• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.158-161
• /
• 2003

A cascade structured neural network called Sigma-Pi$_{t}$ Cascaded Hybrid Neural Network ($\sigma$$\pi$$_{t}$-CHNN) is Proposed. It is an extended version of the Sigma-Pi Cascaded extended Hybrid Neural Network ($\sigma$$\pi$-CHNN), where the classical multiplicative neuron ($\pi$-neuron) is replaced by the translated multiplicative ($\pi$$_{t}$-neuron) model. The learning algorithm of $\sigma$$\pi$$_{t}$-CHNN is composed of an evolutionary programming method, responsible for determining the network architecture, and of a Levenberg-Marquadt algorithm, responsible for tuning the weights of the network. The $\sigma$$\pi$$_{t}$-CHNN is evaluated in 2 pattern classification problems: the 2 spirals and the sonar problems. In the 2 spirals problem, $\sigma$$\pi$$_{t}$-CHNN can generate neural networks with 10％ less hidden neurons than that in previous neural models. In the sonar problem, $\sigma$$\pi$$_{t}$-CHNN can find the optimal solution for the problem i.e., a network with no hidden neurons. These results confirm the expanded information processing capabilities of $\sigma$$\pi$$_{t}$-CHNN, when compared to previous neural network models. network models.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.131-145
• /
• 2014

This study is an empirical analysis on the relationship between social presence and online community users' continuance intention. Based on Bhattacherjee(2001)'s expectation-confirmation model (ECM) of IT continuance model, we test the influence of social presence on one's intention to continue using online communities. This study sampled 132 online community users. Research hypotheses are tested using the structural equation modelling(SEM) approach. The results of this study demonstrate that user satisfaction is influenced by perceived usefulness and perceived enjoyment. But, the confirmation of expectation did not affect user satisfaction. And, social presence has direct effects on perceived usefulness and perceived enjoyment. Further, social presence has a positive effect on users' continuance intention through mediating effect of perceived usefulness. This study suggests that perceived usefulness should be taken into account when carrying out the operating strategy of online communities.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.895-901
• /
• 2004

This paper describes a two-phase intelligent method for filtering spam mail based on textual information and hyperlinks. Scince the body of spam mail has little text information, it provides insufficient hints to distinguish spam mails from legitimate mails. To resolve this problem, we follows hyperlinks contained in the email body, fetches contents of a remote webpage, and extracts hints (i.e., features) from original email body and fetched webpages. We divided hints into two kinds of information: definite information (sender`s information and definite spam keyword lists) and less definite textual information (words or phrases, and particular features of email). In filtering spam mails, definite information is used first, and then less definite textual information is applied. In our experiment, the method of fetching web pages achieved an improvement of F-measure by 9.4% over the method of using on original email header and body only.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.97-105
• /
• 2011

This paper proposes a new "Live Book Service" that is combined the analog contents such as paper books and digital contents with various digital multimedia elements, and this service can project the additional digital multimedia contents on the analog paper. Also, we developed a monolithic stand type system which is composed of camera and pico projector, so that it can demonstrate the proposed contents. We also devised the low computational cost algorithm in bare-hands recognition which can be used as the interface between the system and users. In addition, to recognize the bare-hands which can be used as the interface between the digital and users, we make the low cost algorithm. Therefore this can be the interaction between the system and users. As a result, our proposed system can be used as a useful tool for various e-book or u-learning fields that requires high efficiency and much immersion.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.105-108
• /
• 2007

In this paper, we have developed a UPnP-OSGi Bundle for digital convergence based on UPnP middleware. UPnP-OSGi bundle is demanded sustaining realtime monitering system based on UPnP middleware that is possible multimedia ability of a piece with a multiplicity of service and joint user data , service lifecycle , management division service for home network system offered convergence service. This bundle is possible a multiplicity of control and monitering service segmentation so develop a multiplicity of service is easy. and provide zero-configuration system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.1 no.1
• /
• pp.9-25
• /
• 1991

This tutorial paper has been written for biologists, physicians or beginners in fuzzy sets theory and applications. This field is introduced in the framework of medical diagnosis problems. The paper describes and illustrates with practical examples, a general methodology of special interest in the processing of borderline cases, that allows a graded assignment of diagnoses to patients. A pattern of medical knowledge consists of a tableau with linguistic entries or of fuzzy propositions. Relationships between symptoms and diagnoses are interpreted as labels of fuzzy sets. It is shown how possibility measures (soft matching) can be used and combined to derive diagnoses after measurements on collected data. The concepts and methods are illustrated in a biomedical application on inflammatory protein variations. In the case of poor diagnostic classifications, it is introduced appropriate ponderations, acting on the characterizations of proteins, in order to decrease their relative influence. As a consequence, when pattern matching is achieved, the final ranking of inflammatory syndromes assigned to a given patient might change to better fit the actual classification. Defuzzification of results (i.e. diagnostic groups assigned to patients) is performed as a non fuzzy sets partition issued from a "separating power", and not as the center of gravity method commonly employed in fuzzy control. It is then introduced a model of fuzzy connectionist expert system, in which an artificial neural network is designed to build the knowledge base of an expert system, from training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the connections: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through MIN-MAX fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feed forward network is described and illustrated in the same biomedical domain as in the first part.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.52-56
• /
• 2004

