• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.113-116
• /
• 2008

According to a domestic provision, test levels of the barrier are divided into seven categories(SB1 to SB7) and the corresponding crash conditions are specified. Meanwhile, standard types of concrete barriers with different dimensions have been constructed nation wide. Some studies aimed at finding a proper test level of each type of the concrete barrier have been carried out, but the reliable and consistent results have not been fully established yet. The purpose of this study is to find out the test level corresponding to the concrete barrier of type-2 through static test. AASHTO LRFD was referred to for the loading pattern and a magnitude of the load that simulate a vehicle crash assumed. The test results show that the ultimate strength of the type-2 satisfies the load level required for SB5. However, it seems that the type-2 does not comply with SB6, showing some differences in results from previous analytical studies. In order to take advantage of the static test in establishing the test level of the domestic barrier, more detailed provisions should be specified.

• Convergence Security Journal
• /
• v.7 no.2
• /
• pp.39-47
• /
• 2007

The scheduling algorithms to provide quality of service (QoS) in broadband convergence network (BcN) are compared and analysed. The main QoS management methods such as traffic classification, traffic processing in the input queue and weighted queueing are first analysed, and then the major scheduling algorithms of round robin, priority and weighted round robin under recently considering for BcN to supply real time multimedia communications are analysed. The simulation results by NS-2 show that the scheduling algorithm with proper weights for each traffic class outperforms the priority algorithm.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.21-22
• /
• 2021

Domestic residential buidling grading is currently comprised of 5 fields; sound-proofing, structure, ambient condition, living environment and fire-proofing. However, factors the take up most of the civil complaints are related to leakage, and waterproofing is not listed as part of the grading system. In particular, the Ministry of Land and Transport claims that the most crucial problems are leakage related in residential structures. Therefore, this study proposes to provide such grading system for waterproofing by AHP methodology based on waterproofing application locations in residential structures.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.110-110
• /
• 2018

상수관로의 노후화는 단수유발, 수압부족 및 수질악화, 싱크홀 발생 피해와 누수로 인한 경제적 손실 등을 초래한다. 최근 상수관로의 노후화에 의한 피해가 심각해짐에 따라, 환경부에서는 전국적으로 노후관로를 개량 및 교체하는 작업을 시행하고 있다. 다만, 모든 노후관로를 일시에 보수 및 교체하는 것은 불가능하므로, 사용 중인 관로의 노후도를 정량적으로 판단하여 개량우선순위를 결정해야한다. 현재 국내에서는 '상수도 기술진단' 매뉴얼에 따른 관망성능평가 결과를 이용하여 상수관로의 노후화 정도를 평가하고 있다. 이는 평가항목 별로 기준을 나누어 조건값과 가중치를 부여하고, 총 점수를 합산하여 해당 관로의 평가 점수에 따라 등급을 판정하게 되는 점수평가법이다. 본 연구에서는 기존의 점수평가법과의 비교를 통하여, ANN(Artificial Neural Network)-Clustering 기법이 상수관로의 노후도 평가를 위한 새로운 평가방법이 될 수 있음을 제시하였다. 본 연구는 강원도 Y지역의 상수관로를 대상으로 진행하였으며, 기존의 관망성능평가 항목을 이용하여 전체 관로를 세 가지 등급으로 분류하여 노후도를 평가하였다. 또한 ANN-Clustering방법의 적용 가능성을 판단하기 위하여 기존의 점수평가법 결과와 비교분석을 실시하였으며, 전체 대상관로의 노후도 정도를 직관적으로 파악할 수 있도록 계산된 노후도 등급을 관망도에 도시하였다. ANN-Clustering방법은 관로의 다양한 특성값을 손쉽게 변경하여 적용할 수 있으며, 기존의 점수평가법과 더불어 상수관로의 유지관리를 위한 보다 객관적이고 합리적인 관망성능평가법이 될 수 있을 것으로 기대한다.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.67-75
• /
• 2010

This paper proposes a bacteria cooperative optimization (BCO) method applying individuals's speed for the performance improvements. All individuals in existing BCO methods move the same length at the same time because their speeds are constant. These methods had the problem that the individuals couldn't find the global optimum effectively because good individuals and bad individuals had same speeds. In order to overcome this problem, we applied the speed concept to the BCO algorithm that individuals moved different lengths according to their speeds assigned by the ranks of individuals according to the fitness of individuals. That is to say, we provide high speeds to bad individuals with low fitness in order to fast move to the areas with high fitness and provide low speeds to good individuals with high fitness because they may be near global optimum. It was found from experimental results of four function optimization problems that the proposed method outperformed the existing methods. Our method showed better performances even than the rank replacement method. This means that applying speed concepts to the individuals for BCO is very effective and efficient.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.7
• /
• pp.327-332
• /
• 2016

