• Title/Summary/Keyword: 입력변수선택

Search Result 189, Processing Time 0.03 seconds

Optimization of Ingredient Mixing Ratio for Preparation of Sulgidduk with Saltwort (Salicornia herbacea L.) (함초 첨가 설기떡의 재료 혼합비율의 최적화)

  • Jang, Myung-Sook;Park, Jung-Eun
    • Journal of the Korean Society of Food Science and Nutrition
    • /
    • v.35 no.5
    • /
    • pp.641-648
    • /
    • 2006
  • In an attempt to get basic data for the utilization of saltwort powder (Salicornia herbaceae L.) as a ingredient in the Sulgidduk. D-optimal design of mixture design showed 14 experimental points including 4 replicates for three independent variables. The three independent variables selected for the experiment were water ($13{\sim}18%$), saltwort powder ($2{\sim}6%$), and sugar ($8{\sim}13%$). The optimum responses variables such as color value. texture, and sensory characteristics were evaluated. The compositional and functional properties of test were measured, and these values were applied to the mathematical models. According to the result of measuring probability of the color value, texture and sensory characteristics were respectively and significance was acknowledged (p<0.05). According to the result of F-test, color values (L, a, b), textural properties (gumminess, chewiness) and sensory characteristics (taste, softness) decided linear model, textural property (hardness) and sensory characteristics (color, smell, moistness, overall acceptance) decided quadratic model. A canonical form and trace plot showed that the influence of each ingredient on the mixture final product. An optimum formulation by numerical and graphical methods were similar. Water, saltwort powder, and sugar were 15.2%, 3.0%, and 9.8% respectively by numerical method, and 15.2%, 3.1%, and 9.7% respectively by graphical method.

The First Quantization Parameter Decision Algorithm for the H.264/AVC Encoder (H.264/AVC를 위한 초기 Quantization Parameter 결정 알고리즘)

  • Kwon, Soon-Young;Lee, Sang-Heon;Lee, Dong-Ha
    • Journal of KIISE:Information Networking
    • /
    • v.35 no.3
    • /
    • pp.235-242
    • /
    • 2008
  • To improve video quality and coding efficiency, H.264/AVC adopted an adaptive rate control. But this method has a problem as it cannot predict an accurate quantization parameter(QP) for the first frame. The first QP is decided among four constant values by using encoder input parameters. It does not consider encoding bits, results in significant fluctuation of the image quality and decreases the average quality of the whole coded sequence. In this paper, we propose a new algorithm for the first frame QP decision in the H.264/AVC encoder. The QP is decided by the existing algorithm and the first frame is encoded. According to the encoded bits, the new initial QP is decided. We can predict optimal value because there is a linear relationship between encoded bits and the new initial QP. Next, we re-encode the first frame using the new initial QP. Experimental results show that the proposed algorithm not only achieves better quality than the state of the art algorithm, but also adopts a rate control forthe sequence that was impossible with the existing algorithm. By reducing fluctuation, subjective quality also improved.

Removal of Seabed Multiples in Seismic Reflection Data using Machine Learning (머신러닝을 이용한 탄성파 반사법 자료의 해저면 겹반사 제거)

  • Nam, Ho-Soo;Lim, Bo-Sung;Kweon, Il-Ryong;Kim, Ji-Soo
    • Geophysics and Geophysical Exploration
    • /
    • v.23 no.3
    • /
    • pp.168-177
    • /
    • 2020
  • Seabed multiple reflections (seabed multiples) are the main cause of misinterpretations of primary reflections in both shot gathers and stack sections. Accordingly, seabed multiples need to be suppressed throughout data processing. Conventional model-driven methods, such as prediction-error deconvolution, Radon filtering, and data-driven methods, such as the surface-related multiple elimination technique, have been used to attenuate multiple reflections. However, the vast majority of processing workflows require time-consuming steps when testing and selecting the processing parameters in addition to computational power and skilled data-processing techniques. To attenuate seabed multiples in seismic reflection data, input gathers with seabed multiples and label gathers without seabed multiples were generated via numerical modeling using the Marmousi2 velocity structure. The training data consisted of normal-moveout-corrected common midpoint gathers fed into a U-Net neural network. The well-trained model was found to effectively attenuate the seabed multiples according to the image similarity between the prediction result and the target data, and demonstrated good applicability to field data.

