• ETRI Journal
• /
• 제39권5호
• /
• pp.621-631
• /
• 2017

Abnormal samples are usually difficult to obtain in production systems, resulting in imbalanced training sample sets. Namely, the number of positive samples is far less than the number of negative samples. Traditional Support Vector Machine (SVM)-based anomaly detection algorithms perform poorly for highly imbalanced datasets: the learned classification hyperplane skews toward the positive samples, resulting in a high false-negative rate. This article proposes a new imbalanced SVM (termed ImSVM)-based anomaly detection algorithm, which assigns a different weight for each positive support vector in the decision function. ImSVM adjusts the learned classification hyperplane to make the decision function achieve a maximum GMean measure value on the dataset. The above problem is converted into an unconstrained optimization problem to search the optimal weight vector. Experiments are carried out on both Cloud datasets and Knowledge Discovery and Data Mining datasets to evaluate ImSVM. Highly imbalanced training sample sets are constructed. The experimental results show that ImSVM outperforms over-sampling techniques and several existing imbalanced SVM-based techniques.

• Journal of information and communication convergence engineering
• /
• 제9권4호
• /
• pp.358-362
• /
• 2011

The National Emergency Management Agency of South Korea has established a Disaster Victims Psychology Support Center. The Disaster Victims Psychology Support Center can enable victims who got psychological damage from disasters to return to their daily lives through healing activity, field visits and advice of experts. The previous Psychology Support Center System managed the information of disaster victims through an independent database. However, this paper proposes a system that is developed to identify medical institutions and mental health centers within a distance of radius, based on the potential Hot-Spot areas of disaster victims using the GIS Systems. The proposed system can efficiently support selection of appropriate institutions for disaster victims using their location and age, classification of damage, and damaged parts of the body. Also, this spatial analysis can assist to decide on a policy based on the location of disaster victims and the extent of damage. Therefore, this paper can provide the required information to support decision making based on the concentrated areas for disaster victims.

• 산업경영시스템학회지
• /
• 제17권32호
• /
• pp.297-308
• /
• 1994

In the information system, there are many fields that used by decision making support system. Nowadays, the reasons that the need of the decision making system in audit is increased, are as follows. \circled1 The increased of competitiveness in audit environment \circled2 The rapid replenishment of computer hardware and computer system in corporations. The purposes of this study are as follows. \circled1 The connection of Internal management assess results and practical examination. \circled2 In the making of audit opinion, the establish of non-measure and evaluate logic. \circled3 The suggestion of knowledge base structure about the audit task. \circled4 The development of prototype system for the accounting audit expert system. The expected usefulness of accounting audit expert system development are as follows. \circled1 Audit time may be saved \circled2 The consistence of opinion will be increased \circled3 The elevation of audit technique \circled4 The decreased of audit risk \circled5 In the decision making rationlization of accounting information users, it will be proved as usefulness.

• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 2005년도 추계학술대회 발표 논문집
• /
• pp.326-333
• /
• 2005

The purpose of this paper is to provide a decision support method to a rational buyer, who wants to pay the least price for the product with the highest quality and service. We suggest a minimum efficiency game model and DEA game model to valuate many vendors whose qualifies of outputs are measured by percentage. Our results gave a decision maker (buyer) the upper bound and lower bound of the true efficiency score of a decision making unit (vendor) with respect to the benchmark (target) set by the buyer. As a result, a buyer can choose the best vendor in terms of his/her preference.

• 한국정보시스템학회지:정보시스템연구
• /
• 제21권4호
• /
• pp.109-132
• /
• 2012

Social Network Analysis is an increasingly important part of a broader 'toolbox' of evaluation methods available to R&D policymakers to support decision-making. The aim of this research is to be an accessible, 'beginner's guide' to social network theory and application in the area of mobile telecommunication research and development (R&D) decision-making. This research suggests the methodology of investigation into new technology, and the methodology suggested by this research is believed to be a meaningful first step toward the establishment of the information analysis structure, which is in desperate need.

