Pneumonia is a fatal disease that appears in the lungs and is caused by viral or bacterial infection. Diagnosis of pneumonia in chest X-ray images can be difficult and error-prone because of its similarity with other infections in the lungs. The aim of this study is to develop a computer-aided pneumonia detection system to facilitate the diagnosis decision process. Therefore, a convolutional neural network (CNN) ensemble method was proposed for the automatic diagnosis of pneumonia which is seen in children. In this context, seven well-known CNN models (VGG-16, VGG-19, ResNet-50, Inception-V3, Xception, MobileNet, and SqueezeNet) pre-trained on the ImageNet dataset were trained with the appropriate transfer learning and fine-tuning strategies on the chest X-ray dataset. Among the seven different models, the three most successful ones were selected for the ensemble method. The final results were obtained by combining the predictions of CNN models with the ensemble method during the test. In addition, a CNN model was trained from scratch, and the results of this model were compared with the proposed ensemble method. The proposed ensemble method achieved remarkable results with an AUC of 95.21 and a sensitivity of 97.76 on the test data. Also, the proposed ensemble method achieved classification accuracy of 90.71 in chest X-ray images as normal, viral pneumonia, and bacterial pneumonia.

No abstract

No abstract

ÖzGünümüzde Kardiyovasküler Hastalıklar oldukça yaygındır ve ölüm nedenlerinin başında gelmektedir. Kardiyovasküler Hastalıkların bir tipi olan Koroner Arter Hastalığının doğru ve zamanında teşhisi çok önemlidir. Koroner arter hastalığının kesin tanısı ve hastalık şiddetinin saptanmasında invaziv bir yöntem olan anjiyografi altın standart olarak kullanılmaktadır. Anjiyografi, maliyeti yüksek ve ileri seviyede uzmanlık gerektiren bir yöntem olmasının yanında ciddi komplikasyonlara da sebep olabilmektedir. Bu nedenlerle daha ucuz ve etkili bir yaklaşım sağlayabilecek olan veri madenciliğinin kullanımı üzerinde çalışmalar yapılmaktadır. Bu çalışmada Koroner Arter Hastalığı riskinin tespitinde bir sınıflama modeli geliştirmek için veri madenciliği yaklaşımı uygulanmıştır. Çalışma kapsamında sınıflandırma yöntemleri ile elde edilen sonuçlar ve doğru sınıflandırma oranları karşılaştırılmıştır. Bunun için Cleveland kliniğine ait, 303 kayıt ve 14 değişken içeren kalp hastalığı veri kümesi kullanılmıştır. Gerekli hesaplamalar ve modelleri elde etmek için Weka paket programında 1R, J48 Karar Ağacı, Naive Bayes ve Çok katmanlı yapay sinir ağı (YSA) sınıflandırma yöntemleri uygulanmıştır. Uygulama sonucunda Koroner Arter Hastalığının tespitinde en iyi sonucun %83,498 doğruluk oranı ile Çok katmanlı YSA sınıflandırma yöntemi ile elde edildiği görülmüştür. Çok katmanlı YSA algoritmasını Naive Bayes ve Düzenlenmiş J48 Karar Ağacı algoritmaları izlemiştir. AbstractCardiovascular Diseases are quite common nowadays and are one of the leading causes of death. The correct and timely diagnosis of Coronary Artery Disease, a type of Cardiovascular Disease, is very important for further treatment of the patients. For accurate diagnosis of coronary artery disease and determination of disease severity, angiography, which is an invasive and gold standard diagnosis tool, is used. Angiography is a costly and advanced method that requires clinical expertise and may cause serious complications. For these reasons, research on using data mining techniques, which is a cheaper and more effective approach, for diagnosis is one of today's research topics. In this study, classification-based data mining methods were used to determine the risk of coronary artery disease and these methods were compared in terms of accuracy. A data set consisting of 303 patient records and 14 attributes of Cleveland clinic were used. In particular, 1R, J48 Decision Tree, Naive Bayes and Multilayer Artificial Neural Network classification methods were applied on this data set with the help of WEKA program. The best result (in terms of correct diagnosis ratio) in determining risk of Coronary Artery Disease was obtained with Artificial Neural Network classification method with an accuracy of 83.498%. The multi-layer ANN algorithm was followed by Naive Bayes and the J48 Decision Tree algorithms.

One of the most important problems in machine learning, which has gained importance in recent years, is classification. The k-nearest neighbors (kNN) algorithm is widely used in classification problem because it is a simple and effective method. However, there are several factors affecting the performance of kNN algorithm. One of them is determining an appropriate proximity (distance or similarity) measure. Although the Euclidean distance is often used as a proximity measure in the application of the kNN, studies show that the use of different proximity measures can improve the performance of the kNN. In this study, we propose the Weighted Similarity k-Nearest Neighbors algorithm (WS-kNN) which use a weighted similarity as proximity measure in the kNN algorithm. Firstly, it calculates the weight of each attribute and similarity between the instances in the dataset. And then, it weights similarities by attribute weights and creates a weighted similarity matrix to use as proximity measure. The proposed algorithm is compared with the classical kNN method based on the Euclidean distance. To verify the performance of our algorithm, experiments are made on 10 different real-life datasets from the UCI (UC Irvine Machine Learning Repository) by classification accuracy. Experimental results show that the proposed WS-kNN algorithm can achieve comparative classification accuracy. For some datasets, this new algorithm gives highly good results.