SIU 2018

26th Signal Processing and Communications Applications Conference (SIU 2018)  was held in Çeşme, İzmir, Turkey and we presented two works on the conference. 

The Influences of Different Window Functions and Lengths on Image-based Time-Frequency Features of Fetal Heart Rate Signals

In the clinical practice, the fetal distress conditions such as hypoxia are detected routinely during antepartum and even intrapartum periods with the help of electronic fetal monitoring device, often called Cardiotocography (CTG). Due to the noticeable advances in signal processing, pattern recognition, machine learning techniques and the introduction of the quantitative diagnostic indices, the automated CTG analysis has become a quite essential tool. In this study, we come up with a new investigation on the influences of different window functions on image-based time-frequency (IBTF) features of fetal heart rate (FHR) signals for fetal hypoxia detection. In addition to the traditionally used morphological features, the spectrogram images provided by Short Time Fourier Transform (STFT) were taken into account with different windows functions such as Hamming, Hann, Kaiser, and Blackman as well as different windows lengths. Then, the spectrogram images were converted into 8-bits gray-scale images and IBTF features were obtained using Gray Level Co-occurrence Matrix (GLCM). At the end of the feature extraction stage for signal representation, we achieved a quite large feature set, and we employed genetic algorithm (GA) and support vector machine (SVM) classifier in order to reveal the most relevant features. The whole experiments were performed on an open CTU-UHB intrapartum CTG database. The experimental results show that the  IBTF features have relatively increased the classification performance. All window functions ensured encouraging results. Furthermore, the GA ensured the determination of the 7 most relevant features. Thus, the dimension of feature space was reduced from 28 to 7. Moreover, the classification success increased. Consequently, the most efficient performances (Quality Index = 73.45%) were achieved with Hamming and Kaiser window functions.

Performance Evaluation of Empirical Mode Decomposition and Discrete Wavelet Transform for Computerized Hypoxia Detection and Prediction

This study proposes a new model relying on Empirical Mode Decomposition (EMD) and Discrete Wavelet Transform (DWT) in order to detect fetal hypoxia by using Cardiotocography (CTG) signals. We processed one well known open access intrapartum CTU-UHB database to find if our model could outperform the state-of-the-art models. The model consists of three key stages: (1) Preprocessing, (2) Features extraction using EMD and DWT, (3) Classification with Support Vector Machine (SVM). Also, we present a comparative experimental study to measure the performance of SVM classifier depending on feature extraction methods. As a result, EMD and DWT have been found as useful methods for fetal hypoxia detection. Also, SVM classifier utilizing a combination of DWT and morphological features achieved the highest performance. Furthermore, DWT features produced more successful results than EMD features in terms of the classification success.  Consequently, the proposed model ensured sensitivity of 57.42% and specificity of 70.11%.