Yucelbas, CuneytYucelbas, SuleOzsen, SeralTezel, GulayKuccukturk, SerkanYosunkaya, Sebnem2020-03-262020-03-2620180941-06431433-3058https://dx.doi.org/10.1007/s00521-016-2445-yhttps://hdl.handle.net/20.500.12395/36354Sleep staging is a significant process to diagnose sleep disorders. Like other stages, several parameters are required for the determination of N-REM2 stage. Sleep spindles (SSs) are among them. In this study, a methodology was presented to automatically determine starting and ending positions of SSs. To accomplish this, short-time Fourier transform-artificial neural networks (STFT-ANN), empirical mode decomposition (EMD) and discrete wavelet transform (DWT) methods were used. Two considerable methods which were determination envelope and thresholding of the decomposed signals by EMD and DWT were also presented in this study. A database from the EEG signals of nine healthy subjects-which consisted of 100 epochs including 172 SSs in total-was prepared. According to the test results, the highest sensitivity rate was obtained as 100 and 99.42 % for EMD and DWT methods. However, the sensitivity rate for the STFT-ANN method was recorded as 55.93 %. The results indicated that the EMD method could be confidently used in the automatic determination of SSs. Thanks to this study, the sleep experts will be able to reliably find out the epochs with SSs and also know the places of SSs in these epochs, automatically. Another important point of the study was that the sleep staging process-tiring, time-consuming and high fallibility for the experts-could be performed in less time and at higher accuracy rates.en10.1007/s00521-016-2445-yinfo:eu-repo/semantics/closedAccessDWTEEGEMDSleep spindleSTFTArticle2981733Q1WOS:000427799900002Q1