• Nuclear Engineering and Technology
• /
• 제53권1호
• /
• pp.314-321
• /
• 2021

As Indonesia is rich in natural resources, nuclear power remains a low priority among energy alternatives. However, Indonesia needs to introduce nuclear power to improve the atmospheric environment and to support sustainable economic growth. This study conducted a two-stage survey of logit-probit and analytic hierarchy process to analyze the perception of Indonesian energy policymakers regarding the introduction of nuclear power, the potential for change, and key decision factors. The analysis confirms that the perception of nuclear power is positive and that the willingness to expand nuclear power can improve if negative conditions, such as underdeveloped technology level, foreign aid and assistance, and safety issues are addressed. In addition, it is confirmed that the policy makers consider political/social and environmental factors to be more important for decision-making. The results of this study can give inplications and be used as a key reference for Indonesia's nuclear power policy

• 한국지능시스템학회논문지
• /
• 제17권6호
• /
• pp.799-803
• /
• 2007

본 논문에서는 FSVM(Putty Support Vector Machine)의 퍼지소속함수를 새롭게 제안한다. SVM의 완화변수(slack-variable)에 퍼지소속함수를 결합하는 FSVM은 주어진 데이터베이스의 특성이 반영되어 안정적으로 분류성능을 향상시킬 수 있는 퍼지소속 함수를 필요로 한다. 시계열 자료의 패턴분류 성능을 비교하기 위하여 SVM, FSVM(1), 그리고 제안하는 FSVM(2) 등의 분류모델들을 비교 실험하였다. 사용한 데이터베이스는 한국금융시장의 시계열 경제지표 지수들이다.

• 동의생리병리학회지
• /
• 제28권1호
• /
• pp.113-121
• /
• 2014

With the development of information technology, knowledge information-oriented and information systems are being rapidly paced. In addition, doctor's needs of the system that assist decision making is gradually increasing. Because the complex process of decision-making should be a lot. We propose a web based system for supporting medical treatment based on Korean medicine ontology. There are three kinds of processes. First, a pattern is decided for patient' symptoms, a formula for the pattern is selected and medicinal materials constituting the formula is added or removed. Second, a formula is decided for patient' symptoms, medicinal materials constituting the formula is added or removed. Third, a Treat method is decided for patient' symptoms, medicinal materials constituting the formula is added or removed. We have designed and implemented the clinical decision support system that supports flexible processes and necessary information and functions. The system shows the appropriate form of ontology knowledge as interrelated and provide analysis and processing, does not show simply search. The system is one of the systems utilizing ontology and a web based system that can be used in anywhere. Therefore, This system Will be useful as for doctors to make decision.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권2호
• /
• pp.287-306
• /
• 2020

Purpose Youth unemployment is a social problem that continues to emerge in Korea. In this study, we create a model that predicts the employment of college graduates using decision tree, random forest and artificial neural network among machine learning techniques and compare the performance between each model through prediction results. Design/methodology/approach In this study, the data processing was performed, including the acquisition of the college graduates' vocational path survey data first, then the selection of independent variables and setting up dependent variables. We use R to create decision tree, random forest, and artificial neural network models and predicted whether college graduates were employed through each model. And at the end, the performance of each model was compared and evaluated. Findings The results showed that the random forest model had the highest performance, and the artificial neural network model had a narrow difference in performance than the decision tree model. In the decision-making tree model, key nodes were selected as to whether they receive economic support from their families, major affiliates, the route of obtaining information for jobs at universities, the importance of working income when choosing jobs and the location of graduation universities. Identifying the importance of variables in the random forest model, whether they receive economic support from their families as important variables, majors, the route to obtaining job information, the degree of irritating feelings for a month, and the location of the graduating university were selected.

• ETRI Journal
• /
• 제29권4호
• /
• pp.507-515
• /
• 2007

Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.