Heart disease is one of the most common causes of death globally. In this study, machine learning algorithms and models widely used in the literature to predict heart disease have been extensively compared, and a hybrid feature selection based on genetic algorithm and tabu search methods have been developed. The proposed system consists of three components: (1) preprocess of datasets, (2) feature selection with genetic and tabu search algorithm, and (3) classification module. The models have been tested using different datasets, and detailed comparisons and analysis were presented. The experimental results show that the Random Forest algorithm is more successful than Adaboost, Bagging, Logitboost, and Support Vector machine using Cleveland and Statlog datasets.

The easiness of reaching information through the internet and social media and the expansiveness of opportunities for searching, copying, and spreading data have caused some problems in identifying an author for a specific text. A text carries the characteristic features of the person who wrote it, and these features can be used to identify its author. For this study, we are offering a method that is based on an approach using ensemble learning algorithm (ELA) and genetic algorithm (GA) for author identification in Turkish texts. The raw data set, which includes 40 authors and 3269 texts, was created from Turkish news websites and analyzed in pre-processing step. After, syntactic and structural analyses were done on the data and, in total, 6 different data sets were created. Each of the data sets was subjected to the feature selection process by using GA and ELA approach together. Each of the obtained data sets from the previous step was classified by using the ELA's bagging method which contains 5 different classifiers, namely, Naive Bayes, K-Nearest Neighbor, Artificial Neural Networks, Support Vector Machine, and Decision Tree. After applying the aforementioned processes to the raw data, the author identification approach reached 89% accuracy. The combination of ELA and GA has a strong potential to identify the author of a text.

Yüzyıllardır süregelen yazarı belirsiz metinler sorunu, internet çağının başlamasıyla oldukça artmıştır. Bu durumun en büyük sebebi internetteki verilerin çok yüksek oranını yapısal olmayan verilerin oluşturması ve bu yapısal olmayan verilerin de büyük bir bölümünü sınıflandırılmamış, yazarları belirsiz metinlerin oluşturmasıdır. Son yıllarda yapılan sınıflandırma işlemlerinde makine öğrenmesi yöntemlerinin kullanılması, yazar tanıma problemlerine yeni bir bakış açısı getirmiştir. Bu çalışmada makine öğrenmesi yöntemleri kullanılarak yazar tanıma problemi için web tabanlı arayüze sahip uçtan uca bir uygulama geliştirilmiştir. Sınıflandırma işlemi için 37 yazarın köşe yazılarından oluşturulmuş 46715 metin verisi içeren bir derlem kullanılmıştır. Bu derlemden TF-IDF yöntemi kullanılarak öznitelikler çıkarılmış ve bir veri kümesi elde edilmiştir. Daha sonra veri kümesi, Destek Vektör Makineleri (DVM), NB (NB) ve RO (RO) gibi makine öğrenme algoritmaları ile eğitilmiş ve test edilmiştir. Test sonucunda, DVM %90 doğruluk oranıyla en iyi performansı gösteren sınıflandırıcı model olmuştur. Elde edilen DVM modeline, Python programlama dilinin kütüphanelerinden olan Flask kullanılarak bir web arayüzü geliştirilmiştir. Son olarak uygulama, kararlı ve dağıtıma uygun bir halde çalıştırılması amacıyla Docker konteynerına dönüştürülmüştür. Sonuç olarak, uçtan uca geliştirilen bir yazar tanıma uygulaması doğrudan son kullanıcı tarafından kullanılabilir biçimde sunulmuştur. Makine öğrenmesi desteğiyle web tabanlı böyle bir uygulamanın oluşturulması, yazar tanıma çalışmasını daha anlamlı ve kullanılabilir hale getirmiştir.

No abstract

Objective: Methemoglobinemia is an urgent condition requiring early diagnosis and treatment; it may be fatal if the methemoglobin (MetHb) level is greater than 70% and tissue oxygenation is impaired. Prilocaine is a local anesthetic widely used during circumcision in children that has been associated with methemoglobinemia in therapeutic doses. Infants are vulnerable to hemoglobin oxidation because their cytochrome b5 reductase level is approximately 50% of adult values and fetal hemoglobin is more sensitive to oxidation than adult hemoglobin. Six cases of methemoglobinemia occurring after the use of prilocaine during a circumcision are described. Six patients under the age of 2 years who had undergone prilocaine anesthesia were presented with cyanosis and a methemoglobin level of 35% to 50%. Four patients were treated with methylene blue as first-line therapy. In those 4 patients, cyanosis was resolved within 30 minutes in Case 1, an hour in Case 2, 2 hours in Case 3, and 4 hours in Case 5. In Case 3, the patient developed hemolysis following the methylene blue treatment. One patient was first treated with ascorbic acid due to a temporary shortage of methylene blue. The cyanosis improved in 1 hour and had regressed completely another hour later after a dose of methylene blue. In the final case, the cyanosis improved 30 minutes after intravenous administration of only ascorbic acid. All of the patients were discharged healthy. Bupivacaine may be more appropriate than prilocaine as a local anesthetic in young children due to the risk of potentially severe methemoglobinemia side effect of prilocaine.