorffner, Sleep classification according to AASM and Rechtschaffen & Kales: effects on sleep scoring parameters. Sleep. ,vol. 32, pp. 139- 149 ,(2009) , 10.1093/SLEEP/32.2.139
Marko Robnik-Šikonja, Improving random forests european conference on machine learning. pp. 359- 370 ,(2004) , 10.1007/978-3-540-30115-8_34
Thais Mayumi Oshiro, Pedro Santoro Perez, José Augusto Baranauskas, How many trees in a random forest machine learning and data mining in pattern recognition. pp. 154- 168 ,(2012) , 10.1007/978-3-642-31537-4_13
Özay Çelen, Abdulkadir Teke, Necmettin Cihangiroglu, The Effect of Socio-Cultural Characteristics on the Effectiveness of Teamwork: A Study in the Gülhane Military Medical Faculty Training Hospital Journal of Medical Systems. ,vol. 38, pp. 1- 11 ,(2014) , 10.1007/S10916-014-0126-X
Xiaoxuan Jia, Adam Kohn, Gamma Rhythms in the Brain PLOS Biology. ,vol. 9, ,(2011) , 10.1371/JOURNAL.PBIO.1001045
A SUBASI, Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients Expert Systems With Applications. ,vol. 28, pp. 701- 711 ,(2005) , 10.1016/J.ESWA.2004.12.027
Baha Şen, Musa Peker, Abdullah Çavuşoğlu, Fatih V. Çelebi, A Comparative Study on Classification of Sleep Stage Based on EEG Signals Using Feature Selection and Classification Algorithms Journal of Medical Systems. ,vol. 38, pp. 18- ,(2014) , 10.1007/S10916-014-0018-0