• 응용통계연구
• /
• 제5권2호
• /
• pp.193-209
• /
• 1992

정상조건에서 수명이 상당히 긴 두 개의 부품으로 구성된 직렬형 시스템의 생명검사(Life Test)를 현실적으로 수행하기 위하여 제안된 단계적 충격생명검사에 관하여 고찰하였다. 모형화 단계에서 우리는 특별히 시스템내에서 작동하는 두 부품의 수명을 나타내는 확률변수가 Block과 Basu(1974)에 의해서 제안된 이변량 지수분포를 따르는 경우를 논의하여, 이에 상응하는 충격누적에 관련된 기존모형을 변형 제안하였고, 직렬형 시스템내의 부품간 수명의 종속관계를 포함하는 정보와 부품의 독자적인 생명검사로부터 얻는 정보를 통합하는 모형을 제안하여 시스템내에서 갖는 부품의 분포에 관하여 논의하였다. 한편 자료분석 단계에서는 기본적으로 최대우도 추정법을 초기값의 설정방법을 중심으로 토의하고 모수의 근사 분산, 공분산의 구조를 이용하여 단순검사의 최적시점을 설정하는 방안을 제시하였다.

• 대한한의학회지
• /
• 제39권2호
• /
• pp.1-12
• /
• 2018

Objectives: The objective of this study is to develop a new animal model with Kidney-hypofunction for Sasang Constitutional Medicine, especially for partial Soyangin(one of four constitution which has good digestive function and poor renal function) by Unilateral Ureteral Obstruction, and to estimate the factor related to obesity, dyslipidemia, and metabolic syndrome. Methods: The C57BL/6J mice were divided into 3 groups : normal group, high fat diet(HFD) control group, and HFD group with Unilateral Ureteral Obstruction(UUO). Then, the HFD control group and the experimental group were fed with high fat diet for 6 weeks. Food intake and body weight were measured at regular time by week. After the final experiment, blood was gathered for bloodchemical examination and organs(liver, fatty tissue) were remoed, weighted, and mRNA was analyzed with real-time PCR. Results: The weight growth rate with High fat diet went down by 8.35% in experimental group and had similar FER with the normal group, while HFD control group had higher weight growth rate and FER than any other groups. Also The experimental group had lower triglyceride and LDL cholesterol rate and higher glucose rate in serum. and in mRNA expression, GLUT-9, the protein related to excretion of uric acid and metabolic syndrome, expressed lower rate than that of HFD control group. and IL-6, a kind of cytokine related to obesity and metabolic syndrome, expressed more than HFD control group. Conclusions: It was found that Kidney-hypofunction animal-experimental model is susceptible to metabolic syndrome.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1698-1711
• /
• 2011

Knowledge is often represented as a set of rules or a semantic network in intelligent systems. Recently, ontology has been widely used to represent semantic knowledge, because it organizes thesaurus and hierarchal information between concepts in a particular domain. However, it is not easy to collect semantic relationships among concepts. Much time and expense are incurred in ontology construction. Collective intelligence can be a good alternative approach to solve these problems. In this paper, we propose a collective intelligence approach of Games With A Purpose (GWAP) to collect various semantic resources, such as words and word-senses. We detail how to construct the semantic information model or ontology from the collected semantic resources, constructing a system named FunWords. FunWords is a Korean lexical-based semantic resource collection tool. Experiments demonstrated the resources were grouped as common nouns, abstract nouns, adjective and neologism. Finally, we analyzed their characteristics, acquiring the semantic relationships noted above. Common nouns, with structural semantic relationships, such as hypernym and hyponym, are highlighted. Abstract nouns, with descriptive and characteristic semantic relationships, such as synonym and antonym are underlined. Adjectives, with such semantic relationships, as description and status, illustration - for example, color and sound - are expressed more. Last, neologism, with the semantic relationships, such as description and characteristics, are emphasized. Weighting the semantic relationships with these characteristics can help reduce time and cost, because it need not consider unnecessary or slightly related factors. This can improve the expressive power, such as readability, concentrating on the weighted characteristics. Our proposal to collect semantic resources from the collective intelligence approach of GWAP (our FunWords) and to weight their semantic relationship can help construct the semantic information model or ontology would be a more effective and expressive alternative.

