E-commerce is growing rapidly around the world and this causes a significant increase in credit card transactions, both normal and fraud transactions. Financial institutions throughout the world lose billions because of credit card fraud. Fraudsters have no fixed styles; they always change their behavior and try to learn new technologies that allow them to commit frauds through online transactions. Moreover, they assume that the regular behavior of consumers and fraud patterns change fast. Fraud detection systems have become necessary for banks and financial institutions to minimize their losses. However, not much research has been conducted on credit card fraud detection methodologies, due to the unavailability of credit card transaction dataset for researchers. Also, most of the researchers apply either machine learning or deep learning techniques without comparing the results of applying both techniques in the same dataset. This research aims to apply different machine learning (Logistic Regression, K-Nearest Neighbor, Random Forest) and deep learning (Deep Neural Network, Convolutional Neural Network) techniques in a real-life credit card dataset to choose the most efficient algorithm for detecting fraud transactions. After applying different experiments with different parameters using all the algorithms mentioned before, the Random Forest Algorithm gives slightly better accuracy than Deep Neural Networks.
The measurement of electrical activity of the heart via electrodes is named as Electrocardiography (ECG). An efficient compression technique using the compressive sensing method is required. Compressive Sensing (CS) holds the promise to be a key for acquisition and reconstruction of sparse signals. The reconstruction of such signals makes sampling rates below Nyquist rate. In this work, a novel framework was proposed that is based on the idea of CS theory for the compression of mother and fetal heart beats. The proposed scheme is based on the sparse representation of the components derived from the curvelet transform of the original Electrocardiogram (ECG) signal. The ECG signals may be approximated by a few coefficients that can be taken from a wavelet basis. This fact allows a compressed sensing approach for ECG signal compression to be introduced and to be a domain of search. ECG signals illustrate redundancy between adjacent heart beats. This redundancy implies a high fraction of common support between consecutive heart beats. The main contribution of this paper lies in the using of curvelet transform in order to generate sparsity in ECG signal. This transformation is considered an excellent approach as illustrated in this paper. Simulation results represent a better approach than Discrete Wavelet Transform (DWT) that is based on compression of ECG. MIT-BIH database is used for experimentation. The MIT-BIH database contains different kinds of ECG signals that include both abnormal ECG and normal ECG, which have different sampling rates. MATLAB tool is used for simulation purpose. The novelty of the method is that the Compression Ratio (CR) achieved by detail coefficients is better. The performance measure of the reconstructed signal is carried out by Percentage Root Mean Difference (PRD). This paper also introduces the efficient realization of the different transformation techniques using FPGA. Thus the contribution of this paper lies into two main parts. The first part is specialized in determining the proper transformation that is used in the compression of ECG signals. The second part of the contribution is summarized in using suitable hardware to implement this design. Architecture can be based on the ideas of parallelism and pipelining to get the minimum throughput and speed. Architecture is cascade and simple for calculating curvelet coefficients. The reduction of the memory size can be done by splitting ROM table. The description and functionalities of the design are modeled by Verilog HDL. The simulation and synthesis methodology are used on Virtex-II Pro FPGA that uses less number of resources of the FPGA.
This paper presents a genetic algorithm optimization for MIS/IL solar cell parameters including doping concentration NA, metal work function Om, oxide thickness do ", mobile charge density N m , fixed oxide charge density N" and the external back bias applied to the inversion grid V. The optimization results are compared with theoretical optimization and shows that the genetic algorithm can be used for determining the optimum parameters of the cell.
This paper proposes a design of an asynchronous switch interfacing circuit between any numbers of different local clock synchronous domains. The asynchronous switch will generate a slower clock frequency from different local clock modules and moderate the high rated clock domain to slow down its clock frequency without stopping or pausing any clock of them during the data communication phase. The proposed design is implemented using the CMOS 45nm technology of STMicroelectronics and simulated using timed VHDL model (Xilinx ISE Design Suite 12.1). The delay time is required to change the clock frequency is mathematically modeled. It is shown that the switching delay time depends on the number of multipoint communicating domains. The proposed system is designed to use a small number of circuit elements that results in conspicuous improvements in terms of power consumption, throughput, and circuit area.In this section, a new method is presented for interfacing different clock frequencies in a GALS system. The proposed GALS system uses the asynchronous ring oscillator as the main generating source of local clock in each synchronous domain. This method is based on slowing down the clock
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.