• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.257-260
• /
• 2003

인터넷에 대한 많은 관심만큼 교육용 웹 사이트를 신뢰성 있고 효과적으로 평가할 수 있는 평가모델의 개발이 활발히 연구되어 지고 있다. 본 논문은 지금까지 여러 분야에서 제시되어 사용되고 있는 다양한 웹 문서 평가기준 기준에 관한 기존 연구를 바탕으로 평가 항목을 제시하였다. 그리고, 교육용 웹 사이트 평가 수준을 계량적으로 표현할 수 있는 모델을 제시하였다. 또한 교육용 웹 사이트 평가 모델의 평가단계 평가 영역별 가증치를 설정하여 평가 모형이 교육용 웹 사이트에서 고유의 특성을 잘 반영할 수 있도록 하였다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.5 no.2
• /
• pp.113-124
• /
• 2001

이 연구는 철근콘크리트 구조물의 비탄성 거동을 파악하고 합리적이면서 경제적인 내진설계기준의 개발을 위한 자료를 제공하는데 그 목적이 있다. 정학하고 올바른 내진성능의 파악을 위하여 비탄선 해석프로그램을 사용하였다. 사용된 프로그램은 철근콘크리트 구조물의 해석을 위해서 유한요소법을 이용하여 개발된 RCAHEST이다. 재료적 비선형성에 대해서는 균열콘크리트에 대한 인장, 압축 전단모델과 콘크리트 소에 있는 철근모델을 조합하여 고려하였다. 이에 대한 콘크리트 균열모델로서는 분산균열모델을 사용하였다. 또한, 횡방향 구속철근으로 인한 강도의 증가 효과를 고려하였다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.11 no.3
• /
• pp.59-65
• /
• 1991

Failure criteria for asphalt concrete pavements are developed combining the AASHTO design equation and the multi-layered elastic theory. Thickness range including typical layer thicknesses of four-layer Korea highway structures are employed for pavement structure models. Total of 2430 pavement models with different layer thicknesses and moduli are analyzed. Models with crushed stone and asphalt stabilized base courses are equally included in the analysis. Number of load repetition and the maximum tensile strain at the bottom of asphalt layer are computed from the AASHTO design equation with terminal PSI=2.5 and multi-layered elastic computer program, SINELA, respectively. Failure criteria are developed through the regression analysis. From the analysis, failure criteria for the asphalt concrete pavements with 50% and 95% reliability levels are developed. It is found that the failure criterion of 95% reliability level gives similar results with existing fatigue failure criteria whose terminal performance condition is crack development when compared in a graphical form an equation to estimate failure criterion for a specific reliability level is also proposed.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.141-148
• /
• 2004

The ground positions and elevations information called DEMs(Digital Elevation Models) which are extracted from the stereo aerial photographs and/or satellite images using image matching method have the natural errors caused by variant environments. This study suggests the method to evaluate DEMs using correlation values between the reference and the target DEMs. This would be strongly helpful for experts to correct these errors. To evaluate the whole area of DEMs in the horizontal and vertical errors, the target cell is matched for each reference cell using the correlation values of these two cells. When the target cell is matched for each reference cell, horizontal and vertical error was calculated so as to help experts to recognize a certain area of DEMs which should be corrected and edited. If the correlation value is low and tile difference in height is high, the target cell will be candidated as changed or corrupted cell. When the area is clustered with those candidated cells, that area will be regarded as changed or corrupted area to be corrected and edited. Using this method, the evaluation for all DEM cells is practicable, the horizontal errors as well as vertical errors is calculable and the changed or corrupted area can be detected more efficiently.

• Journal of Advanced Navigation Technology
• /
• v.28 no.1
• /
• pp.149-154
• /
• 2024

Research on particulate matter is advancing in real-time, and various methods are being studied to improve the accuracy of prediction models. Furthermore, studies that take into account various factors to understand the precise causes and impacts of particulate matter are actively being pursued. This paper trains an LSTM model using seasonal data and another LSTM model using concentration-based data. It compares and analyzes the PM_2.5 prediction performance of the two models. To train the model, weather data and air pollutant data were collected. The collected data was then used to confirm the correlation with PM_2.5. Based on the results of the correlation analysis, the data was structured for training and evaluation. The seasonal prediction model and the concentration-specific prediction model were designed using the LSTM algorithm. The performance of the prediction model was evaluated using accuracy, RMSE, and MAPE. As a result of the performance evaluation, the prediction model learned by concentration had an accuracy of 91.02% in the "bad" range of AQI. And overall, it performed better than the prediction model trained by season.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 1999.10a
• /
• pp.415-417
• /
• 1999

