• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.811-816
• /
• 2001

정보 검색 시스템의 중요한 목적중의 하나는 단순히 사용자 질의를 만족하는 문서들의 집합을 검색하는 것이 아니라, 질의를 만족하는 정도에 따라 검색된 문서들에 순위를 부여함으로써 사용자들이 필요한 정보를 얻는데 소모되는 시간을 최소화시키는 것이다. 순수한 부울 검색 시스템은 검색 전략이 이진값에 근거하여 순위 구분 없이 연관/비연관 중의 하나로 결정된다. 딸서 문서와 질의 사이의 유사도를 나타내는 문서값을 계산할 수 없기 때문에, 검색된 문서들을 질의를 만족하는 정보에 따라 정렬할 수 없다. 부울 검색 시스템의 이러한 단점을 보완하는 방법으로 MMM 모델, Paice 모델, P-norm 모델이 개발되었다. 본 논문에서는 높은 검색 효과를 제공하는 백터모델에서 용어 가중치 재부여를 이용한 정보검색 모델을 제안한다. 벡터모델에서 용어 가중치 재부여를 이용한 질의 확장 모델의 연산 특성이 MMM, Paice, P-norm 모델보다 우수함을 설명하고, 또한 성능 비교를 통하여 이를 입증한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.23-26
• /
• 2001

순수한 부울 검색 시스템은 문서와 질의 사이의 유사도를 나타내는 문서값을 계산할 수 없기 때문에, 검색된 문서들을 질의를 만족하는 정보에 따라 정렬할 수 없다. 부울 검색 시스템의 이러한 단점을 보완하는 방법으로 MMM 모델, Paice 모델, p-norm 모델이 개발되었다. 본 논문에서는 높은 검색 효과를 제공하는 벡터모델에서 용어 가중치 재부여를 이용한 정보검색 모델을 제안한다. 벡터모델에서 용어 가중치 재부여를 이용한 질의 확장 모델의 연산 특성이 MMM, Paice, p-norm 모델보다 우수함을 설명하고, 또한 성능 비교를 통하여 이를 입증한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.895-897
• /
• 2004

문서 검색 시스템에서 특정 주지에 관한 문서를 검색하기 위한 색인어의 가중치 부여 방법으로 단순빈도와 역문헌빈도에 의한 가중치 부여 방법을 주로 이용한다 하지만 빈도 정보만을 이용한 방법은 성능 및 정확도의 향상에 한계가 있다. 이에 본 논문에서는 특허 문헌 검색 시스템의 검색 효율을 높이기 위해 자주 출현하는 복합명사의 재출현 양상과 복합명사의 역할변화에 따른 가중치 부여 방법을 제안한다 본 연구에서 제안한 가중치 부여 방법을 이용하여 실험한 결과 단순빈도와 역문헌빈도 정보를 이용한 방법보다 더 나은 성능을 보였다 .

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.743-750
• /
• 2003

In this paper, we propose a query expansion and weighting method for document filtering to increase precision of the result of Web search engines. Query expansion for document filtering uses ConceptNet, encyclopedia and documents of 10% high similarity. Term weighting method is used for calculation of query-documents similarity. In the first step, we expand an initial query into the first expanded query using ConceptNet and encyclopedia. And then we weight the first expanded query and calculate the first expanded query-documents similarity. Next, we create the second expanded query using documents of top 10% high similarity and calculate the second expanded query- documents similarity. We combine two similarities from the first and the second step. And then we re-rank the documents according to the combined similarities and filter off non-relevant documents with the lower similarity than the threshold. Our experiments showed that our document filtering method results in a notable improvement in the retrieval effectiveness when measured using both precision-recall and F-Measure.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.11 no.3 s.55
• /
• pp.43-52
• /
• 2007

This study suggests a method to determine optimal seismic retrofitting schemes for existing bridges based on weighting-factored evaluation. According to the recognition for potential seismic risk, various kinds of retrofitting methods are applied to improve the seismic performance of existing bridges. However, the relevant technique is not available to select optimal retrofitting scheme for bridges now. This suggested method weights five factors, structural compatibility, economic efficacy, environmental factor, consturctability and maintenance, and draws out optimal seismic retrofitting schemes. The application of the developed method to one hundred sixty existing bridges verifies the adaptability of this method. As a result, this study provides an idealized retrofitting schemes, and the suggested method could be a guideline to determine the more cost-effective and optimal retrofitting schemes for existing bridges in Korea.