A Performance Analysis by Adjusting Learning Methods in Stock Price Prediction Model Using LSTM (LSTM을 이용한 주가예측 모델의 학습방법에 따른 성능분석)

  • Jung, Jongjin;Kim, Jiyeon
    • Journal of Digital Convergence
    • /
    • v.18 no.11
    • /
    • pp.259-266
    • /
    • 2020
  • Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

Plume Rise and Initial Dilution Determination Reflecting the Density Profile over Entire Water Column (해수 전체 컬럼에서 밀도 분포를 반영한 플룸 상승과 초기 희석도 결정)

    • Journal of Korean Port Research
    • /
    • v.11 no.2
    • /
    • pp.215-230
    • /
    • 1997
  • A number of ocean outfalls are located around coastal area over the United States and discharge primary treated effluent into deep water for efficient wastewater treatment. Two of them, the Sand Island and Honouliuli municipal wastewater outfalls, are located on the south coast of Oahu. There have been growing interests about the plume dynamics around the ocean outfalls since plume discharged from the multiport diffuser may have significant impacts on coastal communities and immediate consequence on public health. Among the studies of plume dynamics performed in the vicinity of both outfalls, Project MB-4 in the Mamala Bay Study recently made with the funding in the $ 9 million amount statistically dealt with the near-field behavior of the plumes at the Sand Island and Honouliuli outfalls. However, Project MB-4 predicted much higher surfacing frequency than the realistic value obtained by model studies by Oceanit Laboratories, Inc.. It is suggested that improvements should be made in the application of the plume model to more simulate the actual discharge characteristics and ocean conditions. In this study, it has been recommended that input parameters in plume models reflect realistic density profile over the entire water column since. in the previous Mamala Bay Study, the density profiles were measured at 5m depth increments extending from 13 to 63 m depth (the density profile on the upper portion of water column was not included, Roberts 1995). It is proved that the density stratification is the important parameter for the submergence of the plume. In this study, as one of the important parameters, plume rise and initial dilution reflecting the density profile over the entire water column have been taken into account for more reliable plume behavior description.

  • PDF

Development of HyGIS-RAS and HMS Model (HyGIS-RAS모형 및 HyGIS-HMS모형의 개발)

  • Han, Kun-Yeun;Kim, Byung-Hyun;Son, Ah-Long;Kim, Tae-Hyung
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2007.05a
    • /
    • pp.1342-1347
    • /
    • 2007
  • 최근 수자원 분야에서 GIS의 활용은 유역의 수리, 수문분석을 위한 모형의 입력자료 생성 및 모의 결과를 가시화, 이에 따른 유역관리 시스템의 구축 등 폭넓게 활용되고 있다. 또한 국가지리정보시스템에 조사를 통해서 수치지형도 및 주제도를 구축, 구축된 자료의 표준화를 실시하고 있는 실정이다. 그러나 수자원 분야에서 GIS를 활용하기 위한 기술은 주로 선진국을 중심으로 발전하여 왔기 때문에 우리의 실정에 맞지 않아 활용측면에 있어 신뢰할 만한 결과를 얻지 못하고 있는 실정이다. 따라서 국내 상황을 고려하면서 수자원이라는 전문분야 적용에 적합한 GIS(HyGIS)를 개발하고 여기에 수리, 수문분석모형을 연계하여 국내 실무분야에 적용함에 있어 편의성과 실용성을 구비한 모형개발이 이루어져야 한다. 따라서 본 연구에서는 국내 소프트웨어 GeoMania(HyGIS)에 의한 GIS 정보처리의 자동화를 기반으로 하여 실무에서 활용도가 높은 수문모형인 HEC-HMS 및 HEC-1과 수리모형인 HEC-RAS를 연계 및 통합하기 위해서 HyGIS에서 DLL형태로 제공되도록 하였다. HyGIS에서는 수문학적 DEM 분석 및 공간정보 생성, 선형참조가 가능한 하천 네트워크 생성, 유역 시설물 관리 등의 기능을 제공하며 COM(Component Object Model)을 기반으로 개발된 시스템으로 다른 소스로부터 개발된 컴포넌트를 연계하여 시스템의 기능 확장을 손쉽게 수행할 수 있도록 하였을 뿐만 아니라 공간 DB는 GeoMania의 고유 DB인 GSS를 이용한다. HyGIS-HMS는 HyGIS를 통한 국내 유역의 지리정보를 활용하여 HEC-HMS 뿐만 아니라 HEC-1을 추가하여 사용자의 기호와 편의에 따라 모형을 선택할 수 있도록 하였으며 HEC-1의 결과를 가시화하기 위해서 챠트 기능을 추가하였으며 매개변수를 자동으로 산정할 수 있도록 시스템을 구축하였다. HyGIS-RAS는 국내 하천유역에 대해서 기구축 되어있는 하천관리지리정보시스템(RIMGIS)자료를 직접 활용하도록 구성되어있고 자료를 활용하여 제내지와 제외지를 통합하여 TIN분석을 실시하여 범람 홍수해석에 활용할 수 있도록 하였다. 하천수리해석의 기능을 보강하기 위해 역산조도계수 산정모형, 상류-사류 천이류 구간에 대한 부등류 해석모형, 범람 홍수류에 대한 홍수위 산정모형, 하천수리계산시의 불확실도 해석모형 등의 새로운 기능을 추가하여 제시하였다. 모든 입출력자료는 프로젝트 단위별로 운영되어 data의 관리가 손쉽도록 하였으며 결과를 DB에 저장하여 다른 모형에서도 적용할 수 있도록 하였다. 그리고 HyGIS-HMS 및 HyGIS-RAS 모형에서 강우-유출-하도 수리해석-범람해석 등이 일괄되게 하나의 시스템 내에서 구현될 수 있도록 하였다. 따라서 HyGIS와 통합된 수리, 수문모형은 국내 하천 및 유역에 적합한 시스템으로서 향후 HydroInformatics 구현을 염두에 둔 특화된 국내 수자원 분야 소프트웨어의 개발에 기본 토대를 제공할 것으로 판단된다.

