http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 서기성 (검색결과 207 건)
- 무료
- 기관 내 무료
- 유료
-
-
-
서기성 한국시뮬레이션학회 1997 한국시뮬레이션학회 논문지 Vol.6 No.1
For the purpose of decreasing economic loss from the traffic jam, a car route guidance system efficiently utilizing the existing roads has attracted a great deal of attention. In this paper, the search algorithm for optimal path and alternative paths, which is the main function of a car route guidance system, was presented using evolution program. Search efficiency was promoted by changing the population size of path individuals in each generation, applying the concept of age and lifetime to path individuals. Through simulation on the virtual road-traffic network consisting of 100 nodes with various turn constraints and traffic volumes, not only the optimal path with the minimal cost was obtained, avoiding turn constraints and traffic congestion, but also alternative paths with similar costs and acceptable difference was acquired, compared with optimal path.
-
서기성,김세준,강성재,최효민,김성수 대한전기학회 2022 전기학회논문지 Vol.71 No.7
Occluded person re-identification is a challenging task which aims to search for or distinguish the specific person as human body is occluded by obstacles or other persons or by oneself. Some recent State of the art works which adopt transformer and/or pose-guided methods improve the feature representation and performances, but there is a room to enhance them in both representation and heavy structure. In this paper, we suggest to efficiently improve the transformer-based Re-ID method for the occluded person as follows. First, in data augmentation to improve Re-identification performance, instead of deleting an arbitrary area, only the part containing the keypoint feature of a person is deleted for effective learning in occlusion. Second, a consistency loss between global and local features of a body part is proposed for improving the discrimination to recognize the identical person. We compare the mAP and Rank-1 performances of our approach and various existing methods on the Occluded-Duke dataset. Experimental results show that our proposed model outperforms the competitive methods.
-
서기성 대한전기학회 2022 전기학회논문지 Vol.71 No.12
This paper investigates the jumpiness index based modeling for precipitation prediction. The jumpiness index (JI) represents different forecast jumps and the inconsistency correlation for forecasts issued at different times but valid for the same time. Unlike researches that improve the accuracy of predictions mainly, this study attempts to analyze the characteristics of prediction consistency for the numerical model GDAPS using the jumpiness index. In this work, we try to minimize prediction errors through a combination of JI elements and symbolic functions using Cartesian Genetic Programming (CGP), which is a kind of evolutionary computation to solve nonlinear regression problems. The relationship between the time-by-time jumpiness indices and the prediction error is analyzed. Also, the applicability of a combination of jumpiness indices to improve the accuracy of future forecasts is examined. Experiments are conducted to model the relationship between JI and UM error values calculated by GDAPS data for 2013 and 2014 for ground precipitation data using CGP-based symbolic nonlinear regression.
-
서기성 대한전기학회 2022 전기학회논문지 Vol.71 No.12
This paper aims to improve the feature representation by diversifying CNN filters inspired by niche concept in evolution. The singular value decomposition (SVD) entropy based efficient metric for diversity is proposed In the proposed approach, filters are clustered by groups and they are calculated as differences from the center values within the groups, rather than by entire rank based comparison. This provides an effective method for increasing the substantial diversity of filters. Furthermore, the filters with low diversity are adjusted by the diversity spreading framework for better diversity in the reconstruction process. The improvement of the filter representation by performing experiments on CIFAR 10/100 data for VGG16, and ImageNet for ResNet34 is provided. Because there are no similar studies, we compare our results with respect to those of relatively relevant pruning methods in terms of classification performance accuracy as well as the pruned rates and flops.
-
-
-
SVR을 사용한 데이터 학습 기반의 풍속 예측 모델 생성
서기성 한국지능시스템학회 2017 한국지능시스템학회논문지 Vol.27 No.6
Developing numerical models for weather prediction is a very difficult and expensive task. The approach to compensate numerical prediction models is mainly occupied, and the generation of daa tbased prediction models has hardly been tried. We have attemtepd to generate a data based prediction model of wind speed using SVR technique for long term data. Using the UM and KLAPS data from 2007 to 2013 year for Seoul, Busan, and Jeju Island, the prediction model was generated and the performance was evaluated. As a result, the results approximated to the compenation method were obtained. On the other hand, fundamental errors are included by using the generated values of the numerical prediction model instead of actual measurement data for predictor variables constituting the model. In order to solve this problem, we constructed a model using data with errors less than a certain level, which resulted in improved outcomess 기상 예측에 대한 수치 예보 모델을 개발하는 것은 매우 어렵고 비용이 많이 드는 작업이므로, 통계적 데이터 기반의 모델생성이 대안이 될 수 있다. 그러나 지금까지는 주로 수치 예보 모델을 보정하는 접근법이 주를 차지하고 있고, 데이터 기반의예보 모델 생성은 거의 시도되지 않고 있다. 본 논문에서는 장기간의 데이터에 대해서 SVR 기법을 사용하여 풍속에 대한데이터 기반 예보 모델을 생성한다. 서울, 부산, 제주도 지역에 대해서 2007~2013년도의 UM과 KLAPS 데이터를 사용하여모델을 생성하고 보정방식과 성능을 비교하여 근접한 성능 결과를 얻었다. 한편 모델을 구성하는 기본 인자들의 데이터가실측치가 아닌 수치예보모델에 의한 생성값을 사용함으로써 원천적인 오차를 포함하고 있다. 이 문제를 해결하기 위해서오차가 일정 수준 이하의 수치예보모델 데이터를 사용하여 모델을 구성하고 이를 통해 향상된 결과를 얻었다
-
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
