Identification and location of defects in software projects is an important task to improve software quality and to reduce software test effort estimation cost. In software fault prediction domain, it is known that 20% of the modules will in general contain about 80% of the faults. In order to minimize cost and effort, it is considerably important to identify those most error prone modules precisely and correct them in time. Machine Learning (ML) algorithms are frequently used to locate error prone modules automatically. Furthermore, the performance of the algorithms is closely related to determine the most valuable software metrics. The aim of this research is to develop a Majority Vote based Feature Selection algorithm (MVFS) to identify the most valuable software metrics. The core idea of the method is to identify the most influential software metrics with the collaboration of various feature rankers. To test the efficiency of the proposed method, we used CM1, JM1, KC1, PC1, Eclipse Equinox, Eclipse JDT datasets and J48, NB, K-NN (IBk) ML algorithms. The experiments show that the proposed method is able to find out the most significant software metrics that enhances defect prediction performance.

Requirements Engineering (RE) is an important step in the whole software development lifecycle. The problem in RE is to determine the class of the software requirements as functional (FR) and non-functional (NFR). Proper and early identification of these requirements is vital for the entire development cycle. On the other hand, manual identification of these classes is a timewaster, and it needs to be automated. Methodically, machine learning (ML) approaches are applied to address this problem. In this study, twenty ML algorithms, such as Naïve Bayes, Rotation Forests, Convolutional Neural Networks, and transformers such as BERT, were used to predict FR and NFR. Any ML algorithm requires a dataset for training. For this goal, we generated a unique Turkish dataset having collected the requirements from real-world software projects with 4600 samples. The generated Turkish dataset was used to assess the performance of the three groups of ML algorithms in terms of F-score and related statistical metrics. In particular, out of 20 ML algorithms, BERTurk was found to be the most successful algorithm for discriminating FR and NFR in terms of a 95% F-score metric. From the FR and NFR identification problem point of view, transformer algorithms show significantly better performances.

Günümüzde insan kulak görüntülerinin kullanımı, biyometrik yetkilendirme ve gözetleme sistemlerinin sürdürülebilirliği adına önem kazanmaktadır. Güncel çalışmalar, böyle işlemlerin el ile yapılması yerine yarı otomatik veya tam otomatik olarak yapılabileceğini göstermektedir. Derin öğrenme soyut öznitelikleri (temsili öğrenme) kullanması nedeniyle klasik yöntemlere göre oldukça yüksek başarım değerlerine ulaşmaktadır. Çalışmamızda insanların cinsiyetlerine göre tam otomatik olarak sınıflandırılmasında insan kulağı görüntülerinin kullanımına dayanan melez derin öğrenme tabanlı sinerjik bir cinsiyet tanıma yaklaşımı oluşturulmuştur. Melezleme yoluyla hem evrişimli sinir ağı bileşeni hem de tekrarlayan sinir ağı tipli bileşenlerini bir arada içeren melez derin sinir ağı mimari modelleri kullanılmıştır. Bu modellerde tekrarlayan sinir ağı tipi bileşenler olarak uzun kısa süreli bellek ve kapılı tekrarlayan birim alınmıştır. Bu bileşenler sayesinde melez model görüntü içerisindeki piksel bölgeleri arasındaki ilişkisel bağımlılıkları oldukça iyi elde etmektedir. Bu sinerjik yaklaşım sayesinde çalışmamızdaki tek başına evrişimli sinir ağı modeline göre melez modellerin cinsiyet sınıflandırma doğruluğu daha yüksek olmaktadır. Cinsiyet işaretlemesine sahip iki farklı görüntü veri kümesi deneylerimizde kullanılmıştır. Deneysel sonuçların güvenirliği nesnel ölçütlerle kanıtlanmıştır. Yapılan deneylerde melez modellerle yapılan cinsiyet tanımada en yüksek değerler sırasıyla, EarVN veri kümesi için test doğruluğu %85,16 ve WPUT veri kümesi için test doğruluğu %87,61 oranlarında elde edilmiştir. Çalışmamızın son bölümünde tartışma ve sonuçlara yer verilmektedir. Nowadays, the use of the human ear images gains importance for the sustainability of biometric authorization and surveillance systems. Contemporary studies show that such processes can be done semi-automatically or fully automatically, instead of being done manually. Due to the fact that deep learning uses abstract features (i.e., representation learning), it reaches quite high performance values compared to classical methods. In our study, a synergistic gender recognition approach based on hybrid deep learning was created based on the use of human ear images in classifying people fully automatically according to their gender. By means of hybridization, hybrid deep neural network architectural models are used, which include both convolutional neural network component and recurrent neural network type components together. In these models, long-short term memory and gated recurrent unit are taken as recurrent neural network type components. Thanks to these components, the hybrid model extracts the relational dependencies between the pixel regions in the image very well. On account of this synergistic approach, the gender classification accuracy of hybrid models is higher than the standalone convolutional neural network model in our study. Two different image datasets with gender marking were used in our experiments. The reliability of the experimental results has been proven by objective metrics. In the conducted experiments, the highest values in gender recognition with hybrid models were obtained with the test accuracy of 85.16% for the EarVN dataset and 87.61% for the WPUT dataset, respectively. Discussion and conclusions are included in the last section of our study.

