Emir, İzzet; Aydın, Yıldız

This study aims to analyze the effects of features and classifiers in detecting cardiovascular diseases (CVD), which remain the leading cause of morbidity and mortality worldwide. Early and accurate detection of CVD significantly affects treatment outcomes. Therefore, the proposed method aims to automatically detect cardiovascular diseases via artificial intelligence. In this research, the performances of artificial intelligence methods for the cardiovascular disease detection problem are analyzed. The dataset used in this study was sourced from the publicly available Kaggle platform. It used for performance analysis in the developed application includes the features of 70000 patients such as age, gender, height, weight, blood pressure, cholesterol, glucose, smoking and alcohol use. These features were classified with Gradient Boosting, XGBoost, SVM, Random Forest, Logistic Regression, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) methods and performance comparison was performed. In the experimental results, the highest accuracy rate of 72.55% was obtained using the Gradient Boosting method, demonstrating its superior performance in cardiovascular disease detection. In addition, it was observed that the classification performance decreased when the high blood pressure attribute was removed from the dataset, while the removal of other features did not significantly affect the performance.

Akar, Funda

In recent years, the widespread availability of internet access has brought both advantages and disadvantages. Users now enjoy numerous benefits, including unlimited access to vast amounts of information and seamless communication with others. However, this accessibility also exposes users to various threats, including malicious software and deceptive practices, leading to victimization of many individuals. Common issues encountered include spam emails, fake websites, and phishing attempts. Given the essential nature of internet usage in contemporary society, the development of systems to protect users from such malicious activities has become imperative. Accordingly, this study utilized eight prominent machine learning algorithms to identify spam URLs using a large dataset. Since the dataset only contained URL information and spam classification, additional feature extractions such as URL length and the number of digits were necessary. The inclusion of such features enhances decision-making processes within the framework of machine learning, resulting in more efficient detection. As the effectiveness of feature extraction significantly impacts the results of the methods, the study initially conducted feature extraction and trained models based on the weight of features. This paper proposes a data correlated matrix approach for spam URL detection using machine learning algorithms. The distinctive aspect of this study lies in the feature extraction process applied to the dataset, aimed at discerning the most impactful features, and subsequently training models while considering the weighting of these features. The entire dataset was used without any reduction in data. Experimental findings indicate that tree-based machine learning algorithms yield superior results. Among all applied methods, the Random Forest approach achieved the highest success rate, with a detection rate of 96.33% for the non-spam class. Additionally, a combined and weighted calculation method yielded an accuracy of 94.16% for both spam and non-spam data.

Gamze, İspirlioğlu Kara; Özel, Adnan

Adhesively bonded joints are used as an alternative to classical mechanical joining methods, e.g., bolts, rivets, welding, and soldering, due to their advantages such as high strength, uniform stress distribution, and good fatigue resistance. These adhesively bonded joints are becoming more and more important, especially in fields where weight is critical, such as aviation and aerospace. Adhesively bonded joints are preferred because they offer highly reliable connections. In the present study, the low-cycle fatigue of materials joined together as adhesively bonded single-lap joints were investigated experimentally and numerically. Joints of aluminum and steel samples were subjected to variable loads that were lower than the experimentally obtained average breaking loads, and the number of cycles was determined. As a result, the fatigue life of adhesively bonded single-lap stainless steel samples was observed to be higher than that of aluminum samples. In addition, it was also observed that smudging adhesive around the endpoints of the joint significantly increased the fatigue life of steel samples.

Akgül, İsmail; Kaya, Volkan

Malaria is a disease that causes a parasite called plasmodium to be transmitted to humans as a result of the bite of female anopheles’ mosquitoes. Malaria is detected by examining the blood sample taken from the patient as a result of a microbiological examination under a microscope by specialist physicians. Although microscopy is widely used, its efficiency is low because it is time-consuming and depends on the interpretation of the specialist physician. In recent years, deep learning methods used in the field of computer vision increase the efficiency of specialist physicians by making a significant contribution to the decision-making process in solving real-life problems. In this study, ResNet architectures were preferred to quickly classify the malaria parasite using deep learning methods. For the training and testing of ResNet architectures, a dataset consisting of a total of 27558 red blood cell images containing 13779 parasitized and 13779 uninfected were used. Using this dataset, ResNet architectures were compared. As a result of the comparison, the best success accuracy (94.09%) was obtained with the ResNet-50 v2 model.

Osma, Etem; Elveren, Müjgan

Common drug active substances (gemfibrozil, β-estradiol, caffeine, and ciprofloxacin) were combined in simple mixtures and applied to soil containing wheat or barley. Mixtures in water (50 μg/mL) were applied twice during the growing period. Harvested plant samples were extracted and antioxidant enzyme activities, as indicated by CAT, POD, and SOD were compared in exposed and control plants. Lipid peroxidation markers were also determined. Finally, mineral element uptake in exposed and control plants was determined. The data indicated differences in several, if not all, of the plant biomarkers between control plants and those treated with simple mixtures of pharmaceutical substances; many were directly related to oxidative damage. It was determined that there were statistically significant differences in the element intake of 8 nutrients (magnesium, potassium, phosphorus, calcium, zinc, mangan, copper, and iron) in control plants compared with plants treated with PPCPs; we observed both increases and decreases in plant nutrients depending on the particular nutrient, pharmaceutical treatment, and plant species.

Yavuz, Sevtap Çaglar

Imidazole is a significant component of heterocyclic compounds and is employed in a wide range of practices. It is recognized that different imidazole-based constructions exhibit various biological activity features. Ten imidazole derivatives prepared from phenylglyoxal monohydrate and different guanylhydrazones were designed in our previous publication. This study was focused on the structural/electronic properties of these known imidazole derivatives. The molecular geometry of the compounds was calculated using Spartan 10 software and the structure was optimized using the DFT/B3LYP method with the 6-31G** basis set ground state. Also, in silico evaluation of imidazole derivatives was carried out using UCSF Chimera and AutoDock Vina software. The protein used in these calculations is the crystal structure of the 3SN6, beta2 adrenergic receptor-Gs protein complex, responsible for the hormonal regulation of adenylate cyclase.