Deep learning method is widely used in computer vision tasks with large scale annotated datasets. However, it is a big challenge to obtain such datasets in most directions of the vision based non-destructive testing (NDT) field. Data augmentation is proved as an efficient way in dealing with the lack of large-scale annotated datasets. In this paper, we propose CycleGAN-based extra-supervised (CycleGAN-ES) to generate synthetic NDT images, where the ES is used to ensure that the bidirectional mapping are learned for corresponding label and defect. Furthermore, we show the effectiveness of using the synthesized images to train deep convolutional neural networks (DCNN) for defects recognition. In the experiments, we extract numbers of X-ray welding images with both defect and no-defect from the published GDXray dataset, CycleGAN-ES are used to generate the synthetic defect images based on a small number of extracted defect images and manually drawn labels which are used as a content guide. For quality verification of the synthesized defect images, we use a high-performance classifier pre-trained using big dataset to recognize the synthetic defects and show comparability of the performances of classifiers trained using synthetic defects and real defects respectively. To present the effectiveness of using the synthesized defects as an augmentation method, we train and evaluate the performances of DCNN for defects recognition with or without the synthesized defects.

Credit card fraud is a wide-ranging issue for financial institutions, involving theft and fraud committed using a payment card. In this paper, we explore the application of linear and nonlinear statistical modeling and machine learning models on real credit card transaction data. The models built are supervised fraud models that attempt to identify which transactions are most likely fraudulent. We discuss the processes of data exploration, data cleaning, variable creation, feature selection, model algorithms, and results. Five different supervised models are explored and compared including logistic regression, neural networks, random forest, boosted tree and support vector machines. The boosted tree model shows the best fraud detection result (FDR = 49.83%) for this particular data set. The resulting model can be utilized in a credit card fraud detection system. A similar model development process can be performed in related business domains such as insurance and telecommunications, to avoid or detect fraudulent activity.

No abstract

A large number of carbon fiber reinforced polymers have been applied to aircraft and automobiles, and many nondestructive testing methods have been studied to detect their defects. Eddy current magneto-optical imaging nondestructive testing technology has been widely used in the detection of metal materials such as aircraft skin, but it usually requires a large excitation current and, at present, can only detect metal materials with high conductivity. In order to take full advantage of the innate benefits and efficiency of eddy current magneto-optic imaging and enable it to detect defects in carbon fiber reinforced polymers with weak conductivity, it is necessary to improve the magnetic field response of the eddy current magneto-optic imaging system and explore suitable excitation and detection methods. The scanning eddy current magneto-optical imaging nondestructive testing device built in this study has improved the magnetic field response of the system, and the eddy current magneto-optical phase imaging testing method has been proposed to detect the crack defects of carbon fiber reinforced polymers. The effectiveness of the method has been verified by simulation and experiment.

No abstract