• 천문학회보
• /
• 제44권1호
• /
• pp.52.3-52.3
• /
• 2019

We investigate a relative contribution from short to long-term flaring rate to predicting M and X-class flare probabilities. In this study, we consider magnetic parameters summarizing distribution and non-potentiality by Solar Dynamics Observatory/Helioseimic and Magnetic Imager and flare list by Geostationary Operational Environmental Satellites. A short-term rate is the number of major flares that occurred in an given active region (AR) within one day before the prediction time. A mid-term rate is a mean flaring rate from the AR appearance day to one day before the prediction time. A long-term rate is a rate determined from a relationship between magnetic parameter values of ARs and their flaring rates from 2010 May to 2015 April. In our model, the predicted rate is given by the combination of weighted three rates satisfying that their sum of the weights is 1. We calculate Brier skill scores (BSSs) for investigating weights of three terms giving the best prediction performance using ARs from 2015 April to 2018 April. The BSS (0.22) of the model with only long-term is higher than that with only short-term or mid-term. When short or mid-term are considered additionally, the BSSs are improved. Our model has the best performance (BSS = 0.29) when all three terms are considered, and their relative contribution from short to long-term rate are 19%, 23%, and 58%, respectively. This model seems to be more effective when predicting active solar ARs having several major flares.

• 전자공학회논문지S
• /
• 제35S권8호
• /
• pp.96-105
• /
• 1998

본 논문에서는 화자 독립 연속 숫자음 인식 시스템의 성능향상을 위하여 MLP-VQ (Multi-Layer Perceptron-Vector Quantizer)를 이용한 가중 DHMM(WDHMM : Weighted Discrete Hidden Markov Models)을 제안한다. MLP 신경망의 출력분포는 입력 패턴과 학습 패턴들간의 비선형 매핑을 통해 각 패턴들간의 유사도를 나타내는 확률분포를 갖는다. 본 논문에서는 MLP 신경망의 출력분포중 가장 높은 출력 값을 갖는 MLP 신경망의 출력 노드를 인덱스를 이용하여 코드워드를 생성하는 MLP-VQ를 제안하였다. 제안된 MLP-VQ는 기존의 VQ에 비해 현재 입력패턴과 학습된 각 class 패턴들간의 유사성 정도를 인식모델을 반영할 수 있는 특징을 갖는다. 또한 MLP 신경망의 출력분포를 DHMM의 심벌 발생 확률의 가중치로 이용하는 가중 DHMM보다는 음소 클래스간의 관계를 인식모델에 반영할 수 있기 때문에 적은 계산양의 증가로 인식기의 성능을 14.71%개선할 수 있었다. 실험결과에 의하면, MLP-VQ와 WDHMM에 의한 화자독립 연결 숫자음 인식율은 84.22%이다.

• 한국ITS학회 논문지
• /
• 제15권3호
• /
• pp.34-44
• /
• 2016

본 연구에서는 고속도로 VDS에서 수집된 시간평균속도를 이용하여 공간평균속도를 산출하는 방법들의 성능을 비교하고자 한다. 이를 위해서 먼저, 이전 연구들에서 제시된 시간평균속도를 이용한 공간평균속도 추정방법들을 정리하였다. 현장에서 수집된 시간평균속도와 공간평균속도 자료는 기계 혹은 측정 상의 오차로 정확한 값을 보장하기 힘들다. 따라서 미시교통시뮬레이션모형을 이용하여 이상적인 상황에서 공간평균속도 값을 산출한 후, 본 연구에서 선정된 공간평균속도 산출방법론을 통해 산출된 추정값과 비교하였다. 비교 결과, 개별차량의 시간평균속도 자료를 이용하는 경우, 조화평균 값과 교통량-거리가중 조화평균 값이 공간평균속도 값에 가장 근사하게 분석되었다. 그리고 30초 단위 시간평균속도를 사용하는 경우에는 교통량-거리가중 조화평균 값이 가장 유사하였다. 현장에서 공간평균속도를 구하는 것이 매우 어렵기 때문에 본 연구에서는 중부고속도로에 레이더검지기를 설치하여 개별 차량의 경로자료를 수집한 후, 경로자료를 이용하여 공간평균속도를 산출하였다. 분석 결과, 교통량-거리가중 조화평균을 이용한 추정값이 공간평균속도에 비교적 유사한 것으로 나타났다.

