Asli Uyar

A Database of Non-Manual Signs in Turkish Sign Language

Sign languages are visual languages. The message is not only transferred via hand gestures (manual signs) but also head/body motion and facial expressions (non-manual signs). In this article, we present a database of non-manual signs in Turkish sign language (TSL). There are eight non-manual signs in the database, which are frequently used in TSL. The database contains the videos of these signs as well as a ground truth data of 60 manually landmarked points of the face.

Facial feature tracking and expression recognition for sign language

Expressions carry vital information in sign language. In this study, we have implemented a multi-resolution active shape model (MR-ASM) tracker, which tracks 116 facial landmarks on videos. Since the expressions involve significant amount of head rotation, we employ multiple ASM models to deal with different poses. The tracked landmark points are used to extract motion features which are used by a support vector machine (SVM) based classifier. We obtained above 90% classification accuracy in a data set containing 7 expressions.

Arrhythmia Classification Using Serial Fusion of Support Vector Machines and Logistic Regression

Reliable arrhythmia classification from complex electrocardiogram (ECG) signals is one of the most challenging pattern recognition problems. Several individual classifiers have been studied in the ECG domain. Also, parallel and serial classifier fusion systems have been proposed to increase the reliability. In this study, we are mainly interested in producing high confident arrhythmia classification results to be applicable in diagnostic decision support systems. We first experiment and compare two common techniques: support vector machines (SVM) and logistic regression (LR). Then, we propose a two- stage serial fusion classifier system based on SVMs rejection option. We relate the SVMs distance outputs to confidence measure and reject to classify ambiguous samples with first level SVM classifier. A non-symmetric thresholding scheme is applied: two different rejection distance thresholds have been defined for positive and negative ECG samples. The rejected samples have been forwarded to a second stage LR classifier. Finally we choose a way to combine the classifiers decisions to obtain a final decision rule. The experiments have been performed on UCI Arrhythmia Database.

ROC Based Evaluation and Comparison of Classifiers for IVF Implantation Prediction

Determination of the best performing classification method for a specific application domain is important for the applicability of machine learning systems. We have compared six classifiers for predicting implantation potentials of IVF embryos. We have constructed an embryo based dataset which represents an imbalanced distribution of positive and negative samples as in most of the medical datasets. Since it is shown that accuracy is not an appropriate measure for imbalanced class distributions, ROC analysis have been used for performance evaluation. Our experimental results reveal that Naive Bayes and Radial Basis Function methods produced significantly better performance with (0.739 ± 0.036) and (0.712 ± 0.036) area under the curve measures respectively.

Physician experience in performing embryo transfers may affect outcome

The distribution of six physicians pregnancy rates with cycle and patient demographics was investigated for 2,212 transfer cycles. The results indicate that when the patient and cycle characteristics are compromised, the level of physician experience may determine the outcome of embryo transfers.

A frequency based encoding technique for transformation of categorical variables in mixed IVF dataset

Implantation prediction of in-vitro fertilization (IVF) embryos is critical for the success of the treatment. In this study, Support Vector Machine (SVM) method has been used on an original IVF dataset for classification of embryos according to implantation potentials. The dataset we analyzed includes both categorical and continuous feature values. Transformation of categorical variables into numeric attributes is an important pre-processing stage for SVM affecting the performance of the classification. We have proposed a frequency based encoding technique for transformation of categorical variables. Experimental results revealed that, the proposed technique significantly improved the performance of IVF implantation prediction in terms of Area Under ROC curve (0.712±0.032) compared to common binary encoding and expert judgement based transformation methods (0.676±0.033 and 0.696 ± 0.024, respectively).

3P: Personalized Pregnancy Prediction in IVF Treatment Process

We present an intelligent learning system for improving pregnancy success rate of IVF treatment. Our proposed model uses an SVM based classification system for training a model from past data and making predictions on implantation outcome of new embryos. This study employs an embryo-centered approach. Each embryo is represented with a data feature vector including 17 features related to patient characteristics, clinical diagnosis, treatment method and embryo morphological parameters. Our experimental results demonstrate a prediction accuracy of 82.7%. We have obtained the IVF dataset from Bahceci Women Health, Care Centre, in Istanbul, Turkey.

Bayesian Networks for Predicting IVF Blastocyst Development

In in-vitro fertilization (IVF) treatment, blastocyst stage embryo transfers at day 5 result in higher pregnancy rates. However, there is a risk of transfer cancelation due to embryonic developmental failure. Clinicians need reliable models in predicting blastocyst development. In this study, we apply Bayesian networks in order to investigate cause-effect relationships of the variables of interest in embryo growth process and to predict blastocyst development. We have analyzed 7745 embryo records including embryo morphological characteristics and patient related data. Experimental results revealed that, Bayesian networks can predict blastocyst development with 63.5% true positive rate and 33.8% false positive rate.

Adjusting decision threshold in Naive Bayes based IVF embryo selection

In this study, IVF embryo selection has been considered as a binary classification problem and predictibality of implantation outcome of individual embryos has been tested using Naive Bayes method. First, in order to perform classification experiments, an embryo based dataset has been constructed from database of Bahçeci IVF Centre. Since the class distribution of dataset is highly imbalanced (11% Pozitive and 89% Negative implantation outcomes) the decision threshold of Naive Bayes classifier has been optimized using the features of ROC analysis. Experimental results show that classification with optimized threshold performs better than classification with default threshold.

Emerging technologies for improving embryo selection: a systematic review

License. The full terms of the License are available at http://creativecommons.org/licenses/by-nc/3.0/. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. Permissions beyond the scope of the License are administered by Dove Medical Press Limited. Information on how to request permission may be found at: http://www.dovepress.com/permissions.php Advanced Health Care Technologies 2015:1 55–64 Advanced Health Care Technologies Dovepress