• 대한원격탐사학회지
• /
• 제20권3호
• /
• pp.189-196
• /
• 2004

This paper describes what an operational change detection tool requires and the software which was designed and developed according to the requirements. The top requirement for the application of the software to operational change detection was identified: minimization of false detections, missing detections and operational cost. In order to meet such a requirement, the software was designed with the concept that the ultimate decision and isolation of changes must be performed manually by visual interpretation and all automatic algorithms and/or visualization techniques must be defined as support functions. In addition, the modular structure of the proposed software enables the addition of a new support function with the minimum development cost and minimum change of the operational environment.

• 한국경영정보학회:학술대회논문집
• /
• 한국경영정보학회 2007년도 추계학술대회
• /
• pp.591-596
• /
• 2007

본 연구에서는 상황 추론의 기능을 추천 시스템에 접목하였다. 연구의 대상 영역은 음악 추천 분야인데, 본 연구에서 제안하는 시스템은 세 개의 모듈, 즉 Intention Module, Mood Module 그리고 Recommendation Module로 구성되어 있다. Intention Module은 사용자가 음악을 청취할 의향이 있는지 없는지를 외부 환경의 상황 데이터를 이용하여 추론한다. Mood Module은 사용자의 상황에 적합한 음악의 장르를 추론한다. 마지막으로 Recommendation Module은 사용자에게 선정된 장르의 음악을 추천한다.

• 한국컴퓨터정보학회논문지
• /
• 제25권2호
• /
• pp.213-219
• /
• 2020

본 연구는 스마트폰 과의존을 진단하고 예측하기 위하여 할 수 있는 분류분석 방법과 스마트폰 과의존 분류율에 영향을 미치는 중요변수를 규명하고자 시도되었다. 이를 위해 인공지능의 방법인 기계학습 분석 기법 중 의사결정트리, 랜덤포레스트, 서포트벡터머신의 분류율을 비교하였다. 자료는 한국정보화진흥원에서 제공한 '2018년 스마트폰 과의존 실태조사'에 응답한 25,465명의 데이터였고, R 통계패키지(ver. 3.6.2)를 사용하여 분석하였다. 분석한 결과, 3가지 분류분석 기법은 정분류율이 유사하게 나타났으며, 모델에 대한 과적합 문제가 발생되지 않았다. 3가지 분류분석 방법 중 서포트벡터머신의 분류율이 가장 높게 나타났고, 다음으로 의사결정트리 기법, 랜덤포레스트 기법 순이었다. 스마트폰 이용 유형 중 분류율에 영향을 미치는 상위 3개 변수는 생활서비스형, 정보검색형, 여가추구형이었다.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1395-1405
• /
• 2017

In this paper, we analyses heart beat data to identify subjects stress state (binary) using heart rate variability (HRV) features extracted from heart beat data of the subjects and implement supervised machine learning techniques to create the mental stress classifier. There are four steps need to be done: data acquisition, data processing (HRV analysis), features selection, and machine learning, before doing performance measurement. There are 56 features generated from the HRV Analysis module with several of them are selected (using own algorithm) after computing the Pearson Correlation Matrix (p-values). The results of the list of selected features compared with all features data are compared by its model error after training using several machine learning techniques: support vector machine, decision tree, and discriminant analysis. SVM model and decision tree model with using selected features shows close results compared to using all recording by only 1% difference. Meanwhile, the discriminant analysis differs about 5%. All the machine learning method used in this works have 90% maximum average accuracy.

• 정보기술응용연구
• /
• 제1권
• /
• pp.173-211
• /
• 1999

The task of classification permeates all walks of life, from business and economics to science and public policy. In this context, nonlinear techniques from artificial intelligence have often proven to be more effective than the methods of classical statistics. The objective of knowledge discovery and data mining is to support decision making through the effective use of information. The automated approach to knowledge discovery is especially useful when dealing with large data sets or complex relationships. For many applications, automated software may find subtle patterns which escape the notice of manual analysis, or whose complexity exceeds the cognitive capabilities of humans. This paper explores the utility of a collaborative learning approach involving integrated models in the preprocessing and postprocessing stages. For instance, a genetic algorithm effects feature-weight optimization in a preprocessing module. Moreover, an inductive tree, artificial neural network (ANN), and k-nearest neighbor (kNN) techniques serve as postprocessing modules. More specifically, the postprocessors act as second0order classifiers which determine the best first-order classifier on a case-by-case basis. In addition to the second-order models, a voting scheme is investigated as a simple, but efficient, postprocessing model. The first-order models consist of statistical and machine learning models such as logistic regression (logit), multivariate discriminant analysis (MDA), ANN, and kNN. The genetic algorithm, inductive decision tree, and voting scheme act as kernel modules for collaborative learning. These ideas are explored against the background of a practical application relating to financial fraud management which exemplifies a binary classification problem.