• 한국농공학회지
• /
• 제31권1호
• /
• pp.117-130
• /
• 1989

In this study, an implicit one-dimensional model, DWRM(Dynamic Wave Routing Model) was developed by using the four-point weighted difference method. By applying the developed model to the Keum River, the parameters were calibrated and the model applicability was tested through the comparison between observed and computed water levels. In addition, the effects of the construction of an estuary dam to the flood wave were estimated as a result of the model application. The results of the study can be summarized as follows; 1. The roughness coefficients were evaluated by comparison between observed and computed water level at Jindu, Gyuam and Ganggyeung station in 1985. The Root Mean Squares for water level differences between observed and computed values were 0.10, 0.11, 0. 29m and the differences of peak flood levels were 0.07, 0.02, 0. 07m at each station. Since the evaluated roughness coefficients were within the range of 0.029-0.041 showing the realistic value for the general condition of rivers, it can be concluded that the calibration has been completed. 2. By the application of model using the calibrated roughness coefficients, the R. M. S. for water level differences were 0.16, 0.24, 0. 24m and the differences of peak flood level were 0.17, 0.13,0.08 m at each station. The arrival time of peak flood at each station and the stage-discharge relationship at Gongju station agreed well with the observed values. Therefore, it was concluded that the model could be applied to the Keum River. 3. The model was applied under conditions before and after the construction of the estuary dam. The 50-year frequency flood which had 7, 800m$^3$/sec of peak flood was used as the upstream condition, and the spring tide and the neap tide were used as the downstream condition. As the results of the application, no change of the peak flood level was showed in the upper reaches of 19.2km upstream from the estuary dam. For areas near 9.6km upstream from the estuary dam, the change of the peak flood level under the condition before and after the construction was 0. 2m. However considering the assumptions for the boundary conditions of downstream, the change of peak flood level would be decreased.

• 한국시뮬레이션학회논문지
• /
• 제18권4호
• /
• pp.185-195
• /
• 2009

최근 시스템들이 복잡해지면서 시뮬레이션을 통한 시스템의 분석이 주목을 받고 있다. 시뮬레이션 분석에서 가장 핵심적인 부분 중의 하나가 시뮬레이션 모델의 검증이며, 이 과정을 통하여 시뮬레이션 모델이 얼마나 실제 시스템을 대변할 수 있는지를 판단한다. 모델의 검증에서 시뮬레이션 모델과 실제시스템의 데이터를 비교할 때 발생하는 차이는 입력 데이터의 차이에 의한 영향도 있으며, 이를 통한 모델의 검증 결과는 높은 신뢰성을 보장하지 못한다. 따라서 이 논문에서는 실제와 동일한 입력 데이터를 바탕으로 하는 Trace-Driven 시뮬레이션을 기반으로 모델을 설계하였다. 한편, 출력데이터들을 하나의 통계량을 통한 검증이 아닌 클래스 별 검증을 하기 위해 데이터마이닝 분야에서 분류기의 성능을 판단하는 F 척도를 응용하여 시뮬레이션 모델의 검증을 수행하였다. 그 결과, 제안된 검증 방법은 정밀한 모델의 검증을 가능하게 하고, 검증 시에 피드백을 제공함으로써 용이한 수정 작업을 가능하게 한다.

• 품질경영학회지
• /
• 제32권4호
• /
• pp.169-183
• /
• 2004

The synthetic control chart (SCC) proposed by Wu and Spedding (2000) is to detect shifts in the process mean. The performance was re-evaluated by Davis and Woodall (2002), and the steady-state average run length (ARL) performance was shown to be inferior to cumulative sum (CUSUM) or exponentially weighted moving average (EWMA) chart This paper proposes a simple adaptive scheme to improve the performance of the synthetic control chart. That is, once a non-conforming (NC) sample occurs, we investigate the next L-consecutive samples with larger sample sizes and shorter sampling intervals. We employ a Markov chain model to derive the ARL and the average time to s19na1 (ATS). We also propose a statistical design procedure for determining decision variables. Comprehensive comparative study shows that the proposed control chart is uniformly superior to the original SCC or double sampling (DS) Χ chart and comparable to the EWMA chart in ATS performance.

• 한국멀티미디어학회논문지
• /
• 제14권12호
• /
• pp.1559-1571
• /
• 2011

In wireless ad hoc networks, nodes communicate with each other using multihop routed transmission in which hop-by-hop cooperative diversity can be effectively employed. This paper proposes (i) two cooperation models for per-link cooperation (PLC) and per-node cooperation (PNC) for exploiting cooperative diversity in wireless ad hoc networks and (ii) a cooperative routing algorithm for the above models in which best relays are selected for cooperative transmission. First, two cooperation models for PLC and PNC are introduced and represented as an edge-weighted graph with effective link quality. Then, the proposed models are transformed into a simplified graph and a cooperative routing algorithm with O(n2) time is developed, where n is the number of nodes in the network. The effectiveness of the algorithm is confirmed for the two cooperation models using simulation.