• 한국소음진동공학회논문집
• /
• 제16권8호
• /
• pp.806-813
• /
• 2006

An important factor of vibration test using MAST(multi axial simulation table) system is the reliance of input excitation source. Generally the generation of input excitation source is obtained by the measured data on special road in proving ground. The measured data on special road have more exciting energy than the data of real fields, therefore the time and expense for test can be reduced. But the magnitude of input excitation source must be defined by comparison with the excited energy on real field. The object of this paper makes the data base of domestic roads for the definition of input excitation source which is obtained by the measured data on special road in proving ground. These real field data on domestic roads are analyzed by the power spectral density and interrelationship index.

• The Plant Pathology Journal
• /
• 제38권4호
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• 한국수자원학회논문집
• /
• 제44권7호
• /
• pp.523-536
• /
• 2011

본 연구의 목적은 중소하천에서의 홍수예측을 위해 사용되는 기존의 수문학적 모형이 가지고 있는 문제점을 개선한 홍수예측 모형을 개발하는데 있다. 이를 위해 기존의 수문학적 강우-유출 모형에서 사용되는 많은 수문학적 자료 및 매개변수들의 사용 없이 오직 수위 및 강우측정 자료만을 이용하여 홍수를 예측할 수 있는 Takagi-Sugeno 퍼지 추론기법과 신경망을 연계한뉴로-퍼지홍수예측 모형을 구축하고자 하였다. 뉴로-퍼지 홍수예측 모형의 예측정확도는 입력자료로 사용되는 강우와 수위 자료의 시간적 분포 및 자료의 수에 의해 결정된다. 따라서 본 연구에서는 홍수예측 모형 구축을 위한 최적 입력 자료 조합 선정을 위해 다양한 강우와 수위의 입력자료 조합을 구성하여 적용하였고, 이를 통해 홍수 예측을 위한 뉴러-퍼지 홍수예측 모형의 최적 입력 자료 조합을 선정하였다.

• 한국환경과학회지
• /
• 제24권7호
• /
• pp.865-874
• /
• 2015

This study was conducted to investigate the correlation between the distribution chart and input data of the predicted 3-second gust and damage cost, by using the forecast field and analysis field of Regional Data Assimilation Prediction System (RDAPS) as initial input data of Korea risk assessment model (RAM) developed in the preceding study. In this study the cases of typhoon Rusa which caused occurred great damage to the Korean peninsula was analyzed to assess the suitability of initial input data. As a result, this study has found out that the distribution chart from the forecast field and analysis field predicted from the point where the effect due to the typhoon began had similarity in both 3-second gust and damage cost with the course of time. As a result of examining the correlation, the 3-second gust had over 0.8, and it means that the forecast field and analysis field show similar results. This study has shown that utilizing the forecast field as initial input data of Korea RAM could suit the purpose of pre-disaster prevention.

• 전자공학회논문지SC
• /
• 제39권3호
• /
• pp.220-227
• /
• 2002

프랙탈 영상압축의 고속처리를 위한 일차원 VLSI 어레이를 설계하였다. 기존의 제안된 일차원 VLSI 어레이에서 중첩되는 이웃의 정의역블럭의 데이터들을 재사용하므로서 전체 연산에 필요한 데이터의 총입력 횟수를 감소시키고, 이로 인한 전체 처리시간을 줄였다. 어레이로 입력되는 데이터의존관계를 고려하여, 입력순서가 적절히 조정되었으며, 이에 따라 처리요소들을 설계하였다. 몇몇 처리요소에는 데이터의 저장 및 경로설정을 위한 레지스터와 멀티플렉서들이 추가되었다. 따라서 영상의 크기가 N이고 블럭의 크기가 B인 경우, 이 설계는 적은 하드웨어를 추가하여 기존의 어레이보다 처리속도가 (N-4B)/4(N-B)배 향상되었다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 춘계학술대회 논문집
• /
• pp.182-187
• /
• 2007

The accuracy of the results of the rail vehicle dynamic model is dependent on the realism of the track input to the model. An important part of the track input is the irregularities that exist on actual track. This study presents a modeling method for creating track data with the irregularities for use as the input to VAMPIRE, a rail vehicle dynamic analysis program. The characteristics of the measured track data using the mid chord system has been studied and examined the method to create track data with the measured data to apply in the vehicle dynamic analysis.