환경연구자들은 대기환경의 개선과 환경기준의 목표달성과 최적 제어기술을 개발하기 위해 각종 모델을 이용하고 있다. 초기 단계에서는 각종 오염인의 배출자료와 기상자료를 이용하여 대기 중 분진의 농도를 추정하는 분산모델 (dispersion model)이 오랜 기간동안 활발하게 이용되어 왔다. 그러나 분산모델은 배출자료의 오차, 수직ㆍ수평적 분산변수의 불확실도, 복잡한 모델 개발에 따른 시간과 비용 등의 문제점을 가지고 있으며, 모델에 포함된 변수에 의해 특성화된 오염원에 대해서만 농도의 추정이 가능하다는 제약점이 있다.(중략)

• Magazine of the Korea Concrete Institute
• /
• v.10 no.1
• /
• pp.10-19
• /
• 1998

• Korean Journal of Remote Sensing
• /
• v.18 no.4
• /
• pp.233-242
• /
• 2002

In this paper, an epipolar model without the ephemeris data is proposed. Also, various epipolar models such as the epipolar geometry of perspective sensor, the one proposed by Gupta and Hartley and the one based on the Orun and Natarajan's sensor model are reviewed and their accuracy are quantitatively analyzed using devised measure. Modeling data from ground control points, ground control points, ephemeris data and independent checking points are selected on SPOT over Taejon and Boryung area and KOMPSAT over Taejon and Nonsan area. Based on the results, the epipolar model of perspective sensor and the one by Gupta and Hartley have the average accuracy within 1 pixel but show high errors in several checking points. The proposed epipolarity model provides better results than that of perspective sensor and by Gupta and Hartley. Also, it shows the accuracy similar to the one based on Orun and Natarajan's sensor model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.359-359
• /
• 2017

하천관리청은 유량변동이 큰 환경에서도 평상시 하천의 기능을 유지하고 안정적인 용수공급이 이루어지도록 하천수 허가관리를 수행하고 있다. 이때, 하천수 사용허가 검토시 기준으로 사용되는 유량은 자연상태의 기준갈수량에서 하천유지유량을 감안하여 적용하고 있는데, 이는 하천유량의 변동에도 최대 용수수요를 만족할 수 있게끔 관리하기 위한 것으로 최대 사용량일 때의 물의 과부족을 계산하여 허가 여부를 결정한다. 본 연구에서는 Park et al.(2016)이 제안한 시기별(홍수기/이수기, 비관개기/관개기 고려) 하천수 사용허가 기준유량 설정방법을 기반으로, 수질오염총량제(Total Maximum Daily Loads, TMDLs)에서 적용하는 안전율(Margin of Safety, MOS)의 개념을 접목하여 허가기준유량의 불확실성을 정량적으로 고려할 수 있는 방법을 제시하였다. 허가기준 유량은 수문모델에 의해 자연상태의 모의유량을 유황분석하여 도출하게 되므로 유량의 연도별 변도성(Margin of Variability, MOV)과 예측모델 매개변수의 불확실성(Margin of Uncertainty, MOU)을 고려하는 Walker Jr.(2003)의 안전율 산정방법을 적용하였다. 본 연구에서는 금호강 유역을 대상으로 시기별 자연유량 산정시 고려한 SWAT 모형결과를 기반으로 하였으며, 모의자료의 변이계수를 산정하여 시간적 변동성에 의한 불확실성을 도출하고 SWAT-CUP모형을 활용하여 모형의 불확실성을 도출하여 안전율을 계산하였다. 단, 기준갈수량이 허가기준유량으로 사용되는 기간(1월 1일~3월 31일)에는 안전율까지 고려할 경우 지나치게 보수적이라고 판단되어 적용에서 제외하였다. 본 연구에서 제안된 불확실성을 고려한 하천수 관리방법론은 시기별 하천수 허가기준유량 설정에 대한 의사결정자들의 판단을 지원하는데 기여함으로써 정책적 활용도를 높일 뿐만아니라 탄력적인 하천유량관리를 위한 기초연구로 활용될 수 있을 것이며, 타 분야 기술과의 융합이라는 점에서도 의의를 가질 수 있을 것으로 생각된다.