• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.397-397
• /
• 2020

가뭄을 전망하는 방법으로는 통계적 방법과 물리적 방법으로 구분할 수 있다. 통계적 방법은 과거의 기상 및 수문현상이 미래에도 재현될 수 있다는 전제하에 미래 가뭄상황을 전망하는 방법이다. 그러나 이 방법은 예측된 결과들이 모두 과거의 경향에 국한됨에 따라 최근에 급변하는 수문기상의 특성을 고려하는데 한계가 있다(Trenberth, 1994). 물리적 방법은 주어진 초기 수문기상조건으로부터 역학적 알고리즘이 탑재된 기상 및 수문모형의 연계모의를 통하여 미래 가뭄을 전망하는 방법으로 모형에 따른 불확실성이 발생할 수 있으나 최근 수문순환의 변화를 예측가능하다는 장점이 있어 활용도가 높다. 본 연구에서는 기상예보자료와 지표수문모형을 연계한 물리적 기반의 수문학적 가뭄전망정보를 산정하고, 활용성을 평가하였다. 기상예보자료는 기상청 현업예보 모델인 GloSea5로부터 생산된 자료를 이용하였으며, 수문학적 가뭄전망을 위해 MSWSI (Modified Surface Water Supply Index)를 활용하였다. 수문학적 가뭄전망정보는 현재의 수문조건이 지속된다는 가정하에 예보선행시간 3개월까지 산정하였다. 2015~16년 기간에 중권역별 가뭄전망정보를 산정하였으며, 전망정보의 예측성은 통계분석을 이용하여 정량적으로 평가하였다. 금회 제시한 연구방법은 현재의 수문조건이 지속될 시 기상예보에 따른 중권역별 수문학적 가뭄을 예측할 수 있다는 점에서 활용성이 높을 것으로 판단된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.593-606
• /
• 2016

Computer simulation is widely used in a variety of computational science and engineering fields, including computational fluid dynamics, nano physics, computational chemistry, structural dynamics, and computer-aided optimal design, to simulate the behavior of a system. As the demand for the accuracy and complexity of the simulation grows, however, the cost of executing the simulation is rapidly increasing. It, therefore, is very important to lower the total execution time of the simulation especially when that simulation makes a huge number of repetitions with varying values of input parameters. In this paper we develop a simulation service system that provides the ability to predict the result of the requested simulation without actual execution for that simulation: by recording and then returning previously obtained or predicted results of that simulation. To achieve the goal of avoiding repetitive simulation, the system provides two main functionalities: (1) storing simulation-result records into database and (2) predicting from the database the result of a requested simulation using statistical machine learning techniques. In our experiments we evaluate the prediction performance of the system using real airfoil simulation result data. Our system on average showed a very low error rate at a minimum of 0.9% for a certain output variable. Using the system any user can receive the predicted outcome of her simulation promptly without actually running it, which would otherwise impose a heavy burden on computing and storage resources.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.415-423
• /
• 2021

Recently, an R-based point time series data validation system has been established for the statistical post processing and improvement of the National Center for AgroMeteorology-Land Atmosphere Modeling Package (NCAM-LAMP) medium-range prediction data. The time series verification system was used to compare the NCAM-LAMP with the AWS observations and GDAPS medium-range prediction model data operated by Korea Meteorological Administration. For this comparison, the model latitude and longitude data closest to the observation station were extracted and a total of nine points were selected. For each point, the characteristics of the model prediction error were obtained by comparing the daily average of the previous prediction data of air temperature, wind speed, and hourly precipitation, and then we tried to improve the next prediction data using Support Vector Machine( SVM) method. For three months from August to October 2017, the SVM method was used to calibrate the predicted time series data for each run. It was found that The SVM-based correction was promising and encouraging for wind speed and precipitation variables than for temperature variable. The correction effect was small in August but considerably increased in September and October. These results indicate that the SVM method can contribute to mitigate the gradual degradation of medium-range predictability as the model boundary data flows into the model interior.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.1078-1090
• /
• 2022