  • PDF

An Impact Assessment of Climate and Landuse Change on Water Resources in the Han River (기후변화와 토지피복변화를 고려한 한강 유역의 수자원 영향 평가)

  • Kim, Byung-Sik;Kim, Soo-Jun;Kim, Hung-Soo;Jun, Hwan-Don
    • Journal of Korea Water Resources Association
    • /
    • v.43 no.3
    • /
    • pp.309-323
    • /
    • 2010
  • As climate changes and abnormal climates have drawn research interest recently, many countries utilize the GCM, which is based on SRES suggested by IPCC, to obtain more accurate forecast for future climate changes. Especially, many research attempts have been made to simulate localized geographical characteristics by using RCM with the high resolution data globally. To evaluate the impacts of climate and landuse change on water resources in the Han-river basin, we carried out the procedure consisting of the CA-Markov Chain, the Multi-Regression equation using two independent variables of temperature and rainfall, the downscaling technique based on the RegCM3 RCM, and SLURP. From the CA-Markov Chain, the future landuse change is forecasted and the future NDVI is predicted by the Multi-Regression equation. Also, RegCM3 RCM 50 sets were generated by the downscaling technique based on the RegCM3 RCM provided by KMA. With them, 90 year runoff scenarios whose period is from 2001 to 2090 are simulated for the Han-river basin by SLURP. Finally, the 90-year simulated monthly runoffs are compared with the historical monthly runoffs for each dam in the basin. At Paldang dam, the runoffs in September show higher increase than the ones in August which is due to the change of rainfall pattern in future. Additionally, after exploring the impact of the climate change on the structure of water circulation, we find that water management will become more difficult by the changes in the water circulation factors such as precipitation, evaporation, transpiration, and runoff in the Han-river basin.

FFC2Q Model for NPS Load Analysis according to Characteristics of Early Stage of Runoff (강우 초기특성에 따른 비점오염부하량 산정을 위한 FFC2Q 모형)

  • Lee, Jong-Tae;Seo, Kyung-A;Hur, Sung-Chul
    • Journal of Korea Water Resources Association
    • /
    • v.43 no.3
    • /
    • pp.245-256
    • /
    • 2010
  • We study the basic theory and applicability of the WQUAL block in the FFC2Q model and the characteristics of non-point pollutant loads during the early stage of runoff. Study is also performed on selection of the values of the related parameters and their effect on the simulation results. FFC2Q simulation results are compared for verification with the measured data for three rainfall events in the Gunja Subbasin and found to be similar to the measured data in peak-flows, total runoff volumes, total loads, peak concentrations and times of peak concentration. This model thus shows results very close to those applying the SWMM and MOUSE models, even though it uses simplified input data. Related to rainfall distribution, under the condition of Huff 1st quartile distribution the pollutant loads occurred earlier than under other conditions, and in the early stage of rainfall the BOD and COD loads increased faster than the SS loads. The NPS loads were concentrated in the early stage of rainfall and finally reached total loads, so the rainfall after that could not contribute so much to the NPS loads.

Prediction System for Turbidity Exclusion in Imha Reservoir (임하호 탁수 대응을 위한 예측 시스템)