• Journal of Environmental Impact Assessment
• /
• v.24 no.2
• /
• pp.190-203
• /
• 2015

VRI(Vulnerability-Resilience Index), which is defined as a function of 3 variables: climate exposure, sensitivity, and adaptive capacity, has been quantified for the case of Typhoon which is one of the extreme weathers that will become more serious as climate change proceeds. Because VRI is only indicating the relative importance of vulnerability between regions, the VRI quantification is prerequisite for the effective adaptation policy for climate in Korea. For this purpose, damage statistics such as amount of damage, occurrence frequency, and major damaged districts caused by Typhoon over the past 20 years, has been employed. According to the VRI definition, we first calculated VRI over every district in the case of both with and without weighting factors of climate exposure proxy variables. For the quantitative estimation of weighting factors, we calculated correlation coefficients (R) for each of the proxy variables against damage statistics of Typhoon, and then used R as weighting factors of proxy variables. The results without applying weighting factors indicates some biases between VRI and damage statistics in some regions, but most of biases has been improved by applying weighting factors. Finally, due to the relations between VRI and damage statistics, we are able to quantify VRI expressed as a unit of KRW, showing that VRI=1 is approximately corresponding to 500 hundred million KRW. This methodology of VRI quantification employed in this study, can be also practically applied to the number of future climate scenario studies over Korea.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2827-2830
• /
• 2002

본 논문에서는 청소로봇이 두 점간에 이동할 때 벽면을 안전하게 추적하는 방법과 두 점간의 이동 알고리즘을 제안하고자 한다. 제안한 방법은 각각의 적외선 센서에 다른 가중치 벡터를 부여하여 장애물이나 벽면에 대한 정보를 이용하게 된다. 청소로봇은 벽면정보를 이용하여 벽면 주행하게 했다. 그리고 두 점검간의 이동알고리즘으로 이동 할 경우에 벽면 추적 방법과 각도 오차 값과 거리의 error값이 오차가 0이 되도록 두 점간의 이동 알고리즘의 수식의 대수적인 합으로 안전하게 벽면을 주행하였다. Visual C++기반에서 시뮬레이션 한 결과 안전하게 벽면을 추적하고 벽면을 따라 주행하는 벽면주행 알고리즘을 제안하였다.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1078-1085
• /
• 2004

The SARLM(Source Adaptive Receiver-Driven Multi-Layered Multicast) has been proposed to address heterogeneous bandwidth constraints through layer merging and splitting. However, this method causes that receivers subscribing to the higher layer drop down to the lower layer and hence may decrease utilization of available bandwidth after layer merging. In this paper, we proposed a multicast regrouping method considering distributive status of receivers according to loss rates. The proposed method weights receivers according to loss rates. And then it groups higher layer with receivers subscribing to lower layer have extra bandwidth and lower layer with receivers subscribing to higher layer have high loss rate. Experimental results show that receivers subscribing to higher layer can receive in high transmission rate and consequently the proposed method effectively improves utilization of available bandwidth.

• Journal of Korean Society of Forest Science
• /
• v.103 no.1
• /
• pp.137-146
• /
• 2014

We have developed the Forest Carbon Sink Index on afforestation and reforestation activities, a regulation stated in article 26 of the 'Law on the maintenance and enhancement of carbon sink (Carbon Sink Law)', which took effect on March, 2013. According to the legal purpose to evaluate the performance of individual forest carbon offset projects and to compare each other at a certain point, values of the forest carbon sink index were calculated by the scoring method. Three criteria were established based on the Carbon Sink Law: 'Carbon' (real greenhouse gas reduction), 'Human' (socio-economic effect) and 'Nature' (environmental effect). Continuously, 9 indicators from the three criteria were selected by top-down approach; the adequacy of each criteria and indicators were reviewed through on-line Delphi survey; and finally weighted value of each criteria and indicators were assigned. To reflect the characteristics of the domestic forest carbon offset projects, which focus on corporate social responsibility-typed projects, we applied the score weighting method to minimize gaps among criteria and ones among indicators. After applying our newly developed forest carbon sink index to five domestic forest carbon offset projects, we could confirm that the criteria of 'Human' and 'Nature', which criteria are in relatively low weight, can play a role as an actual incentive to reduce negative socio-economic and environmental impacts. Based on performance evaluation of the five forest carbon offset project by the forest carbon sink index, the best or good performance project developers could be rewarded, and further the performance evaluation would work as an incentive to stimulate the involvement of domestic project developers in the field of forest carbon offset project.

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.149-158
• /
• 2005

The object of this paper is to develop the shortest path algorithm. The existing shortest path algorithm models are developed while considering travel time and travel distance. A few problems occur in these shortest path algorithm models, which have paid no regard to cognition of users, such as when user who doesn't have complete information about the trip meets a strange road or when the route searched from the shortest path algorithm model is not commonly used by users in real network. This paper develops a shortest path algorithm model to provide ideal route that many people actually prefer. In order to provide the ideal shortest path with the consideration of travel time, travel distance and road cognition, travel time is predicted by using Kalman filtering and travel distance is predicted by using GIS attributions. The road cognition is considered by using space data of GIS. Optimal routes provided from this paper are shortest distance path, shortest time path, shortest path considering distance and cognition and shortest path considering time and cognition.