In 5G vehicular networks, two key challenges have become apparent, including end-to-end delay minimization and data privacy. Learning-based approaches have been used to alleviate these, either by predicting delay or protecting privacy. Traditional approaches train machine learning models on local devices or cloud servers, each with their own trade-offs. While pure-federated learning protects privacy, it sacrifices delay prediction performance. In contrast, centralized training improves delay prediction but violates privacy. Existing studies in the literature overlook the effect of training location on delay prediction and data privacy. To address both issues, we propose a novel genetic algorithm optimized federated learning (GAoFL) approach in which end-to-end delay prediction and data privacy are jointly considered to obtain an optimal solution. For this purpose, we analytically define a novel end-to-end delay formula and data privacy metrics. Accordingly, a novel fitness function is formulated to optimize both the location of training model and data privacy. In conclusion, according to the evaluation results, it can be advocated that the outcomes of the study highlight that training location significantly affects privacy and performance. Moreover, it can be claimed that the proposed GAoFL improves data privacy compared to centralized learning while achieving better delay prediction than other federated methods, offering a valuable solution for 5G vehicular computing.

Requirements Engineering (RE) is an important step in the whole software development lifecycle. The problem in RE is to determine the class of the software requirements as functional and non-functional. Proper and early identification of these requirements is vital for the entire development cycle. On the other hand, manual government of requirement classes is a timewasting task, and it needs intensive effort. Automatic requirement classification techniques through advanced Machine Learning (ML) strategies are started to be developed to address this problem. Basically, software requirements are generated as natural language explanations and therefore requirement classification may be handled as a particular Natural Language Processing (NLP) problem. From ML point of view, classification strategies require dataset to be used in the training/learning phase. For this goal, we generated a unique Turkish dataset having collected the requiremenst from real-world software projects with 4600 samples. Of these requirements, 3000 and 1600 were labeled as functional and non-functional, respectively. The data set has been evaluated using (i) traditional machine learning algorithms, (ii) deep learning algorithms, and (iii) transformer models respectively. As a result BERTurk was found to be the most successful algorithm to discriminate functional and non-functional requirements in terms of 95% f-score metric.

Yazılım geliştirme teknolojilerinde yaşanan gelişmeler, yazılımların geliştirilmesinde kullanılan yazılım yaşam döngülerinin sürelerinin kısalması, yazılımlardaki kapsamın ve gereksinimlerin artması ile beraber farklı çevik yazılım geliştirme yaklaşımlarını ortaya çıkarmıştır. Çalışmada bir çevik yazılım geliştirme yöntemi olan SCRUM detaylı olarak anlatılmış ve farklı teknolojilere göre geliştirilen web ve arttırılmış gerçeklik temelli iki SCRUM Görev Tahtası uygulamasının kullanımı ile elde edilen sonuçlara yer verilmiştir. Geliştirilen arttırılmış gerçeklik temelli Scrum Görev Tahtası uygulaması, web-tabanlı Scrum uygulamasının gerçekleştirdiği işlemleri yapabilmektedir. Geliştirilen her iki uygulama karşılaştırıldığında, web-tabanlı Scrum Görev Tahtası uygulamasının AR tabanlı Scrum Görev Tahtası uygulamasına göre kullanımının daha kolay olduğu, daha az teknoloji ve teknik bilgi gerektirdiği görülmüştür.