• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.239-252
• /
• 2005

Ubiquitous Sensor Network(USN) , the core technology for the Ubiquitous environments ,must be operated in the restrictive battery capacity and computing. From this cause, USN needs the lightweight design for low electric energy and the minimum computing. The previous mutual authentication. based on J$\emptyset$sang's trust model, in USN has a character that makes the lightweight mutual authentication possible in conformity with minimum computing. But, it has an imperfection at the components of representing the trust from a lightweight point of view. In this paper, we improve on the J$\emptyset$sang's trust model to apply a lightweight mutual authentication in USN. The proposed trust model in USN defines the trust information with the only degree of trust-entity(x)'s belief. The defined trust information has a superiority over the J$\emptyset$sang's trust model from a computing Point of view. because it computes information by Probability and logic operation(AND).

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.293-296
• /
• 2005

최근 우리나라는 가계신용의 급신장과 신용불량의 급증 등으로 개인 신용부문이 금융기관의 건전성 유지에 부정적인 영향을 미치고 있다. 이러한 잠재적 문제를 사전에 방지하기 위해 금융기관 등에서는 개인 신용평가에 대한 수요가 커지고 있는 실정이다. 주어진 데이터로부터의 반복적인 학습 과정을 거쳐 패턴을 분류하고 또한 모델과 학습 방법에 따라 입력변수와 목적변수의 속성이 연속형이나 이산형인 경우를 모두 다룰 수 있는 신경망 모델은 개개인의 다양하고 복잡한 데이터를 입력변수로 받아서 신용등급을 나누는데 우수한 능력을 보여줄 수 있다. 본 논문에서는 신경망 모델을 이용해 개인의 신용등급을 객관적이고 일률적으로 평가해서 등급을 나누어주는 알고리즘을 제안하고자 한다.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2007.05a
• /
• pp.190-197
• /
• 2007

외환위기 이후 우리나라 금융기관은 상대적으로 위험성이 높은 기업대출보다, 높은 수익성을 가지는 가계 대출에 관심을 기울이게 되었다. 가계대출이 증가함에 따라 개인신용평가의 중요성이 부각되고, 이에 많은 신용평가시스템이 개발되어 왔다. 하지만 기존의 신용평가시스템은 대출 신청 당시의 데이터 및 과거의 데이터를 가지고 개인의 신용을 평가하기 때문에, 미래 상황에 대한 예측은 고려하지 못한다. 시스템 다이나믹스는 시간의 흐름에 따른 각 요인의 변화를 살펴봄으로써 미래 상황에 대한 예측이 가능한 분석 방법이다. 이에 본 연구에서는 시스템 다이나믹스 방법론을 활용하여 개인 신용 상태에 대한 미래의 동태적인 변화를 예측하여, 그 결과를 반영한 신용평가모델을 개발하고자 한다. 이를 위하여, 먼저 신용평점 영향을 주는 변수들을 선정하고, 이 변수들 간의 인과관계를 밝혀낸 후, 인과관계를 토대로 분석 모델을 구축한 뒤, 컴퓨터 시뮬레이션을 실행함으로써, 대출 희망자의 미래의 신용상태 변화 모양을 예측해 본다. 이러한 시뮬레이션 결과를 신용평가에 반영하게 되면, 금융기관의 신용 대출의 위험을 줄이는 데 기여할 것으로 기대된다.

• Korean Journal of Construction Engineering and Management
• /
• v.5 no.4 s.20
• /
• pp.97-106
• /
• 2004

Credit evaluation by domestic financial institutions on Korean construction companies has had many problems with its tools and criteria ignoring the industrial characteristics. This study develops the DCiF(discounted cash inflow) model as a solution and discusses its usage in construction financing. It also examines the significance of the DCiF indices through regressions and statistical comparison with the other credit evaluation estimates. The results show its clear significance and consistent fitness. Based on the empirical results, implications and methodology are provided for the effective use of the indices in credit evaluation on the construction companies.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.11-20
• /
• 2024

This study presents TabNet, a novel deep learning method, to enhance corporate credit rating accuracy amidst growing financial market uncertainties due to technological advancements. By analyzing data from major Korean stock markets, the research constructs a credit rating prediction model using TabNet. Comparing it with traditional machine learning, TabNet proves superior, achieving a Precision of 0.884 and an F1 score of 0.895. It notably reduces misclassification of high-risk companies as low-risk, emphasizing its potential as a vital tool for financial institutions in credit risk management and decision-making.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.237-247
• /
• 2005

Ubiquitous Sensor Network(USN) is the very core of a technology for the Ubiquitous environments. There is the weakness from various security attacks such that tapping of sensor informations, flowing of abnormal packets, data modification and Denial of Service(DoS) etc. And it's required counterplan with them. Especially it's restricted by the capacity of battery and computing. By reasons of theses. positively, USN security technology needs the lightweighted design for the low electric energy and the minimum computing. In this paper, we propose lightweight USN mutual authentication methology based on trust model to solve above problems. The proposed authentication model can minimize the measure of computing because it authenticates the sensor nodes based on trust information represented by subjective logic model. So it can economize battery consumption and resultingly increse the lifetime of sensor nodes.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.41-42
• /
• 2019

본 논문에서는 다양한 기계학습 모델을 이용한 신용 데이터 분석 기법에 대해 서술한다. 기계학습 모델은 크게 Canonical models, Committee machines, 그리고 Deep learning models로 분류된다. 이러한 다양한 기계학습 모델 중 일부 학습 모델을 기반으로 Benchmark dataset인 Credit Approval 데이터를 분석하고 성능을 평가한다. 성능 평가에는 k-fold evaluation method를 사용하며, k-fold evaluation 결과에 대한 평균 성능을 측정하기 위해 Accuracy, Precision, Recall, 그리고 F1-score가 사용되었다.

• Journal of Internet Computing and Services
• /
• v.7 no.1
• /
• pp.121-130
• /
• 2006

In next generation wireless networks, an application must be capable of rating service information in real-time and prior to initiation of the service it is necessary to check whether the end user's account provides coverage for the requested service. However, to provide prepaid services effectively, credit-control should have minimal latency. In an endeavor to support real-time credit-control for Mobile IPv6 (MIPv6), we design an implementation architecture model of credit-control authorization. The proposed integrated model combines a typical credit-control authorization procedure into the MIPv6 authentication procedure. We implement it on a single server for minimal latency. Thus, the server can perform credit-control authorization and MIPv6 authentication simultaneously. Implementation details are described as software blocks and units. In order to verify the feasibility of the proposed model. latency of credit-control authorization is measured according to various Extensible Authentication Protocol (EAP) authentication mechanisms. The performance results indicate that the proposed approach has considerably low latency compared with the existing separated models, in which credit-control authorization is separated from the MIPv6 authentication.

• Journal of Digital Convergence
• /
• v.18 no.4
• /
• pp.149-161
• /
• 2020

This paper aims to explore the question of whether the environment in Korea where credit card use is prevalent affects the intention to accept Fintech-based mobile payment. The institution that encourages the credit card use such as credit card receipt obligation may lead to the lock-in and build infrastructures to influence the acceptance of new payment acceptance. This paper investigates how the perceived of use, usefulness, accessibility and stability affect the intention to use mobile payment based on the Technology Acceptance Model(TAM) model with the mediator of lock-in and moderator of credit card receipt obligation. In the results, we found that the perceived usefulness, perceived ease of use and accessibility positively impact on the intention of mobile payment usages. It is also observed that the usefulness and accessibility of credit cards positively mediate to the intention of mobile payment use.