• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.6
• /
• pp.57-69
• /
• 2001

Expert system is one of AI area. It simulates the human's way of thinking to give solutions of problem in many applications. Most expert system consists of many components such as inference engine, knowledge base, and so on. Especially the performance of expert system depend on the control of efficiency of inference engine. Inference engine has to get features; first, if possible to minimize restrictions when it constructed the knowledge base. second, it has to serve various kinds of inferencing methods. In this paper we propose knowledge scheme for representing domain knowledge in ease, knowledge implementation technique for inferencing, and integrated knowledge-base engine with blackboard and inference engine. And we describe a expert system prototype that implemented in this paper using proposed methods, it perform diagnose about heavy industrial device. The fault diagnosis system prototype has been studied in this paper will be practical foundation in the research area of knowledge based system.

• Journal of the Korea Society for Simulation
• /
• v.26 no.2
• /
• pp.59-65
• /
• 2017

Along with the development of M&S, modeling research utilizing AI technology is attracting attention because of the fact that the needs of fields including human decision making such as defense M&S are increased. Obviously AI is a way to solve complex problems. However, AI did not consider logical time such as input time and processing time required by M&S. Therefore, in this paper we proposed a "time-based expert system" which redesigned the representative AI technology rule-based expert system. It consists of a rule structure "IF-THEN-AFTER" and an inference engine, takes logical time into consideration. We also tried logical analysis using a simple example. As a result of the analysis, the proposal Time-based Expert System proved that the result changes according to the input time point and inference time.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.65-76
• /
• 2022

Recently, not only traditional statistical techniques but also machine learning algorithms have been used to make more accurate bankruptcy predictions. But the insolvency rate of companies dealing with financial institutions is very low, resulting in a data imbalance problem. In particular, since data imbalance negatively affects the performance of artificial intelligence models, it is necessary to first perform the data imbalance process. In additional, as artificial intelligence algorithms are advanced for precise decision-making, regulatory pressure related to securing transparency of Artificial Intelligence models is gradually increasing, such as mandating the installation of explanation functions for Artificial Intelligence models. Therefore, this study aims to present guidelines for eXplainable Artificial Intelligence-based corporate bankruptcy prediction methodology applying SMOTE techniques and LIME algorithms to solve a data imbalance problem and model transparency problem in predicting corporate bankruptcy. The implications of this study are as follows. First, it was confirmed that SMOTE can effectively solve the data imbalance issue, a problem that can be easily overlooked in predicting corporate bankruptcy. Second, through the LIME algorithm, the basis for predicting bankruptcy of the machine learning model was visualized, and derive improvement priorities of financial variables that increase the possibility of bankruptcy of companies. Third, the scope of application of the algorithm in future research was expanded by confirming the possibility of using SMOTE and LIME through case application.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• pp.41-50
• /
• 2024

Korea is facing a significant problem with historically low fertility rates, which is becoming a major social issue affecting the economy, labor force, and national security. This study analyzes the factors contributing to the regional gap in fertility rates and derives policy implications. The government and local authorities are implementing a range of policies to address the issue of low fertility. To establish an effective strategy, it is essential to identify the primary factors that contribute to regional disparities. This study identifies these factors and explores policy implications through machine learning and explainable artificial intelligence. The study also examines the influence of media and public opinion on childbirth in Korea by incorporating news and online community sentiment, as well as sentiment fear indices, as independent variables. To establish the relationship between regional fertility rates and factors, the study employs four machine learning models: multiple linear regression, XGBoost, Random Forest, and Support Vector Regression. Support Vector Regression, XGBoost, and Random Forest significantly outperform linear regression, highlighting the importance of machine learning models in explaining non-linear relationships with numerous variables. A factor analysis using SHAP is then conducted. The unemployment rate, Regional Gross Domestic Product per Capita, Women's Participation in Economic Activities, Number of Crimes Committed, Average Age of First Marriage, and Private Education Expenses significantly impact regional fertility rates. However, the degree of impact of the factors affecting fertility may vary by region, suggesting the need for policies tailored to the characteristics of each region, not just an overall ranking of factors.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1305-1333
• /
• 2020

Deep learning has recently achieved remarkable results in the field of medical imaging. However, as a deep learning network becomes deeper to improve its performance, it becomes more difficult to interpret the processes within. This can especially be a critical problem in medical fields where diagnostic decisions are directly related to a patient's survival. In order to solve this, explainable artificial intelligence techniques are being widely studied, and an attention mechanism was developed as part of this approach. In this paper, attention techniques are divided into two types: post hoc attention, which aims to analyze a network that has already been trained, and trainable attention, which further improves network performance. Detailed comparisons of each method, examples of applications in medical imaging, and future perspectives will be covered.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.141-160
• /
• 2019

Agile methodologies in software development, including the development of artificial intelligence software, have been widespread over the past several years. In spite of the popularity of agile methodologies in practice, there is a lack of empirical evidence to identify determinants of success of software projects in which agile methods are used. To understand the role of clients in software project where agile methods are used, we examine the effect of client-side factors, including lack of user involvement, unrealistic client expectations, and constant changes of requirements on project success from practitioners' perspective. Survey methods are used in this study. Data were collected by means of online survey to IT professionals who have experience with software development methodologies, and ordered logit regression is used to analyze the survey data. Results of our study imply the following managerial findings. First, user involvement is critical to project success to take advantage of agile methods. Second, it is interesting that, with an agile method, constant changes of client's requirements is not a negative factor but a positive factor of project success. Third, unrealistic client expectations do negatively affect project success even with agile methods.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.6
• /
• pp.642-648
• /
• 2019

