• International Journal of Highway Engineering
• /
• v.12 no.3
• /
• pp.87-92
• /
• 2010

As the Concept "how environmental friendly" becomes more and more important in road construction. However, so far there is no estimation method. Environmental friendly concept can be incorporated at the plan level in order to influence decision making, and support policies that affect environment. The overall goal of this study was to develop environmental friendly concept measures for the national highway and to develop a methodology to implement a more environmental friendly concept. The research identified 8 performance measures through a project analysis that could address environmental impact assessment system's ten strategic goals - Topography, Wildlife, hydrology, landuse, air quality, water quality, soil, waste, noise, landscape. The qualitatively and quantitatively evaluation approach was selected as the decision support framework and performance measure were investigated using the AHP(Analytic Hierarchy Process) and pilot corridor for a 10 section and calculate the index values. The methodology was applied to a pilot corridor comprised of a 120km section of national highway in korea. The methodology made it possible to identify the specific performance measures that need improvement to enhance the overall environmental friendly concept. It is fairly intuitive, based on readily available data, and is easy to apply. It provides a powerful tool for government to assess the relative environmental friendly conceptof their transportation corridors now and in the future. It allows for comparisons within a corridor and with other corridors and identifies the improvements needed to enhance the environmental friendly concept.

• Journal of Digital Convergence
• /
• v.18 no.2
• /
• pp.205-211
• /
• 2020

The method of predicting the future may be predicted by technical characteristics or technical performance. Therefore, technology prediction is used in the field of strategic research that can produce economic and social benefits. In this study, we predicted the future market through the study of how to predict the future with these technical characteristics. The future prediction method was studied through the prediction of the time when the market occupied according to the demand of special product. For forecasting market demand, we proposed the future forecasting model through comparison of representative quantitative analysis methods such as CAGR model, BASS model, Logistic model and Gompertz Growth Curve. This study combines Rogers' theory of innovation diffusion to predict when products will spread to the market. As a result of the research, we developed a methodology to predict when a particular product will mature in the future market through the spread of various factors for the special product to occupy the market. However, there are limitations in reducing errors in expert judgment to predict the market.

• Spatial Information Research
• /
• v.7 no.1
• /
• pp.49-61
• /
• 1999

The purpose of this study is to find out the methodologies, using GIS techniques, to appraise the parcel prices and to estimate the compensation expenditures according to road expansions. This study consists of 2 parts. The first pare is to find out the ways for appraisal of patrol prices in certain area by the publicly announced land prices. The second part is to estimate the differences of compensation expenditures according to road expansion methods. The conclusions are as follows. First, to appraise the target parcel prices, a comparison to the publicly announced land prices should be used. For this, 19 items of land characteristics of existing land information should be analyzed and compared using GIS techniques. Second, the compensation expenditure could be easily estimated using GIS techniques too. In this process, if necessary, we have to apply the minimum parcel size in Building Codes.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.81-84
• /
• 1998

본 논문에서는 문장의 문법 구조로부터 운율 경계 강도를 효율적으로 예측하기 위해서, 문법 정보의 세밀함에 따라 품사셋을 3단계로 설정하였다. 그리고 운율 경계 강도를 예측하는데 있어서 어떠한 품사셋이 최적인가를 알아보기 위해 150문장의 코퍼스를 구축하였으며, 세 종류의 품사셋에 대해 코퍼스를 수작업으로 품사분석을 하였다. 청취실험으로 결정한 운율 경계 강도를 바탕으로 확률론적인 모델링 방법을 사용하여 예측하는 실험을 하였다. 이러한 예측결과를 평가 비교하여 최적의 품사셋을 정하였다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.13 no.1
• /
• pp.63-74
• /
• 2000

The main objective of this paper is to apply as the basic data for development of a methodology to discuss the future earthquake preparedness measures in Korea by investigating the concept and applicabilities of the Japanese Standard for Evaluation of Seismic Performance of Existing RC Buildings developed in Japan among the methodologies of all the countries of the world. This paper describes the seismic performance, Is-index, of existing RC buildings in Tokyo, Japan evaluated by the Japanese Standard, also the relationships between Is-index distribution of existing RC buildings in Tokyo and that of Shizuoka and Chiba Prefecture reported already in reference[4][5][6] are investigated. And from the comparison with Is-index to buildings damaged by earthquakes experienced in Japan, the damage ratio due to severe earthquake of 3 districts mentioned above is estimated based on the probabilistic point of view. The results of this study can be utilized to identify urgently required earthquake preparedness measures with highest priority in existing RC buildings, and the methodology to evaluate the seismic performance of existing RC buildings in Japan, statistics analysis method and the methodology to estimate earthquake damage ratio based on the probabilistic point of view shown in this study can be recommended to develop a methodology to discuss the future earthquake preparedness measures in Korea.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.329-345
• /
• 2021

Recommender systems use data from customers to suggest personalized products. The recommender systems can be categorized into three cases; collaborative filtering, contents-based filtering, and hybrid recommender system that combines the first two filtering methods. In this work, we introduce and compare deep learning-based recommender system using autoencoder. Autoencoder is an unsupervised deep learning that can effective solve the problem of sparsity in the data matrix. Five versions of autoencoder-based deep learning models are compared via three real data sets. The first three methods are collaborative filtering and the others are hybrid methods. The data sets are composed of customers' ratings having integer values from one to five. The three data sets are sparse data matrix with many zeroes due to non-responses.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.247-250
• /
• 2021

