Credit card fraud is an important issue and incurs a considerable cost for both cardholders and issuing institutions. Contemporary methods apply machine learning-based approaches to detect fraudulent behavior from transaction records. But manually generating features needs domain knowledge and may lay behind the modus operandi of fraud, which means we need to automatically focus on the most relevant patterns in fraudulent behavior. Therefore, in this work, we propose a spatial-temporal attention-based neural network (STAN) for fraud detection. In particular, transaction records are modeled by attention and 3D convolution mechanisms by integrating the corresponding information, including spatial and temporal behaviors. Attentional weights are jointly learned in an end-to-end manner with 3D convolution and detection networks. Afterward, we conduct extensive experiments on real-word fraud transaction dataset, the result shows that STAN performs better than other state-of-the-art baselines in both AUC and precision-recall curves. Moreover, we conduct empirical studies with domain experts on the proposed method for fraud post-analysis; the result demonstrates the effectiveness of our proposed method in both detecting suspicious transactions and mining fraud patterns.
The flexoelectric effect of materials, which is the coupling between strain gradient and electric polarization, is most noticeable for the micro/nano electromechanical systems. In the present paper, the size-dependent electromechanical properties of the bilayer piezoelectric sensor are studied and analyzed considering the strain gradient elastic and flexoelectric effects. The governing equation and the corresponding generalized mechanical boundary conditions of the bilayer cantilever sensor are derived utilizing the variational method of flexoelectric materials based on the electric Gibbs free energy. And a new piezo-flexoelectric coupling parameter is proposed and the relationship between the induced electric potential (voltage) and the rotation angles of the ends is obtained. The analytical expressions of deflection and induced electric potential are given when the bilayer piezoelectric sensor is subject to a uniform force. The numerical results show that the normalized deflection, normalized stiffness and induced electric potential are dependent on the structural size, material parameters and internal material length scale parameters. The piezoelectric effect will play a leading role in the induced electric potential when the sensor thickness is larger than a critical value. With decreasing sensor thickness, the flexoelectric and strain gradient elastic effects will dominate the induced electric potential. Moreover, an intrinsic size depending on the material properties is identified for the maximum induced electric potential. The thickness and polarization direction of the piezoelectric layer also have a great influence on the induced electric potential of the sensor systems.
A B S T R A C T In this paper, the fatigue life, surface crack extension direction and crack growth rate in an elastic bar with a circular cross section are determined through experiments under cyclic torsion with axial static and cyclic tension/compression loading. The effects of the loading type, loading value and stress ratio on the crack growth behaviour are discussed.The results show that, under pure fatigue torsion loading, the crack extension direction is almost the same whatever the value of torsion loading. Under fatigue torsion with cyclic tension loading, it is found that the crack extension direction is mainly determined by the alternating parts of the stresses and is almost independent of the average parts of the stresses, whereas the fatigue life is obviously dependent on the average stress.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.