• Journal of the Korean Data and Information Science Society
• /
• 제18권4호
• /
• pp.1033-1043
• /
• 2007

The multi layer perceptron for segmenting objects in images only uses the input windows that are made from a image in a fixed size. These windows are recognized so each independent learning data that they make the performance of the multi layer perceptron poor. The poor performance is caused by not considering the position information and effect of input windows in input images. So we propose a new approach to add the position information and effect of input windows to the multi layer perceptron#s input layer. Our new approach improves the performance as well as the learning time in the multi layer perceptron. In our experiment, we can find our new algorithm good.

• 한국농공학회지
• /
• 제39권1호
• /
• pp.41-47
• /
• 1997

A geographical resource analysis support system (GRASS) was incorporated to an input and output processor for the agricultural nonpoint source pollution (AGNPS) model. The resulting interface system, GIS-AGNPS was a user-friendly, menu-driven system. GIS-AGNPS was developed to automatically process the input and output data from GIS-based data using GRASS and Motif routines. GIS-AGNPS was consisted of GISAGIN which was an input processor for the AGNPS model, GISAGOUT a output processor for the AGNPS and management submodel. The system defines an input data set for AGNPS from attributes of basic and thematic maps. It also provides with editing modes so that users can adjust and detail the values for selected input parameters, if needed. The post-processor at the system displays graphically the outputs from AGNPS, which may he used to identify areas significantly contributing nonpoint source pollution loads.

• 한국유기농업학회지
• /
• 제26권4호
• /
• pp.619-628
• /
• 2018

This study analyze the economic effect of chemical fertilizer. We used the input and output data, and the analysis variables include production output nitrogen, phosphoric acid, potassium, seeds, and labor. The main results are as follows. First, for spring potatoes, potassium increases to a certain level of output, but over a certain stage, the output decreases as the input increases. Optimal use of potassium in the calculation of spring potatoes can achieve the effect of reducing input costs and increasing output simultaneously. Second, radish In autumn, nitrogen increases to a certain level, but over a certain stage it represents a reverse U-shaped relationship in which output decreases as input increases. This means that reducing the amount of fertilizer input increases the output. This means that soil-related agricultural big data can contribute to the management of nutrients and greenhouse gas reduction in agricultural land.

• 자원환경지질
• /
• 제56권6호
• /
• pp.887-897
• /
• 2023

스웨덴, 스위스, 영국 등 폐기물 처분 선도국들은 고준위방사성폐기물 심층처분시설의 계획, 부지선정, 건설, 운영, 폐쇄, 그리고 폐쇄 후 관리 전 단계에서 안전성평가를 수행하고 있다. 안전성평가는 각 단계에서 반복적으로 이루어지며, 장기간에 걸쳐 다양하고 방대한 양의 데이터를 생성하므로, 안전성평가 자료를 위한 데이터베이스를 구축하고 효과적으로 관리하기 위한 자료관리체계를 구축하는 것이 필수적이다. 본 연구에서는 폐기물 처분 분야에서 선도적인 국가의 안전성평가 자료관리체계를 1) 안전성평가 입력 및 참조자료, 2) 자료관리 지침, 3) 자료관리 조직, 그리고 4) 자료관리 전산시스템으로 구분하여 분석하였다. 각 국가는 특정 부분에서는 차이를 보였지만, 안전성평가 입력자료를 처분 시스템 구성 요소를 기반으로 분류하고, 이를 제공, 사용, 관리하는 조직을 설립하며, 지침 및 매뉴얼에 따라 품질관리 체계를 구현하는 등 공통적인 특성을 보이고 있다. 이러한 사례들은 고준위방사성폐기물 처분시설의 안전성을 확보하고 신뢰성을 향상시키기 위해 효과적으로 데이터 관리 시스템과 문서 관리 시스템을 구축하는 것이 중요하다는 것을 시사한다. 이를 위해서는 유연하게 활용 가능한 입력자료의 분류, 입력자료의 일관성과 추적성 보장, 그리고 입력자료와 문서관리를 위한 품질관리 체계를 수립하는 것이 필요하다.

• 산업기술연구
• /
• 제35권
• /
• pp.95-102
• /
• 2015

Two extreme wind speed prediction models, the EWM(Extreme wind speed model) in IEC61400-1 and the Gumbel method were compared in this study. The two models were used to predict extreme wind speeds of six different sites in Korea and the results were compared with long term wind data. The NCAR reanalysis data were used for inputs to two models. Various periods of input wind data were tried from 1 year to 50 years and the results were compared with the 50 year maximum wind speed of NCAR wind data. It was found that the EWM model underpredicted the extreme wind speed more than 5 % for two sites. Predictions from Gumbel method overpredicted the extreme wind speed or underpredicted it less than 5 % for all cases when the period of the input data is longer than 10 years. The period of the input wind data less than 3 years resulted in large prediction errors for Gumbel method. Predictions from the EWM model were not, however, much affected by the period of the input wind data.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2002년도 학술발표회 논문집(II)
• /
• pp.1179-1186
• /
• 2002

