Countless research works of deep neural networks (DNNs) in the task of credit card fraud detection have focused on improving the accuracy of point predictions and mitigating unwanted biases by building different network architectures or learning models. Quantifying uncertainty accompanied by point estimation is essential because it mitigates model unfairness and permits practitioners to develop trustworthy systems which abstain from suboptimal decisions due to low confidence. Explicitly, assessing uncertainties associated with DNNs predictions is critical in real-world card fraud detection settings for characteristic reasons, including (a) fraudsters constantly change their strategies, and accordingly, DNNs encounter observations that are not generated by the same process as the training distribution, (b) owing to the time-consuming process, very few transactions are timely checked by professional experts to update DNNs. Therefore, this study proposes three uncertainty quantification (UQ) techniques named Monte Carlo dropout, ensemble, and ensemble Monte Carlo dropout for card fraud detection applied on transaction data. Moreover, to evaluate the predictive uncertainty estimates, UQ confusion matrix and several performance metrics are utilized. Through experimental results, we show that the ensemble is more effective in capturing uncertainty corresponding to generated predictions. Additionally, we demonstrate that the proposed UQ methods provide extra insight to the point predictions, leading to elevate the fraud prevention process.
Topological Insulators are systems where the broken time reversal symmetry gives rise to protected edge modes that support backscatter-free and one-way propagation of electromagnetic waves by opening non-trivial bandgaps. In this study we investigate a oneway topologically protected waveguide in the frequency range of f=6.0 to 8.0 GHz. The time reversal symmetry is broken by an applied magnetic field in the z direction. We show that the waveguide propagates the light in only one direction that can be controlled by the applied magnetic field and no backscattering is present in the waveguide which results in a near 100% transmission of light to the output. Furthermore, we investigate effect of the applied magnetic field on the topological properties of the system by considering the material dispersion of the rods. Our results show that 3 different frequency ranges will be supported by the edge modes at each given magnetic field. By increasing the magnitude of the applied magnetic field, a blue shift in the non-trivial bandgap is seen, where it can be used to tailor the modes for the waveguide.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.