• 아태비즈니스연구
• /
• 제12권4호
• /
• pp.13-40
• /
• 2021

Purpose - The purpose of this study is to predict corporate corruption in emerging markets such as Brazil, Russia, India, and China (BRIC) using different machine learning techniques. Since corruption is a significant problem that can affect corporate performance, particularly in emerging markets, it is important to correctly identify whether a company engages in corrupt practices. Design/methodology/approach - In order to address the research question, we employ predictive analytic techniques (machine learning methods). Using the World Bank Enterprise Survey Data, this study evaluates various predictive models generated by seven supervised learning algorithms: k-Nearest Neighbour (k-NN), Naïve Bayes (NB), Decision Tree (DT), Decision Rules (DR), Logistic Regression (LR), Support Vector Machines (SVM), and Artificial Neural Network (ANN). Findings - We find that DT, DR, SVM and ANN create highly accurate models (over 90% of accuracy). Among various factors, firm age is the most significant, while several other determinants such as source of working capital, top manager experience, and the number of permanent full-time employees also contribute to company corruption. Research implications or Originality - This research successfully demonstrates how machine learning can be applied to predict corporate corruption and also identifies the major causes of corporate corruption.

• 한국정보시스템학회지:정보시스템연구
• /
• 제7권1호
• /
• pp.181-208
• /
• 1998

In many literatures of model management, various schemes for representing model base schema have proposed. Ultimately, the goal is to arrive at a set of mutually supportive and synergistic methodologies and tools for the modeling problem domain and model base design. This paper focus on how best to structure and represent conceptual model of problem domain and schema of model base. Semantic concepts and modeling constructs are valuable conceptual tools for understanding the structural relationships and constraints involved in an model management environment. To this end, we reviewed the model management literature, and analyzed the constructs of modeling tools of data model management graph-based approach. Although they have good tools but most of them are not enough for the representation of structural relationships and constraints. So we wanted more powerful tools which can represent diverse constructs in a decision support modeling and model base schema design. For the design of a model base, we developed object modeling framework which uses Object Modeling Techniques (OMT). In Object Modeling Framework, model base schema are classified into conceptual schema, logical schema, and physical schema. The conceptual schema represents the user's view of problem domain, and the logical schema represents a model formatted by a particular modeling language. The schema design, this paper proposes an extension of Object Model to overcome some of the limitations exhibited by the OMT. The proposed tool, Extended Object Model(EOM) have diverse constructs for the representation of decision support problem domain and conceptual model base schema.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.425-428
• /
• 2005

Healthcare is a research field suitable for applying the recent ubiquitous techniques. As a test system, we developed a kind of CDSS (Clinical Decision Support System) running in ubiquitous environment. called as 'uCDSS'. The uCDSS is a core system of the ubiquitous healthcare and is composed of some 'uMLMs(Ubiquitous Medical Logic Modules)'. The uMLMs based on the class in C# programming language could be reused in development of CDSS, or another EHR system running in .NET environment. As a test system, we developed the DM(Diabetes Mellitus knowledge system using ASP.NET. This system shows the potential of C# class-based uMLMs and the extensibility to any .NET development project.

• Journal of Preventive Medicine and Public Health
• /
• 제50권4호
• /
• pp.217-227
• /
• 2017

In terms of years of life lost to premature mortality, cancer imposes the highest burden in Korea. In order to reduce the burden of cancer, the Korean government has implemented cancer control programs aiming to reduce cancer incidence, to increase survival rates, and to decrease cancer mortality. However, these programs may paradoxically increase the cost burden. For examples, a cancer screening program for early detection could bring about over-diagnosis and over-treatment, and supplying medical services in a paternalistic manner could lead to defensive medicine or futile care. As a practical measure to reduce the cost burden of cancer, appropriate cancer care should be established. Ensuring appropriateness requires patient-doctor communication to ensure that utility values are shared and that autonomous decisions are made regarding medical services. Thus, strategies for reducing the cost burden of cancer through ensuring appropriate patient-centered care include introducing value-based medicine, conducting cost-utility studies, and developing patient decision aids.

• 산업공학
• /
• 제5권2호
• /
• pp.3-17
• /
• 1992

In this study, an integrated economic analysis model to analyze the new telecommunication services is developed. This model considers both the technological and managerial aspests altogether with respect to the profit and public benefit criteria. To encounter the various dynamically changing environments and evaluation criteria, multiple criteria decision making (MCDM)techniques are employed. The model consists of three stages; The first stage surveys related formal or informal data, generates analysis alternatives, and performs acceptabillty test in view of marketing. The second stage generates executive alternatives for each acceptable analysis alternative and checks the executionability in view of telecommunication technologies. The third stage performs the final integrated economic analysis including the profitability analysis. This study offers a basis for the future development of decision support system or expert system on the economic analysis of the new telecommunication services.