As the usage of social media has increased, the size of shared data has instantly surged and this has been an important source of research for environmental issues as it has been with popular topics. Sentiment analysis has been used to determine people's sensitivity and behavior in environmental issues. However, the analysis of Turkish texts has not been investigated much in literature. In this article, sentiment analysis of Turkish tweets about global warming and climate change is determined by machine learning methods. In this regard, by using algorithms that are determined by supervised methods (linear classifiers and probabilistic classifiers) with trained thirty thousand randomly selected Turkish tweets, sentiment intensity (positive, negative, and neutral) has been detected and algorithm performance ratios have been compared. This study also provides benchmarking results for future sentiment analysis studies on Turkish texts.

The significance and novelty of the present work is the preparation of non-lead ceramics with the general formula of (1 − x)K0.5Na0.5NbO3–xLaMn0.5Ni0.5O3 (KNN–LMN) with different values of x (0 < x < 20) (mol%) to examine the shielding qualities of the KNN–LMN ceramics. This is done by carrying out Phy-X/PSD calculation and predicting the attenuation behavior of the samples by utilizing the deep learning (DL) algorithm. From the attained results, it is seen that the higher the x (concentration of LMN in the KNN–LMN lead-free ceramics), the better the shielding proficiency observed in terms of gamma-shielding performance for the chosen KNN–LMN-based lead-free ceramics. In all sections, good agreement is observed between Phy-X/PSD results and DL predictions.

Representation of words in mathematical expressions is an essential issue in natural language processing. In this study, data sets in different categories are classified as positive or negative according to their content. Using the Glove (Global Vector for Word Representation) method, which is one of the word embedding methods, the effect of the vector set based on the word similarities previously calculated on the classification performance has been analyzed. In this study, the effect of pre-trained, embedded and deterministic word embedding classification performance has analyzed by using Long Short-Term Memory (LSTM). The proposed LSTM based deep learning model has been tested on three different data sets and the results have been evaluated.

No abstract

Today, image processing has been used in many different sectors, especially in health, production and military fields, for various purposes directly in human life. The development of deep learning algorithms and starting to use of computer vision has accelerated the studies such as critical target, important location and strategic region determination especially in the military field. In this study, the airport has been determined on the landing runways. Training, test and evaluation data sets were created by using both medium and high-altitude unmanned air vehicles and satellite images. SSD-Single Shot Multibox algorithm and Faster R-CNN algorithm were used by retraining during the determination process. The results of both algorithms were evaluated within the extend of evaluation criteria such as accuracy, sensitivity, specificity, false positive rate, false negative rate, positive pred value, F score, error rate, result and training time. The image detection accuracy with SSD algorithm was 76,61%, with Faster R-CNN algorithm the image detection accuracy was 99.52% according to valuation dataset. With this study, which of the two architectures has been revealed to be successful in determining critical areas in unmanned aerial vehicles and satellite images.

No abstract

Credit card payment is one of the most preferred methods of e-commerce sites. Fraud orders are the biggest concerns for online shopping sites. Fraud operations affect not only customers but also companies and banks. Hence, companies should be able to classify orders and take measures against suspicious transactions. Classification is easier on the banking side because of more information about customers, but it is more difficult to determine this process on e-commerce sites. In this study, the actual order data of a private e-commerce enterprise has been examined and suspicious transactions are determined. First of all, all order data is analyzed and filtered. The best variables for classification are determined by variable selection algorithms. Afterwards, classification algorithms are applied and suspicious orders are determined with 92% success rate. Naïve Bayesian, Decision Trees and Artificial Neural Network have been used as comparative data mining methods.

In the 1950s, the concept of artificial intelligence emerged, suggesting that machines could possess the ability to think and learn. In the 21st century, with advancements in GPUs and CPUs, deep learning has become an integral part of human life. Proximal femoral fractures are known to be one of the leading causes of mortality and injuries among the elderly population. This study aims to detect proximal femoral fractures in X-ray images and compare the success of using the YOLOv4 algorithm and provide decision support system within the diagnosis. To retrain the algorithm, more than 500 patients’ X-ray images were examined. Through data augmentation techniques, the initial set of 410 patients’ femur proximal fracture X-ray images was expanded to 820 images. After retraining the YOLO algorithm, two different groups were included for comparing the algorithm’s performance: orthopedic specialists and general practitioners. The results from these three groups were evaluated using specific criteria. The YOLOv4 model demonstrated an accuracy of 90.33%. In comparison, orthopedic and traumatology resident doctors achieved an accuracy of 91.42%, while the general practitioner group achieved an accuracy of 81.30%.