Macro scale distributed hydrological models simulate river discharge with better accuracy but it depends upon the grid resolution of input data. Effects of different input resolutions are studied here. Three different grid resolution input data obtained from HUBEX-IOP EEWB data and GAME Re-analysis data are used to simulate river discharge and compared against the observed one. CAME Re-analysis 1.25-degree resolution data are found quite satisfactory in larger basins, while HUBEX-IOP EEWB 10-minute resolution data are better for small catchments. GAME Re-analysis 2.5-degree resolution data did not give good result. Simulated results by using spatially interpolated data are rather worse than using original data. The Huaihe River basin $(132350\textrm{km}^2)$ is taken as the case of study.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.77-82
• /
• 2020

IoT devices frequently require input resources to communicate with various sensors or IoT platforms. IoT device wastes a lot of time as idle time or waiting time to check the data of the input resource and use the input resource. In addition, IoT devices use various input resources. We compares and analyzes input idle time and input waiting time generated from hardware serial input resource, software serial input resource, digital port input resource, and analog port input resource using Arduino widely used as IoT device. In order to design the IoT device framework, it is necessary to understand the characteristics of input resources and to design them to minimize unnecessary input idle time and input waiting time. The analog input wait time has a much larger input wait time than the digital input wait time, so it must be designed to receive analog information periodically at the appropriate timing. The characteristics of the input resources analyzed in this way help to design an efficient IoT device.

• 전기학회논문지
• /
• 제67권4호
• /
• pp.569-577
• /
• 2018

In this paper, with the aid of information which is included within data, preprocessing algorithm-based black plastic classifier is designed. The slope and area of spectrum obtained by using laser induced breakdown spectroscopy(LIBS) are analyzed for each material and its ensuing information is applied as the input data of the proposed classifier. The slope is represented by the rate of change of wavelength and intensity. Also, the area is calculated by the wavelength of the spectrum peak where the material property of chemical elements such as carbon and hydrogen appears. Using informations such as slope and area, input data of the proposed classifier is constructed. In the preprocessing part of the classifier, Principal Component Analysis(PCA) and fuzzy transform are used for dimensional reduction from high dimensional input variables to low dimensional input variables. Characteristic analysis of the materials as well as the processing speed of the classifier is improved. In the condition part, FCM clustering is applied and linear function is used as connection weight in the conclusion part. By means of Particle Swarm Optimization(PSO), parameters such as the number of clusters, fuzzification coefficient and the number of input variables are optimized. To demonstrate the superiority of classification performance, classification rate is compared by using WEKA 3.8 data mining software which contains various classifiers such as Naivebayes, SVM and Multilayer perceptron.

• 대한산업공학회지
• /
• 제36권3호
• /
• pp.154-163
• /
• 2010

Process monitoring of output variables affecting final performance have been mainly executed in semiconductor manufacturing process. However, even earlier detection of causes of output variation cannot completely prevent yield loss because a number of wafers after detecting them must be re-processed or cast away. Semiconductor manufacturers have put more attention toward monitoring process inputs to prevent yield loss by early detecting change-point of the process. In the paper, we propose the method to efficiently monitor functional input variables in multi-phase semiconductor manufacturing process. Measured input variables in the multi-phase process tend to be of functional structured form. After data pre-processing for these functional input data, change-point analysis is practiced to the pre-processed data set. If process variation occurs, key variables affecting process variation are selected using contribution plot for monitoring efficiency. To evaluate the propriety of proposed monitoring method, we used real data set in semiconductor manufacturing process. The experiment shows that the proposed method has better performance than previous output monitoring method in terms of fault detection and process monitoring.

• 디지털융복합연구
• /
• 제12권4호
• /
• pp.277-283
• /
• 2014

퍼지모델링은 일반적으로 주어진 데이터를 이용하고 퍼지규칙은 입력변수를 선정하고 각 입력변수에 대한 입력공간을 분할함으로써 입력변수 및 공간분할에 의해 확립된다. 퍼지규칙의 전반부는 입력변수, 공간분할 수 및 소속 함수를 선정하고 본 논문에서 후반부는 선형추론 및 변형된 이차식에 의해 다항식함수의 형태로 나타낸다. 전반부 파라미터의 동정은 입출력 데이터의 최소값과 최대값을 이용하는 최소-최대 방법 및 입출력 데이터를 군집으로 형성하는 C-Means 클러스터링 알고리즘을 사용하여 입력공간을 분할한다. 각 규칙의 후반부 파라미터들, 즉 다항식의 계수들의 동정은 표준최소자승법에 의해 수행된다. 본 논문에서 전반부 소속 함수는 사다리꼴형 멤버쉽 함수를 사용하여 입력공간을 분할하고 비선형공정에서 널리 이용되는 가스로데이터를 사용하여 성능을 평가한다.