This study is a leading research project to develop an automatic grade decision making algorithm of a 6-years-old fresh ginseng. For this work, we developed a Ginseng image acquiring instrument which can take 4-direction's images of a Ginseng at the same time and obtained 245 jingen images using the instrument. The 12 parameters were extracted for each image by a manual way. Lastly, 4 parameters were selected depending on a Ginseng grade classification criteria of KGC Ginseng research institute and a survey result which a distribution of averaging 12 parameters. A pattern recognition classifier was used as a support vector machine, designed to "k-class classifier" using the OpenCV library which is a open-source platform. We had been surveyed the algorithm performance(Correct Matching Ratio, False Acceptance Ratio, False Reject Ratio) when the training data number was controlled 10 to 20. The result of the correct matching ratio is 94% of the $1^{st}$ ginseng grade, 98% of the $2^{nd}$ ginseng grade, 90% of the $3^{rd}$ ginseng grade, overall, showed high recognition performance with all grades when the number of training data are 10.

• Journal of the Korean Wood Science and Technology
• /
• v.39 no.1
• /
• pp.1-7
• /
• 2011

Recently, the visual grading rule of Korea Forest Research Institute (KFRI) was revised and it is necessary to investigate the distribution characteristics of visual graded lumber in accordance with the revised rule. Therefore, in this study, the distribution characteristics of bending strength was investigated with revised visual grading rule and changed prior rule, respectively. The size of specimens was $38{\times}140{\times}3,000$ (mm) and the species were $Larix$ $kaempferi$ and $Pinus$ $koraiensis$. The moisture content was under 18% and the specimens were tested in accordance with ASTM D-198. The number of No. 1 and 2 grades, suitable for structural lumber, was increased when the revised visual grading rule was applied. Moreover, the revised rule was more effective to distinguish sharply between No. 1 and 2 grades and below No. 3 grade. Meanwhile, the lower 5% exclusion limit and allowable stresses were generally decreased when revised visual grading rule had been applied. However, the announcement of Korea Forest Service, tested with small clear specimen, was much lower than the allowable stresses of this test, tested with structural lumber. Therefore, the revision of allowable design values should be considered for more exact use and effective structural design.

• Product Safety
• /
• s.196
• /
• pp.16-17
• /
• 2010

$\blacksquare$ 지식경제부(최경환 장관)은 에너지소비효율 등급표시를 위반한 9개 업체에 대해 생산 판매금지등의 시정명령을 했다고 밝혔음 $\circ$ (대상 및 내용) '09. 1월 ~ 10.1월간, 19개품목 179개모델 제품에 표시된 성능과 매장에서 채취한 샘플제품의 시험측정결과를 비교 검사하고 위반제품에 대해 아래와 같이 시정 명령을 요구하였음 - (생산판매금지) 최저소비효율에 미달된 5개 회사의 전기냉장고, 백열전구, 어댑터 충전기 등 6개모델 - (등급조정) 소비효율등급표시를 위반한 2개회사의 전기진공청소기, 선풍기 등 2개 모델 - (표시사항정정) 소비효율 표시사항의 허용오차를 초과한 2개회사의 선풍기 2개 모델 $\circ$ (조치의무 등) 위반업체 및 모델을 관보에 게재('10.3.10)하고 해당 제조 수입업체는 시정명령에 대한조치결과를 1개월이내 보고해야함 - 시정명령 미이행시에는 위반내용에 따라 벌금 과태료등의 벌칙에 처할 수 있음

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.146-151
• /
• 2013

이중언어 사전 구축 방법을 평가하는 방법에는 정확률, 재현율, MRR(Mean Reciprocal Rank) 등이 있다. 이들 방법들은 평가 집합에 있는 대역어를 정확하게 찾는 것에 초점을 맞추고 있다. 그러나 어떤 대역어가 얼마나 많이 사용되는지는 전혀 고려하지 않는다. 즉 자주 사용되는 대역어를 빨리 찾을 수 있는 방법이 좋은 방법이라고 말할 수 있다. 이와 같은 문제를 해결하기 위해서 본 논문에서는 이중언어 사전 구축의 새로운 평가 방법인 등급 재현율을 제안한다. 등급 재현율(rated recall)은 대역어가 학습 말뭉치에 나타난 정도를 반영하는 재현율이며, 자주 사용되는 대역어를 얼마나 정확하게 찾는지를 파악할 수 있는 좋은 측도이다. 본 논문에서는 문맥벡터와 중간언어를 이용한 이중언어 사전 구축 시스템의 성능을 평가하고 기존의 방법과 비교 분석하였다.