Yazar "Comert, Z." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Comparison of Machine Learning Techniques for Fetal Heart Rate Classification
    (Polish Acad Sciences Inst Physics, 2017) Comert, Z.; Kocamaz, A. F.
    Cardiotocography is a monitoring technique providing important and vital information on fetal status during antepartum and intrapartum periods. The advances in modern obstetric practice allowed many robust and reliable machine learning techniques to be utilized in classifying fetal heart rate signals. The role of machine learning approaches in diagnosing diseases is becoming increasingly essential and intertwined. The main aim of the present study is to determine the most efficient machine learning technique to classify fetal heart rate signals. Therefore, the research has been focused on the widely used and practical machine learning techniques, such as artificial neural network, support vector machine, extreme learning machine, radial basis function network, and random forest. In a comparative way, fetal heart rate signals were classified as normal or hypoxic using the aforementioned machine learning techniques. The performance metrics derived from confusion matrix were used to measure classifiers' success. According to experimental results, although all machine learning techniques produced satisfactory results, artificial neural network yielded the rather well results with the sensitivity of 99.73% and specificity of 97.94%. The study results show that the artificial neural network was superior to other algorithms.
  • Küçük Resim Yok
    Öğe
    A Simple and Effective Approach for Digitization of the CTG Signals from CTG Traces
    (Elsevier Science Inc, 2019) Comert, Z.; Sengur, A.; Akbulut, Y.; Budak, U.; Kocamaz, A. F.; Gungor, S.
    Objectives: Cardiotocography (CTG) is a useful tool for monitoring of the fetal heart rate (FHR) and uterine contractions (UC) during the intrauterine life. Generally, CTG is provided on a printed paper which is hard to save for future evaluations. So, digitization of CTG signals is in demand for future evaluations. A straightforward approach for digitization of the CTG signals is to apply image processing on the scanned CTG printed papers. Material and methods: In this paper, an automatic procedure is proposed for digitization of the CTG signals. The proposed approach consists of four main stages such as pre-processing, image segmentation, signal extraction and signal calibration. The pre-processing stage covers median filtering and contrasts limited adaptive histogram equalization (CLAHE) for noise removal and contrast enhancement. Image segmentation is used to binarize the CTG images for signal determination using the Otsu's thresholding algorithm. The signal extraction is carried out by a two-stepped algorithm. The acquired CTG signals are then calibrated for obtaining the final CTG signals. We use the correlation coefficient to measure the similarity between the automatically digitized CTG signals and original signals. Results: In experimental works, an open-access database, which contains 552 CTG recordings, is employed. The results are quite impressive. According to the obtained results, the average correlation coefficients for FHR and UC signals are 0.9715 +/- 0.0168 and 0.9717 +/- 0.0465, respectively. Conclusions: The obtained results show that the proposed method is quite efficient in digitization of the CTG signals. In future works, this tool will be used to digitize the recordings belonging to the antepartum period collected from the obstetrics clinics in Medical Park Hospital in Elazig, Turkey. (C) 2019 AGBM. Published by Elsevier Masson SAS. All rights reserved.