• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.31-40
• /
• 2012

Face recognition refers to the process of identifying individuals based on their facial features. It has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous consumer applications, such as access control, surveillance, security, credit-card verification, and criminal identification. However, illumination variation on face generally cause performance degradation of face recognition systems under practical environments. Thus, this paper proposes an novel face recognition system using a fusion approach based on local binary pattern and two-dimensional principal component analysis. To minimize illumination effects, the face image undergoes the local binary pattern operation, and the resultant image are divided into two sub-images. Then, two-dimensional principal component analysis algorithm is separately applied to each sub-images. The individual scores obtained from two sub-images are integrated using a weighted-summation rule, and the fused-score is utilized to classify the unknown user. The performance evaluation of the proposed system was performed using the Yale B database and CMU-PIE database, and the proposed method shows the better recognition results in comparison with existing face recognition techniques.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.231-240
• /
• 2020

E-commerce development led to the explosion of online payment. Consumers have many choices when deciding on the online payment method for each transaction. Using a combination of both qualitative and quantitative methods with the help of SPSS AMOS version 22.0, the article explores the factors that influence consumers' online payment method decision behavior in Vietnam. Research results show that awareness of usefulness, awareness of risk, awareness of trust, awareness ease of use, product uncertainly perception and perceived behavioral control have effects on the behavior of deciding on online payment methods. Awareness of risk has the strongest negative impact on online payment method decision behavior and awareness of usefulness has the strongest positive impact on online payment method decision behavior. Based on these important results, the article proposes a number of implications: (i) continuing to invest and upgrade modern technology to ensure customer information absolutely confidential; (ii) converting all ATM cards on the market to EMV chip standard card technology; (iii) improving service activities, quickly handle things to create confidence for customers; (iv) credit institutions operating in the field of online payment linked to e-commerce sites, supermarkets, convenience stores, restaurants must ask partners to increase transparency for the products.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.3
• /
• pp.79-89
• /
• 1998

The Error Back-Propagation(EBP) algorithm is widely applied to train a multi-layer perceptron, which is a neural network model frequently used to solve complex problems such as pattern recognition, adaptive control, and global optimization. However, the EBP is basically a gradient descent method, which may get stuck in a local minimum, leading to failure in finding the globally optimal solution. Moreover, a multi-layer perceptron suffers from locking a systematic determination of the network structure appropriate for a given problem. It is usually the case to determine the number of hidden nodes by trial and error. In this paper, we propose a new algorithm to efficiently train a multi-layer perceptron. OUr algorithm uses stochastic perturbation in the weight space to effectively escape from local minima in multi-layer perceptron learning. Stochastic perturbation probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the EGP learning gets stuck to it. Addition of new hidden nodes also can be viewed asa special case of stochastic perturbation. Using stochastic perturbation we can solve the local minima problem and the network structure design in a unified way. The results of our experiments with several benchmark test problems including theparity problem, the two-spirals problem, andthe credit-screening data show that our algorithm is very efficient.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.3
• /
• pp.65-74
• /
• 2012

A barcode is a representative means of cognition. It is either printed on the package of a product or attached to it as a sticker. It is used for the fast cognition of a product at a store. It is considerably cheap to make a barcode. Also, it is possible to read it fast by using a barcode reader. Because of such convenience provided by the barcode, a new system using the barcode as a means of settling payments like a currency or a credit card has been developed. However, due to its characteristics, it is easy to reduplicate, forge or falsify a barcode easily. Therefore, this study focuses on the case of applying the system using barcodes as a means of settling payments without providing solutions for the potential weaknesses. Also, this study suggests various points to consider regarding the creation of safe barcodes as one of the related measures, while providing various methods using additional means of certification other than the one of using barcodes in addition to the way of applying complexity with barcode numbers. Throughout this study, it will be possible to safely establish and operate the payment-settlement system using barcodes.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.3
• /
• pp.56-64
• /
• 2000

The purpose of this study is to analyze the success factors of the Sam Bo Hwa Seong Co., Ltd. this research is case study. In order to accomplish the objective, 1 had personal interview with the present Kim and reviewed business policy and company regulation. The main success factors of the Sam Bo Hwa Seong corporation are as following: first, a large experience of the top management, second, the artisan spirit and a mission sense of the CEO, third, a strong thrust of the present Kim, fourth, the partnership between labor and management, fifth, an exhaustive credit and a perfect quality control, sixth, research and development investment for the technical improvement. The result of this research will be a useful information to the management in small-medium firms and to the reserve management who wants establishment of the corporation.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.2
• /
• pp.643-655
• /
• 2021