Vessels sail according to the COLREG to prevent a collision. However, it is difficult to apply COLREG under special situation as heavy traffic, at this time personal skills of the operator are required. In this case, traffic control is required through the maritime traffic monitoring system. Therefore, maritime traffic management is globally implemented by VTS. In this system, VTS of icer uses the VTS system to assess risks and recommends possible safety operation to vessels with radio systems. This study considers that the risk analysis method with AI (Artificial Intelligence) technology from the operator's aspect. In addition, the research explains the Maritime Traffic Safety Monitoring System, Including AR (Augmented Reality) technology to increase vessel control efficiency. This system is able to predict hazards and risk priorities, and it leads to sequential elimination of dangerous situations. Especially, the hazard situations can be analyzed from operator's perspective of each vessel instead of the VTS officer's aspect, which is more practical than the conventional method. Furthermore, the result of analysis enables to comprehend quantitative hazardous areas and support recommended routes to avoid a collision. As a result, I firmly believe that the system will support to prevent a collision in complex traffic waters. In particular, it could be adopted as a collision prevention system for Maritime Autonomous Surface Ship, which occupies a significant proportion in Maritime 4th industrial revolution.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.397-406
• /
• 2000

대부분의 국방정보시스템의 소프트웨어는 높은 가용성, 신뢰성, 신속성, 정확성 등을 요구하는 대규모이면서 복잡한 실시간 시스템이다. 이러한 국방정보시스템의 소프트웨어 개발사업에 있어서 저비용 고효율의 미개국방경영 건설을 위하고 강한 전투력을 육성하기 위해서는 국방정보시스템의 효율적인 소프트웨어 개발사법이 요구된다. 따라서, 국방정보시스템의 소프트웨어 사업관리자가 개발사업을 관리하고 감독하는데 있어서 개발자와 사용자간의 조정 및 통제 기능을 수행하고 해당 국방정보시스템의 특성을 파악하여 성공적인 사업수행을 할 수 있도록 기술적인 사업관리 측면에서 구체적이고 상세화된 방안/지침을 제공하기 위한 전문가시스템의 지식베이스 도메인 지식개발에 관한 연구이다. 기존의 국방정보시스템의 사업관리자가 경험을 동해 축적해 온 기술, 정책, 아이디어, 노하우 등에 대한 지식을 습득하고 사업 관련자료에서 제시한 소프트웨어 생명주기 단계별 방안이나 지침 등을 바탕으로 하여 식별된 사실이나 내용을 지식베이스로 구축하여 국방정보시스템의 사업관리자가 필요로 할 때 설명모듈을 거쳐 임무 및 세부활동사항을 게시하여 줌으로써 사업관리 경험이 부족하거나 사업관리자가 교체되었을 때 사업관리자들이 업무를 지속적으로 연계시켜 임무수행이 가능하도록 기초/기반 여건을 제공하고자 한다. 본 논문은 국방정보시스템의 소프트웨어 개발사업에서 소프트웨어 생명주기 단계별 사업관리자의 임무 및 세부활동사항 지원용 전문가시스템을 개발할 때 이용할 수 있도록 도메인 지식을 개발하는 것이며 논문의 결과를 활용시 기대되는 효과는 본문을 참고 바란다.의 장점을 취합하여 설계되었다. 본 시스템은 기존의 UN/EDIFACT표준을 사용하고 있는 EDI환경과 기존 VAN 방식의 EDI 중계 시스템과 연동되며, 향후 관세청의 XML/EDI 표준 시행을 미리 대비하는 선도연구로서 자리매김이 된다. 본 연구에서는 개발된 XML/EDI 통관시스템은 향후, 서비스의 최대 걸림돌이 되어왔던 값비싼 EDI 사용료의 부담에서 벗어날 수 있게 할 것이며, 저렴한 EDI구축/운영 비용으로 전자문서교환의 활성화와 XML이 인터넷 기반의 문서유통 표준으로 자리매김할 수 있는 중요한 계기가 될 것이다.재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is

• Journal of Korean Society of Archives and Records Management
• /
• v.21 no.4
• /
• pp.1-18
• /
• 2021

Today, record management has become more important in management as records generated from administrative work and data production have increased significantly, and the development of information and communication technology, the working environment, and the size and various functions of the government have expanded. It is explained as an example in connection with the concept of public records with the characteristics of big data and big data characteristics. Social, Technological, Economical, Environmental and Political (STEEP) analysis was conducted to examine such areas according to the big data generation environment. The appropriateness and necessity of applying big data technology in the field of public record management were identified, and the top priority applicable framework for public record management work was schematized, and business implications were presented. First, a new organization, additional research, and attempts are needed to apply big data analysis technology to public record management procedures and standards and to record management experts. Second, it is necessary to train record management specialists with "big data analysis qualifications" related to integrated thinking so that unstructured and hidden patterns can be found in a large amount of data. Third, after self-learning by combining big data technology and artificial intelligence in the field of public records, the context should be analyzed, and the social phenomena and environment of public institutions should be analyzed and predicted.