• 대한산업공학회지
• /
• 제18권1호
• /
• pp.63-80
• /
• 1992

The concept of rapid prototyping intended for a significant reduction in cost and lead time becomes even more practical with the recent development of various equipments to make the concept concrete. For the purpose of real application of commercially available SLA(stereolithography apparatus), this paper is intended to develop the standard conversion procedure from CAD data to the input data for SLA. While the procedure presented in this paper is based on CAD system "CATIA" and SLA of 3D systems, Inc., which are being used in authors' company DAEWOO Motor Co., Ltd., the basic concept of this paper can be applied to any other CAD systems and machines of using stereolithography process. The algorithm presented in this paper is classified into two stages-node sampling and triangulation. First of all, point data are sampled through the node sampling procedure, and then these are triangulated so that the input data for SLA operation is finally generated. The suggested method is devised in a way to meet the input requirements of SLA and more importantly consume less computation time and generate less number of input data for SLA.

• 기술혁신연구
• /
• 제7권1호
• /
• pp.176-186
• /
• 1999

This paper starts out by reviewing the literature that in different ways utilizes patent data as an output of Research ＆ Development (R&D) investment. The main focus, however, is an analysis of time-lag between industrial R&D input and its output. To achieve this research's purpose, the basic data associated with the industrial R&D input (expenditure, researchers) and output (applied patent and utilities) for the past 15 years, from 1980 to 1994, in the areas of electrical-electronic, mechanical and chemical industries have been collected. And the raw input data were altered into real flow data (but stock data) using Laspeyres approach and analyzed using multiple regression analysis, especially stepwise regression analysis. The result of this study can be summarized as follows: a) The time-lag; between industrial R&D input and its output is within 1 to 3 years. b) The time-lag: of patents was longer than that of utility models. c) The time-lag: in electrical-electronic, chemical industry was longer than that of the mechanical industry.

• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.99-111
• /
• 2022

불확실성과 복잡성이 존재하는 제조시스템의 생산성 분석과 의사결정을 위하여 시뮬레이션 기법이 활용될 수 있다. 이러한 시스템의 시뮬레이션을 위해 대상의 특성을 반영하는 입력 모델링 과정이 필요하다. 하지만 건설기계 조립라인과 같은 수작업 중심과 긴 리드타임을 가지는 복잡한 환경에서는 시뮬레이션에 활용할 데이터의 수집이 제한된다. 본 연구는 입력 데이터의 수집이 어려운 환경에서 동영상 데이터를 이용한 시뮬레이션 입력 모델링 절차를 제안한다. 동영상 데이터 기반 작업분석을 통해 측정시간을 정미시간과 표준시간으로 산정하고, 시뮬레이션의 입력 분포로 활용할 수 있다. 제안하는 절차로 산정된 확률분포를 시뮬레이션에 이용하여 대상 시스템의 주요 생산성 지표를 분석하였다. 본 연구에서 제안하는 절차는 데이터가 적은 상황에서 시뮬레이션을 활용한 생산성 분석으로 의사결정 보조에 도움을 줄 것으로 기대된다.

• 대한산업공학회지
• /
• 제27권1호
• /
• pp.47-53
• /
• 2001

In this paper, we compare the classification performances of both ensemble and clustering algorithms (Data Bagging, Variable Selection Bagging, Parameter Combining, Clustering) to logistic regression in consideration of various characteristics of input data. Four factors used to simulate the logistic model are (1) correlation among input variables (2) variance of observation (3) training data size and (4) input-output function. In view of the unknown relationship between input and output function, we use a Taguchi design to improve the practicality of our study results by letting it as a noise factor. Experimental study results indicate the following: When the level of the variance is medium, Bagging & Parameter Combining performs worse than Logistic Regression, Variable Selection Bagging and Clustering. However, classification performances of Logistic Regression, Variable Selection Bagging, Bagging and Clustering are not significantly different when the variance of input data is either small or large. When there is strong correlation in input variables, Variable Selection Bagging outperforms both Logistic Regression and Parameter combining. In general, Parameter Combining algorithm appears to be the worst at our disappointment.