OffSig-SinGAN: A Deep Learning-Based Image Augmentation Model for Offline Signature Verification

Offline signature verification(OfSV)is essential in preventing the falsification of documents.Deep learning(DL)based OfSVs require a high number of signature images to attain acceptable performance.However,a limited number of signature samples are available to train these models in a real-world scenario.Several researchers have proposed models to augment new signature images by applying various transformations.Others,on the other hand,have used human neuromotor and cognitive-inspired augmentation models to address the demand for more signature samples.Hence,augmenting a sufficient number of signatures with variations is still a challenging task.This study proposed OffSig-SinGAN:a deep learning-based image augmentation model to address the limited number of signatures problem on offline signature verification.The proposed model is capable of augmenting better quality signatures with diversity from a single signature image only.It is empirically evaluated on widely used public datasets;GPDSsyntheticSignature.The quality of augmented signature images is assessed using four metrics like pixel-by-pixel difference,peak signal-to-noise ratio(PSNR),structural similarity index measure(SSIM),and frechet inception distance(FID).Furthermore,various experiments were organised to evaluate the proposed image augmentation model’s performance on selected DL-based OfSV systems and to prove whether it helped to improve the verification accuracy rate.Experiment results showed that the proposed augmentation model performed better on the GPDSsyntheticSignature dataset than other augmentation methods.The improved verification accuracy rate of the selected DL-based OfSV system proved the effectiveness of the proposed augmentation model.

Dependence of effective screening length in granular columns on bead and silo sizes and their ratio

Apparent mass measurements at the bottom of silos have been carried out. An important parameter in the Janssen model known as the effective screening length has been investigated for different bead and silo diameters as well as of their ratios. It is found that the effective screening length augments with the grain diameter d in addition to the granular column size. It is also revealed that λ exhibits stronger correlation with the bead diameter than that of the silo. This phenomenon is attributed to the reduced-shielding of the vertical stresses to the horizontal ones.

Reflection of thermoelastic wave on the interface of isotropic half-space and tetragonal syngony anisotropic medium of classes 4, 4/m with thermomechanical effect

The thermoelastic wave propagation in a tetragonal syngony anisotropic medium of classes 4, 4/m having heterogeneity along z axis has been investigated by employing matrizant method. This medium has an axis of second-order symmetry parallel to z axis. In the case of the fourth-order matrix coefficients, the problems of wave refraction and reflection on the interface of homogeneous anisotropic thermoelastic mediums are solved analytically.

An Open IoT Framework Based on Microservices Architecture

With the continuous development and evolvement of Internet of Things(Io T), monolithic application becomes much larger in scale and even more complex in structure. This leads to poor scalability, extensibility and maintainability. In response to those challenges, microservice architecture has been introduced in the field of Io T application, due to its flexibility, lightweight and loose coupling. However, the existing Io T framework of microservice mainly focus on a specific domain, therefore, this greatly limits its application. In this paper, we propose a general microservice system framework for the Io T application, which is a better scalable, extendable and maintainable architecture. We introduce its system design and related microservices, and emphasize on core service and device communication from service layer to physical layer. It has better capacity to support interoperability and accommodate heterogeneous objects. In addition, this framework can easily achieve more application integration such as automation, intelligence, Geo service and Big Data.

Do Macroeconomic Determinants of Non-Performing Loans Vary with the Income Levels of Countries?

This paper explores the macroeconomic determinants of non-performing loans(NPL) in 19 Asian countries(low to high income economies) using the Generalized Method of Moments estimation approach based on the economic data for the period between 1998 and 2015. The categorization of the economies is based on the average gross national income per capita as set by the World Bank.Specifically, the paper aims to evaluate if the determinants of NPL vary with the income levels of the countries. The results indicate that the NPL is strongly influenced by the inflation rate. The effect is,however, negative in the high-income and the middle-income countries and positive in the low-income countries. The GDP per capita has a dynamic negative relationship with the NPL in the high-income and the low-income countries. The remittance has a significant positive association in the high-income and a significant negative association in the low-income countries. Similarly, the unemployment rate has a positive effect on NPL in the middle-income and the low-income countries. With the rise in the official exchange rate, the NPL level increases in the low-income countries. The overall estimation results suggest that the NPL in Asian banking system depend on some key macroeconomic variables,such as unemployment rate, inflation rate, official exchange rate, remittance received and gross domestic product per capita, and these associations vary with the income level of the countries. Therefore,economic level of a country should be carefully considered while formulating credit policy to minimize credit risks in the banking system.

Return and Volatility Connectedness between Stock Markets and Macroeconomic Factors in the G-7 Countries

We examine the relationship between return and volatility of the stock markets and macroeconomic fundamentals for the G-7 countries by using monthly data ranging from July 1985 to June 2015. To meet this end, we apply the spillover index approach based on the generalized VAR framework developed by Diebold and Yilmaz (2012, 2014). The empirical analysis shows strong interactions between the returns and volatilities of the G-7 stock markets and the considered set of corresponding macroeconomic factors including industrial production, money supply, interest rates, inflation, oil prices and exchange rates. The return and volatility spillover transmission/reception dynamics of the relationships between these stock markets and the macroeconomic fundamentals have changed after the global financial crisis of 2008. Our findings provide useful insights for investors and policy makers concerned with the unprecedented swings in the stock markets of G-7 countries.

Cointegration and Causality Relationship Between Stock Market,Money Market and Foreign Exchange Market in Pakistan

This paper examines the relationship between stock market(KSE-100), money market(M2 and 180 days T-bill rate), and foreign exchange market(ER: PKR/USD) in Pakistan by using monthly data covering the period from 2000:M1 to 2015:M12. The study investigates long-run equilibrium relationship between these three financial markets by employing Johansen and Juselius[1]cointegration tests. Long-run and short-run causality relationship between stock market and other macroeconomic variables is also established by employing vector error correction model(VECM) and pairwise granger causality tests. The results of multivariate cointegration test(trace test) indicate a one cointegrating vector, and the significant normalized cointegrating coefficients are evident of long run equilibrium relationship between all the selected variables. Negative and significant ECT(-1) for all variables during full sample period witness the presence of long-run causality connection among variables, while during the military regime and democratic regime, significant difference of long-run causal connections are identified across the regimes. Moreover, the results of granger causality test also indicate that there are significant variations in the causality relationship among variables across the regimes. Therefore, it is essential for forecasting, planning and policy making to consider the importance of political governance system while analyzing the historical cointegration among financial market and make the necessary adjustments accordingly.