• 한국정보과학회논문지:소프트웨어및응용
• /
• 제26권1호
• /
• pp.93-93
• /
• 1999

Researches on digit recognition have been conducted actively for a long time because the classes to recognize are much fewer than other character sets and because it is very likely thatthe digit recognition can be applied to many problems in real world, The recent studies on designingrecognition system with high performance are in progress with two different aspects. One is toconstruct a recognizer using several features at the same time, and the other is to use severalrecognizers. In this paper, we propose a multistage combination method to recognize the unconstrainedhandwritten numerals. The method is a two-stage combination method which uses multiplecombination methods at the same time unlike the existing methods with only one combination method.The recognizers are first combined by several combination methods of different classes simultaneously,and then the results of them are combined by another combination method to generate a final result.Five recognizers and eight combination methods are used in the proposed system. The experimentalresults showed that the recognition rates on CENPARMI and CEDAR data were 97.75% and 98.6%,respectively and the recognition performance could be improved as the process passed through stages,We could get the best performance by combining the combination methods of different classes, whichmeans there are a complementary relation among them, The proposed method can be considered asan extended version of the existing combination methods.

• 한국항행학회논문지
• /
• 제20권3호
• /
• pp.203-209
• /
• 2016

자동종속 감시 시스템 (ADS-B; automatic dependent surveillance - broadcast) 시스템과 다변측정 항공감시 시스템(MLAT, multilateration) 시스템은 통신/항행/감시 및 교통관리 (CNS/ATM; communications, navigation, and surveillance/air traffic management)의 다양한 분야 중에서 감시분야에 속한다. ADS-B와 MLAT는 위성 및 디지털 통신 기술을 기반으로 구현되어 레이더 보다 성능이 뛰어나지만, 여전히 오차는 가지고 있다. 우는 이러한 오차를 줄이기 위해 reweighted convex combination method를 제안한다. Reweighted convex combination method는 기존의 convex combination method를 개선한 정보융합 기법으로 시스템에 주어지는 가중치를 재조정하여 항공기 추적 성능을 향상시킨다. reweighted convex combination method을 ADS-B와 MLAT에 적용 시켰을 때, 평균 51.51 %의 성능향상이 있었다.

• 한국의류학회지
• /
• 제38권3호
• /
• pp.415-426
• /
• 2014

This study investigated the color change, enhancement of dye uptake, washing fastness, and light fastness of cotton and silk when dyed with Juniperus chinensis and Terminalia chebula (combination dyeing) using various methods. The dyeing methods were 1) dyeing Juniperus chinensis extract and Terminalia chebula Retzius extract sequentially (J-T), 2) dyeing Terminalia chebula Retzius extract and Juniperus chinensis extract sequentially (T-J), 3) dyeing Juniperus chinensis extract and Terminalia chebula Retzius extract simultaneously (J+T), and 4) dyeing Juniperus chinensis extract 4 times repeatedly and followed by a dyeing Terminalia chebula Retzius extract in sequence. In terms of increased dyeing uptake, combination dyeing (dyeing 2 times like method 1, 2, 3) had the same impact as the repeated dyeing (method 4). The color of J, T combination dyeing showed wide range of mixed YR series, Y series resulting from Terminalia chebula Retzius, and R series resulting from Juniperus chinensis. In cotton, J-T dyeing method showed superior enhancement of dye uptake, and T-J method in silk. In both of the cases, Y series color from Terminalia chebula Retzius extract was mainly shown (Y series color was superior to R series color after dyeing). Therefore, it is recommended for cotton to implement T-J method and for silk to implement J-T method in order to enhance both dyeing uptake and emphasize the color of R series. The K/S value of combination dyed fabrics was decreased by increasing washing time; however, the K/S value of combination dyed fabrics was increased by increasing UV irradiation time. But after repeated washing and longer UV irradiation, ${\Delta}E$ value of combination dyed fabric became smaller compared to fabric dyed with Juniperus chinensis only. Thus, it was found that after J, T combination dyeing, fabric became less prone to fading by washing and UV than after Juniperus chinensis single dyeing was done.

• Bioinformatics and Biosystems
• /
• 제1권2호
• /
• pp.128-133
• /
• 2006

This paper compares domain combination based protein-protein interaction prediction method with domain based protein-protein interaction method. The prediction accuracy and reliability of the methods are compared using the same prediction technique and interaction data. According to the comparison, domain combination based prediction method has showed superior prediction accuracy to domain based prediction method for protein pairs with fully overlapped domains with protein pairs in learning sets. When we consider that domain combination based method has the effects of assigning a weight to each domain interaction, it implies that we can improve the prediction accuracies of currently available domain or domain combination based protein interaction prediction methods further by developing more advanced weight assignment techniques. Several significant facts revealed from the comparative studies are also described in this paper.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.1037-1040
• /
• 2000

We introduce the forecasting method for a next day electric peak load that uses the optimal combination of two types of neural networks. First network uses learning data that are past 10days of the target day. We name the neural network Short Term Neural Network (STNN). Second network uses those of last year. We name the neural network Long Term Neural Network (LTNN). Then we get the forecasting results that are the linear combination of the forecasting results by STNN and the forecasting results by LTNN. We name the method Combination Forecasting Method (CFM). Then we discuss the optimal combination of STNN and LTNN. Using CFM of the optimal combination of STNN and LTNN, we can reduce the forecasting error.

• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1489-1502
• /
• 2019

This work introduces a novel unweighted combination method (UCSS) for business failure perdition (BFP). With considering features of BFP in the age of big data, UCSS integrates the quantitative and qualitative analysis by utilizing soft set theory (SS). We adopt the conventional expert system (ES) as the basic qualitative classifier, the logistic regression model (LR) and the support vector machine (SVM) as basic quantitative classifiers. Unlike other traditional combination methods, we employ soft set theory to integrate the results of each basic classifier without weighting. In this way, UCSS inherits the advantages of ES, LR, SVM, and SS. To verify the performance of UCSS, it is applied to real datasets. We adopt ES, LR, SVM, combination models utilizing the equal weight approach (CMEW), neural network algorithm (CMNN), rough set and D-S evidence theory (CMRD), and the receiver operating characteristic curve (ROC) and SS (CFBSS) as benchmarks. The superior performance of UCSS has been verified by the empirical experiments.

• 감성과학
• /
• 제13권2호
• /
• pp.301-308
• /
• 2010

본 연구는 톤 인 톤 배색과 톤 온 톤 배색을 활용한 배색의 감성 효과에 관한 것이다. 톤 인 톤 배색 과 톤 온 톤 배색에 근거하여 제작한 24개 배색에 대하여 Osgood의 SD법(Semantic Differential Method)을 이용하여 10명 대학생에게 배색에 대한 인상 평가를 받았으며 자료 분석은 엑셀 통계 프로그램 2004를 사용하여 요인분석을 하였다. 연구결과, 톤 인 톤 배색에 근거한 배색과 톤 온 톤 배색에 근거한 배색의 인상이 매우 다르게 평가되는 것을 확인했다. 따라서 색채조화의 형식으로 제안되는 배색 기법이 배색의 감성 효과에 영향을 미칠 가능성을 확인하였다. 그리고 '좋다-싫다', '어린이답다-어른답다', '강하다-약하다', '따뜻하다-차갑다' 4개 이미지 차원이 도출되었으며 이러한 이미지에는 색상과 색조가 영향을 주는 요소로 작용한다는 것을 확인하였다. 제품의 사진배색과 거의 동일한 색종이 배색의 인상을 비교한 것으로 색표를 이용한 배색과 그 배색에 근거한 제품의 배색 인상에는 거의 차이가 없다는 것을 확인하였다. 그러나 제품이 가진 고유 특성이나 형태, 재질 등에 의해 인상이 크게 달라지는 것도 확인하였다. 이러한 연구 결과는 배색 이미지나 색채 디자인의 기초 자료로 활용 될 것이다.

• 전기학회논문지
• /
• 제62권1호
• /
• pp.133-139
• /
• 2013

Convex combination of two adaptive filters is an efficient method to improve adaptive filter performances. In this paper, a subband convex combination method of two adaptive filters for fast convergence rate in the transient state and low steady state error is presented. The cost function of mixing parameter for a subband convex combination is defined, and from this, the coefficient update equation is derived. Steady state analysis is used to prove the stability of the subband convex combination. Some simulation examples in system identification scenario show the validity of the subband convex combination schemes.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2001년도 학술발표대회논문집
• /
• pp.65-68
• /
• 2001

Color is an imfortant factor for interior design. But both selecting the appropriate color and combinating many color are not easy. Actually designers spend much time searching interior images published in magazine to refer to previous cases of the color combination. And the side up, they undergo a process to try to search own hoping color in the interior design example of the magazine. As an alternative to avoid this inefficient process, this study provides a method to show good cases of color combination. This method can reduce trial and error in the determination the color combination.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2005년도 학술발표회 논문집
• /
• pp.185-192
• /
• 2005

Using existing static methods, it is possible to estimate accurately the reponses of structures governed by the fundamental mode. However, these methods do not provide reliable estimates for the structure where higher mode effects are significant. Parametric study was performed to analyze the dynamic characteristics of the structure with long vibration period. Based on the investigations, a new modal combination method using modal combination coefficients, Factored Modal Combination, was developed, and static earthquake load patterns addressing higher mode effects reasonably were proposed. Existing modal combination methods, such as SRSS and CQC, lack a theoretical basis to be applied to inelastic structures. In contrast, the proposed method can be applied conveniently in inelastic range as well as in elastic range.