The distribution patterns of battery usage time data per battery level are able to affect the performance of estimating battery remaining time in mobile devices. Outliers may mainly affect the estimation performance of statistical regression methods. In this paper, we propose a software framework that detects and processes outliers to improve the estimation performance of statistical regression methods. The proposed framework first detects outliers that degrade the estimation performance. The proposed framework replaces outliers with smoothed data. The difference between an outlier and its replaced data will be properly distributed into individual data. Finally, individual data are reinforced to improve the estimation performance. The numerical results obtained by experimenting the proposed framework confirmed that it yielded good performance of estimating battery remaining time.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4A
• /
• pp.343-352
• /
• 2010

Recently, many researchers have been carried out to estimate more controlled service life and long-term performance of carbonated concrete structures. Durability analysis and design based on probability have been induced to new concrete structures for design. This paper provides a carbonation prediction model based on the Fick's 1st law of diffusion using statistic data of carbonated concrete structures and the probabilistic analysis of the durability performance has been carried out by using a Bayes' theorem. The influence of concerned design parameters such as $CO_2$ diffusion coefficient, atmospheric $CO_2$ concentration, absorption quantity of $CO_2$ and the degree of hydration was investigated. Using a monitoring data, this model which was based on probabilistic approach was predicted a carbonation depth and a remaining service life at a variety of environmental concrete structures. Form the result, the application method using a realistic carbonation prediction model can be to estimate erosion-open-time, controlled durability and to determine a making decision for suitable repair and maintenance of carbonated concrete structures.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.292-294
• /
• 2004

단백질 상호작용 검출 방법의 발달로 많은 양의 데이터가 산출되고 있고, 이러한 상호작용 데이터의 방대한 양으로 인해 통계적 방법을 이용하여 데이터를 처리함으로서 유용한 지식을 얻을 수 있다 예측한 상호작용 데이터는 첫째, 대량의 데이터를 생산해내므로, 많은 false-positive를 내포하고 있고, 둘째, 예측한 상호작용을 검증시 실험을 하는 방법 외에는 신뢰도를 측정하기가 어렵다는 문제점이 있다. 본 연구에서는 점수 할당시스템을 사용함으로서 예측한 인간 단백질 상호작용 데이터의 false-positive를 줄이고, 각각 상호작용에 점수를 부설함으로서 상호작용 데이터의 신뢰도를 검증하는 방법을 제안하고 있다.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.175-176
• /
• 2007

Radial Basis Function Network (RBFN)을 이용하여 플라즈마 전위의 예측 모델을 개발하였다. RBFN의 예측성능은 Genetic Algorithm (GA)를 이용하여 최적화 하였다. 체계적인 모델링을 위해 통계적인 실험계획법이 적용되었으며, 실험은 반구형 유도 결합형 플라즈마 장비를 이용하여 수행이 되었다. $Cl_2$ 플라즈마에서의 데이터 측정에는 Langmuir probe가 이용되었다. 최적화된 GA-RBFN 모델을 일반 RBFN 모델과 비교하였으며, 15%정도 모델의 예측성능을 향상시켰다.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2749-2751
• /
• 2002

일반화된 회귀 신경망 (GRNN)을 이용하여 플라즈마을 분류하는 새로운 알고리즘을 보고한다. 데이터분포를 통계적인 평균치와 표준편차를 이용하여 특징지었으며, 바이어스 인자을 이용하여 9 종류의 데이터을 발생하였다. 각 데이터에 대하여 GRNN의 학습인자를 최적화하였으며, 모델성능은 예측과 분류 정확도로 나누어 바이어스와 학습인자의 함수로 분석하였다. 바이어스는 모델성능에 상당한 영향을 주었으며, 학습인자와의 상호작용을 통하여 완전 분류를 이루었다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.7
• /
• pp.469-477
• /
• 2009

In mobile systems, energy efficiency is critical to extend battery life. Therefore, power consumption should be taken into account to develop software in addition to performance, Efficient software design in power and performance is possible if accurate power prediction is accomplished during the execution of software, In this paper, power estimation model is developed using statistical analysis, The proposed model analyzes processor behavior Quantitatively using the data of performance monitoring events and power consumption collected by executing various benchmark programs, And then representative hardware events on power consumption are selected using hierarchical clustering, The power prediction model is established by regression analysis in which the selected events are independent variables and power is a response variable, The proposed model is applied to a PXA320 mobile processor based on Intel XScale architecture and shows average estimation error within 4% of the actual measured power consumption of the processor.