This study investigated the effect of the Amanah Ikhtiar Malaysia (AIM) microfinancing on the economic, social, and household empowerment of women borrowers in Malaysia. The study used a quantitative approach based on primary data. For this study, the participants comprised 384 AIM borrowers from Terengganu, Kelantan, and Pahang in the east coast region of Malaysia. Purposive stratified random sampling was used as well as the Krejcie and Morgan method to count the number of samples. Descriptive statistics and the Women Empowerment Index (WEI) were used in the analysis. The study findings reveal that AIM microfinancing affects the economic, social, and household empowerment of women borrowers in Malaysia. However, in comparing the three categories, women enjoyed more freedom in social and household decision-making than in economic decision-making. The present study recommends policies for the successful and effective operation of microfinance programs by providing the necessary guidelines for the control of AIM loan for women borrowers; increasing income-generating activities, sufficient access of credit, and proper education for the borrowers; and giving economic freedom of choice with necessary skill training policymaking options for the government and NGOs with the aim to improve the total household income and empowerment of the microcredit borrowers in Malaysia.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.1
• /
• pp.343-352
• /
• 2021

This study aims to identify the impact of the audit approach based on business risks (i.e., external environment risk, operations risk, information risk) in reducing unsystematic risks (i.e., operational risk, credit risk, liquidity risk, capital risk, and administrative risk) in Jordanian banks. To reduce the effect of unsystematic risks and, thus, improve banking performance, an audit approach based on business risks has emerged. To achieve the objectives, this study relied on descriptive statistics and the regression approach to study twenty-five Jordanian banks. The researcher used the intentional sampling method represented by employees of the accounting, financial and control departments in Jordanian banks. Seventeen banks contributed to the study, with a percentage of 68%, totaling 356 employees. A questionnaire was designed to obtain the data, and due to homogeneity among the sampling members, a purposive sample was drawn and 300 questionnaires were distributed. The results of the study found a statistically significant effect of the audit approach based on business risks with its combined dimensions on reducing unsystematic risks in Jordanian banks. The results of the study also found a statistically significant effect of the business risk-based audit approach with its combined dimensions on reducing operational risks in Jordanian banks.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.7
• /
• pp.73-84
• /
• 2020

Existing studies disagree over the core predictors of firm-level financial choices in developing countries. The general practice only validates the traditional capital structure model, which leads to inconsistency and a lack of novelty. This study removed overfitting issues among existing factors and presented the most reliable and advanced capital structure model in Pakistani firms. The panel data include 368 Pakistani companies from 19 non-financial sectors over the period 2004 to 2017. We apply Akaike and Bayesian Information Criteria to remove overfitting issues among inconsistent proxies in the capital structure model. The fixed effects regression is used for basic results and the Generalized Method of Moments is applied to control the endogeneity. Besides the conventional proxies, we report that credit rating, distance from bankruptcy, managerial concentration, and institutional quality are the most advanced capital structure determinants in Pakistan. These predictors remain significant across firm size and growth levels. Also, the findings confirm that new predictors are reliable to define capital structure dynamics and improve the speed of adjustment in overall and sub-sample analysis. The major findings suggest that managers and policymakers should consider these advanced predictors to design their financial settings in firms.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.365-373
• /
• 2021

Loan monitoring is a fundamental element of credit control. The importance of loan monitoring is to reduce loan defaults and to increase loan repayment performance. The ex-post monitoring can also increase the loan quality and thus a concern to many creditors in the market economy. This study identifies the role of ex-post monitoring on loan repayment performance in the context of rural Vietnam. Employing primary data from rural areas of Vietnam, this study investigates the impacts of ex-post monitoring on loan repayment performance of individual borrowers in terms of on-time loan repayment and the rate of loan repayment. Descriptions of borrower demographics, loan information, and ex-post monitoring show the initial picture of borrowers and loans in Vietnam's rural areas. Quantitative estimations that use the Probit and the Tobit model confirm the argument that better ex-post monitoring would result in better loan repayment performance in both on-time repayment and repayment rate. Thus, some policy suggestions have been made to improve the monitoring system in each financial institution. The study also indicates that some other factors too affect loan repayment performance such as borrower's characteristics (education, agricultural working area, and income) as well as loan's characteristics (loan size, maturity, and loan purpose).

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.421-431
• /
• 2021

This study investigates the empirical linkages between ASEAN countries' institutional quality and financial inclusion using country data from 2008-2019. In this paper, six governance indicators from the World Governance index are used to measure the impact of institutions on financial inclusion. The PCA method's financial inclusion index is constructed from 3 indicators: penetration, access, and usage: penetration, access, and usage with six indices respectively as the number of ATMs per 1000 km², the number of bank branches per 1000 km², the number of ATMs per 100,000 people and the number of bank branches for 100,000 adults, the ratio of credit to private to GDP, and the ratio of deposit to private to GDP. Regression analysis with the Generalized Moments method shows the positive impact of institutions and other control variables like GDP per capita, inflation, bank concentration, and human development index on financial inclusion. Therefore, this study recommends that the government and policymakers in countries pursue the financial inclusion agenda to pay attention to the financial and economic indicators and institutional factors. This is because many savers, borrowers, and investors may not be protected when financial contracts are enforced or breaches occur in an environment where economic, legal, judicial, and political institutions are weak, such as in ASEAN countries.