The Information of classification and estimate about KOSPI200 index`s up and down in the stock market becomes an important standard of decision-making in designing portofolio in futures and option market. Because the coming trend of time series patterns, an economic indicator, is very subordinate to the most recent economic pattern, it is necessary to study the recent patterns most preferentially. This paper compares classification and estimated performance of SVM(Support Vector Machine) and Fuzzy SVM model that are getting into the spotlight in time series analyses, neural net models and various fields. Specially, it proves that Fuzzy SVM is superior by presenting the most suitable dimension to fuzzy membership function that has time series attribute in accordance with learning Data Base.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.445-445
• /
• 2018

기후변화에 따른 환경오염은 21세기 인류에게 가장 심각한 문제 중의 하나로 대두되고 있다. 환경적인 측면에서 하천오염은 경제적으로 많은 문제를 발생시키고 있다. 이러한 하천오염 문제를 해결하기 위해서는 오염물질의 농도 측적 및 데이터 축적이 필수적이라 할 수 있다. 그러나 일반적으로 오염물질 부하량에 대한 직접적인 측정은 비용 측면에서 쉽지 않은 것이 사실이다. 또한 실시간으로 BOD, COD, TN, TP 등의 자료를 이용하여 예측하는 것에는 자료의 부족성으로 인해 한계가 있다. 본 연구에서는 구글의 딥러닝 오픈소스 라이브러리인 텐서플로우를 활용하여 기계학습을 통한 하천오염 예측을 목적으로 하고 있다. 기계학습을 위하여 텐서플로우를 활용하여 RNN, LSTM 인공신경망 모형을 구축하였다. 하천오염의 학습과 예측을 위해 결과치 분석을 위한 자료로는 금강 유역에 위치한 옥천 관측소 충청북도 옥천군 이원면 이원대교에 위치한 $36^{\circ}14'31.0''N$ $127^{\circ}40'02.6''E$의 관측소에서 BOD, COD, DO, 부유물질의 자료를 사용하였다. 모형의 학습을 위해서 입력자료는 수위, 유량, 평균기온, 평균풍속 자료를 2004년 ~ 2017년까지의 14년간의 자료를 사용하였다. 연구를 위해 BOD, COD, DO 부유물질 자료는 물환경정보시스템(http://water.nier.go.kr/)의 자료를 활용하고 수위, 유량등의 자료는 국가수자원관리종합정보시스템 (http://www.wamis.go.kr/)의 자료를 사용하였다. 그러나 수온, 수위, 풍속등의 자료는 일 자료가 있는가 반면 BOD, COD, TN, TP등의 자료는 일 자료가 있지 않아 이를 원활히 활용할 수 있도록 예측을 위한 결과치의 선형보간법을 통해 일 자료를 획득한 후 연구를 하였다. RNN, LSTM의 분석 시 학습속도, 반복시행횟수 sequence length의 길이 등의 값을 조절 하면서 결과치를 분석하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.63-63
• /
• 2022

기상 예보자료는 발생 가능한 재난의 예방 및 대비 차원에서 매우 중요한 자료로 활용되고 있다. 우리나라 기상청에서는 동네예보를 통해 5km 공간해상도의 1시간 간격 초단기예보와, 6시간 간격 정량강우예보(Quantitative Precipitation Forecast, QPF)의 단기예보 정보를 제공하고 있다. 그러나 이와 같은 예보자료는 강우량의 시·공간변화가 큰 집중호우와 같은 기상자료를 활용한 수문학적인 해석에는 한계가 있다. 예보자료를 수문학에 활용하기 위한 시·공간적 해상도 개선뿐만 아니라 방대한 기상 및 기후 자료의 예측성능을 개선하기 위한 다양한 연구가 진행되고 있다. 본 연구에서는 기상청이 제공하는 지역 앙상블 예측 시스템(Local ENsemble prediction System, LENS)와 종관기상관측시스템(ASOS) 및 방재기상관측시스템(AWS) 관측 데이터 및 동네예보에 기계학습 방법을 적용하여 수문학적 정량적 강수량 예측(Hydrological Quantitative Precipitation Forecast, HQPF) 정보를 생산하였다. 전처리 과정을 통해 모든 데이터의 시간해상도와 공간해상도를 동일한 해상도로 변환하였으며, 예측 변수의 인자 분석을 통해 기계학습의 예측 변수를 도출하였다. 기계학습 방법으로는 처리속도와 확장성을 고려하여 XGBoost(eXtreme Gradient Boosting) 방식을 적용하였으며, 집중호우에서의 예측정확도를 높이기 위해 확률매칭(PM) 방식을 적용하였다. 생산된 HQPF의 성능을 평가하기 위해 2020년에 발생한 14건의 호우 사상을 대상으로 태풍형과 비태풍형으로 구분하여 검증을 수행하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.4
• /
• pp.428-436
• /
• 2020

The purpose of this study is to analyze the needs for developing a curriculum for strengthening the long-term care service expertise and job competency. Specifically, the researchers analyzed previous studies on national long-term care services and national policy data, and conducted focus group interviews with 14 experts from related agencies. Activity theory was applied as a framework for analysis and a questionnaire about the importance and difficulty of subjects from 25 long-term service employees was administered for validating the results of the qualitative data analysis. The upper part of the subject-goal-tool of the activity system was considered the main area of action, and the following rule-community-division was divided into contextual parts for action, and the implications for demand analysis and future operation of the online curriculum are summarized. In total, six courses were required for development. These courses could be applied to as a learner-centered flip learning for long-term care service workers and various educational methods of collective education and supplementary education have been proposed. Based on the study results, implications in the educational field for effective management of courses were suggested at the end of the study.