  • Jeong, Seokil;Choi, Hyun Gu;Kim, Hwa Yeong;Lim, Tae Hwan
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2021.06a
    • /
    • pp.487-487
    • /
    • 2021
  • 탁수는 유기물 또는 무기물이 유입되면서 빛의 투과성이 낮아진 수체를 의미한다. 탁수가 발생하게 되면 어류의 폐사, 정수처리 비용의 증가 및 경관의 변화로 인한 피해가 발생하게 된다. 국내에서는 홍수기 또는 태풍 시 유역의 토사가 저수지 상류에서 유입하여 호내의 탁수를 발생시키는 경우가 있는데, 특히 낙동강 유역의 임하호에서 빈번하게 고탁수가 발생하여 왔다. 본 연구에서는 임하호에서 탁수 발생 시 신속 배제를 위한 수치적인 예측 시스템을 소개하고자 한다. 저수지 탁수관리의 기본개념은 용수공급능력을 고려한 고탁수의 신속한 배제이다. 이는 선제적 의사결정을 요구하므로, 지류에서 탁수가 발생한 즉시 향후 상황에 대한 예측이 필요하다. 이러한 예측을 위해 유역관리처는 3단계의 수치해석을 수행한다. 첫 번째는 유역 상류에서 탁수가 감지되었을 때, 호 내 탁수의 분포를 예측하는 것이다. 수심 및 수평방향의 탁수 분포에 대한 상세한 결과가 도출되어야 하기에, 3차원 수치해석 프로그램인 AEM3D를 이용한다. 이때, 과거 고탁수 유입에 대한 자료를 기반으로 산정된 매개변수가 적용된다. 두 번째는 예측된 호내 분포를 초기조건으로 댐 방류량 및 취수탑 위치(선택배제)에 따른 탁수 배제 수치해석을 수행하게 된다. 다양하고 많은 case에 대한 신속한 모의 및 3달 이상의 장기간 예측을 요구하므로, 2차원 수치모델인 CE-QUAL-W2를 활용한다. 이 단계에서 수자원의 안정적 공급이 가능한 범위 내에서 효과적인 탁수 배제 방류 방법 등이 결정되며, 방류 탁도가 예측된다. 세 번째 단계는 방류탁도를 경계조건으로 하여 하류 하천(반변천~내성천 합류 전)의 탁도를 예측하는 것이다. 하천의 탁도 예측은 국내뿐만 아니라 국외에서도 그 사례를 찾아보기가 쉽지 않은데, 이는 중소형의 지류에 대한 입력자료가 충분하지 않고 불확실성이 높기 때문이다. 이에 과거 10여 년의 data를 이용한 회귀분석을 통해 탁수 발생물질(SS)-부유사-유량과의 관계를 도출하고, 2차원 하천모델(EFDC)을 이용하여 수심 평균 탁도를 예측하게 된다. 이러한 세 단계의 예측은 탁수가 호내로 유입됨에 따라 반복되고, 점차 예측 정확도가 향상되게 된다. 세 단계의 과정을 통한 임하호 탁수의 조기 배제는 현재 적지 않은 효과를 거두고 있다고 판단된다. 그러나 탁수를 발생시키는 현탁물질의 종류는 매번 일정하지 않기 때문에, 이러한 예측 시스템에 정확도에 영향을 줄 수 있으므로, 여러 상황을 고려한 딥러닝을 도입하여 탁수 물질에 대한 정보를 예측한다면 보다 합리적인 의사결정 지원 도구가 될 수 있을 것이다.

  • PDF

Estimation of Reference Crop Evapotranspiration Using Backpropagation Neural Network Model (역전파 신경망 모델을 이용한 기준 작물 증발산량 산정)

  • Kim, Minyoung;Choi, Yonghun;O'Shaughnessy, Susan;Colaizzi, Paul;Kim, Youngjin;Jeon, Jonggil;Lee, Sangbong
    • Journal of The Korean Society of Agricultural Engineers
    • /
    • v.61 no.6
    • /
    • pp.111-121
    • /
    • 2019
  • Evapotranspiration (ET) of vegetation is one of the major components of the hydrologic cycle, and its accurate estimation is important for hydrologic water balance, irrigation management, crop yield simulation, and water resources planning and management. For agricultural crops, ET is often calculated in terms of a short or tall crop reference, such as well-watered, clipped grass (reference crop evapotranspiration, $ET_o$). The Penman-Monteith equation recommended by FAO (FAO 56-PM) has been accepted by researchers and practitioners, as the sole $ET_o$ method. However, its accuracy is contingent on high quality measurements of four meteorological variables, and its use has been limited by incomplete and/or inaccurate input data. Therefore, this study evaluated the applicability of Backpropagation Neural Network (BPNN) model for estimating $ET_o$ from less meteorological data than required by the FAO 56-PM. A total of six meteorological inputs, minimum temperature, average temperature, maximum temperature, relative humidity, wind speed and solar radiation, were divided into a series of input groups (a combination of one, two, three, four, five and six variables) and each combination of different meteorological dataset was evaluated for its level of accuracy in estimating $ET_o$. The overall findings of this study indicated that $ET_o$ could be reasonably estimated using less than all six meteorological data using BPNN. In addition, it was shown that the proper choice of neural network architecture could not only minimize the computational error, but also maximize the relationship between dependent and independent variables. The findings of this study would be of use in instances where data availability and/or accuracy are limited.