관계추출(Relation Extraction)이란 주어진 문장에서 엔터티간의 관계를 예측하는 것을 목표로 하는 태스크이다. 이를 위해 문장 구조에 대한 이해와 더불어 두 엔터티간의 관계성 파악이 핵심이다. 기존의 관계추출 연구는 영어 데이터를 기반으로 발전되어 왔으며 그에 반해 한국어 관계 추출에 대한 연구는 부족하다. 이에 본 논문은 한국어 문장내의 엔터티 정보에 대한 위치 정보를 활용하여 관계를 예측할 수 있는 방법론을 제안하였으며 이를 다양한 한국어 사전학습 모델(KoBERT, HanBERT, KorBERT, KoELECTRA, KcELECTRA)과 mBERT를 적용하여 전반적인 성능 비교 및 분석 연구를 진행하였다. 실험 결과 본 논문에서 제안한 엔터티 위치 토큰을 사용하였을때의 모델이 기존 연구들에 비해 좋은 성능을 보였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.6-6
• /
• 2018

최근 집중 호우로 인한 내수침수 피해가 도시화와 기후변화로 늘어나고 있다. 내수침수 피해로 인한 복구비용과 시간이 증가하고 있으며 향후에는 이보다 더 크게 늘어날 것으로 예상된다. 이러한 문제를 해결하기 위하여 충분한 선행시간을 가지고 내수 침수 구역을 제시할 수 있어야 한다. 기존의 물리적 모델은 정확하고 정교한 결과를 제공하지만, 시뮬레이션을 준비하고 마치는 데에 시간이 많이 소요된다. 그 이유로서는 강우량, 지형적 특성, 배수관망 시스템, 수문학적 매개변수 등의 다양한 데이터도 필요하기 때문이다. 이는 도시유역에 대한 내수침수의 실시간 예측이 어렵게 되었으며, 충분한 선행시간을 확보하지 못하는 원인이 되었다. 본 연구에서는 이 문제에 대한 해결책으로 결정론적 방법과 확률론적 방법을 자료지향형 모형으로 결합하여 해결책을 제시하고자 하며, 특정 강우 조건하에 도시유역에서의 내수침수에 영향을 미치는 맨홀에 대한 정보를 제공하고자 한다. 위와 같은 과정을 수행하기 위하여 입력자료 조합에 대한 비선형 분석을 실시하였으며, 그 결과로 특정 강우 조건에 대하여 각 맨홀에 대한 누적월류량을 예측할 수 있는 비선형 인공신경망을 구축할 수 있었다. 본 연구에서 제시된 방법론은 국내의 강남 배수분구에 대하여 적용이 되었으며, 내수침수 예측결과와 2차원 해석결과를 비교하고자 하였다. 본 연구에서는 위 과정을 통하여 1차원 도시유출해석을 위한 입력 자료를 준비하는 시간을 절약하고, 다양한 강우 조건과 내수침수지도 사이의 연관성을 학습하는 예측 모형을 이용하여 도시유역의 내수침수에 대한 충분한 선행시간을 확보하고자 한다. 결론적으로, 이 연구의 결과는 도시유역에 대한 비구조적 대책 수립에 도움을 줄 것으로 확인이 되며 도시 유역 내에 맨홀 위치들을 고려한 위험지구를 파악하는 데에 유용할 것으로 판단된다.

• Journal of the Korea Society for Simulation
• /
• v.24 no.3
• /
• pp.89-96
• /
• 2015

In order to use missiles more effectively, assessing methodologies was advanced about weapon effects for various target types. We tried to find out the most effective analysis methodologies for missiles to attack 3 dimensional building target's and analyzed adaptedness as an assessing methodology. There are EFD (Expected Fractional Damage) and SSPD (Single Sortie Probability of Damage) methodologies to assess building target damage. In order to calculate effectiveness we used input parameter such as size of the target and CEP (Circular Error Probable), MAE_bldg (Mean Area of Effects for Building) of weapons and impact angle as encountering condition between the target and the missile. We compared EFD and SSPD, in order to analyze adaptedness as a effective methodology by CEP and MAE. The result was that EFD methodology was more adaptive to assess 3 dimensional building targets by missile systems than SSPD.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1371-1383
• /
• 2014

Classification ensemble technique is a method to combine diverse classifiers to enhance the accuracy of the classification. It is known that an ensemble method is successful when the classifiers that participate in the ensemble are accurate and diverse. However, it is common that an ensemble includes less accurate and similar classifiers as well as accurate and diverse ones. Ensemble pruning method is developed to construct an ensemble of classifiers by choosing accurate and diverse classifiers only. In this article, we proposed an ensemble pruning method called WAVE-bagging. We also compared the results of WAVE-bagging with that of the existing pruning method called Lasso-bagging. We showed that WAVE-bagging method performed better than Lasso-bagging by the extensive empirical comparison using 26 real dataset.