Güven Çentik

Güven Çentik

Auto-generated profile, based on publicly available information

Güven Çentik

TRAKYA UNIVERSITY, EDIRNE VOCATIONAL SCHOOL

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 April 2016 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
İlhan Umutİlhan Umut
İlhan Umut
GÇGüven Çentik
Güven Çentik
The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, -nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while -nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present. The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, -nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while -nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present.

1 June 2024 in Gazi University Journal of Science
Verified
Journal Article
Closed access
PDF file
İlhan Umutİlhan Umut
İlhan Umut
HÜHakan Üstünel
Hakan Üstünel
GÇGüven Çenti̇k
Güven Çenti̇k
EUErdem Uçar
Erdem Uçar
LÖLevent Öztürk
Levent Öztürk
In this study, it was aimed to find out whether electroencephalographic (EEG) frequency bands can be used to distinguish people with obstructive sleep apnea (OSA) from those who do not have it. 11842 different cases taken from 121 patients suffering from OSA were combined with the case study of 30-person control group without sleep apnea. Apneas were highlighted at the respiration-record channels and EEG records which are concurrent with abnormal respiration cases were extracted from C4-A1 and C3-A2. Following that, they were examined with Fourier and Wavelet Transforms using a new software that was developed by us. The percentage values of Delta (0, 5-4 Hz), Theta (4-8 Hz), Alpha (8-13 Hz) and Beta (13-30 Hz) frequency bands were evaluated with the help of t-test and ROC Analysis to differentiate between apneas. The C3-A2 Beta (%) frequency level gave the highest distinguishing asset (AUC=0.662; p<0.001); however, the C3-A2 Alpha (%) level yielded the lowest distinguishing (AUC=0.536; p<0.001). Similarly, the C4-A1 Alpha (%) level produced the lowest distinguishing asset (AUC=0.536; p<0.001) whereas the C4-A1 Beta (%) frequency level gave the highest distinguishing asset (AUC=0.658; p<0.001). The chief finding of this study suggests that the EEG rates of patients with OSA differ from those of patients without OSA and following the changes at these channels may give rise to detection of apneas, and the Beta (%) yielded the most meaningful result among four different frequency bands in the study.