Dursun, MehmetOzsen, SeralYucelbas, CuneytYucelbas, SuleTezel, GulayKuccukturk, SerkanYosunkaya, Sebnem2020-03-262020-03-2620170941-06431433-3058https://dx.doi.org/10.1007/s00521-016-2578-zhttps://hdl.handle.net/20.500.12395/34729Interference between EEG and EOG signals has been studied heavily in clinical EEG signal processing applications. But, in automatic sleep stage classification studies these effects are generally ignored. Thus, the objective of this study was to eliminate EOG artifacts from the EEG signals and to see the effects of this process. We proposed a new scheme in which EOG artifacts are separated from electrode or other line artifacts by a correlation and discrete wavelet transform-based rule. Also, to discriminate the situation of EEG contamination to EOG from EOG contamination to EEG, we introduced another rule and integrated this rule to our proposed method. The proposed method was also evaluated under two different circumstances: EOG-EEG elimination along the whole 0.3-35 Hz power spectrum and EOG-EEG elimination with discrete wavelet transform in 0-4 Hz frequency range. To see the consequences of EOG-EEG elimination in these circumstances, we classified pure EEG and artifact-eliminated EEG signals for each situation with artificial neural networks. The results on 11 subjects showed that pure EEG signals gave a mean classification accuracy of 60.12 %. The proposed EOG elimination process performed in 0-35 Hz frequency range resulted in a classification accuracy of 63.75 %. Furthermore, conducting EOG elimination process by using 0-4 Hz DWT detail coefficients caused this accuracy to be raised to 68.15 %. By comparing the results obtained from all applications, we concluded that an improvement about 8.03 % in classification accuracy with regard to the uncleaned EEG signals was achieved.en10.1007/s00521-016-2578-zinfo:eu-repo/semantics/closedAccessSleep EEGEOG artifact eliminationSleep stage scoringArtificial neural networksArticle281030953112Q1WOS:000426865100020Q1