• Journal of Korea Water Resources Association
• /
• v.41 no.10
• /
• pp.995-1007
• /
• 2008

Studies on modeling the rainfall-runoff relationship which shows nonlinear trend strongly use artificial neural networks theory not only for the prediction but also for the characteristics analysis of the data used by pattern classification. For the pattern classification, the results from Self-Organizing Map (SOM) mention that the map size and array for the SOM training have significantly influenced on the SOM performance. Since there is no deterministic method or theoretical equation to determine the number of rows and columns for the map size, hexagonal array is generally used for the map array. Therefore, this study present a determination of the optimized map structure for the rainfall-runoff analysis in Naju station considering the map size and array simultaneously which can represent the classified characterization of rainfall-runoff relationship. The result showed that the map size of 20$\times$16 hexagonal array with 8-clustered patterns was selected as an appropriate map structure for rainfall-runoff analysis in Naju station.

• Radiation Oncology Journal
• /
• v.7 no.2
• /
• pp.171-183
• /
• 1989

A general effect for cell proliferation has been incorporated into Roesch's survival equation (Accumulation Model). From this an isoeffect formula for the low dose-rate regimen is obtained. The prediction for total doses equivalent to 60Gy delivered at the constant dose-rate over 7 days agrees well with the dose-time data of Paterson and of Green, when the parameter ratio A/B (${\approx}{\alpha{\mu}}/2{\beta}\;where\;{\mu}$ is the repair rate) is chosen to be 0.7Gy/h. When a constant proliferation rate and known facts of division delay are assumed, an isoeffect relation between low dose-rate treatment and acute dose-rate treatment can be derived. This formula in the regimens where proliferation is negligible predicts exactly the data of Ellis that 8 fractions of 5 Gy/day for 7 days are equivalent to continuously applied 60Gy over 7days, provided the A/B ratio is 0.7 Gy/h and the $\alpha/\beta$ ratio is 4Gy. Overall agreement between the clinical data and the predictions made by the formula at the above parameter values suggests that the biologcal end points used as the tolerance level in the studies by Paterson, Green, and Ellis all agree and they are not entirely the early effects as generally assumed. The absence of dose-rate effects observed in the mouse KHT sarcoma can better be explained in terms of a large value for the A/B ratio. Similarly, the same total dose used independently of the dose-rate to treat head and neck tumors by Pierquin can be justified.

• Korean Journal of Weed Science
• /
• v.31 no.4
• /
• pp.340-347
• /
• 2011

This study was conducted to predict the rice yield loss and to determine the economic threshold levels for direct-seeding flooded rice cultivation from competition to the most serious weeds, Sagittaria trifolia L. and Bidens frondosa L. The rice yield loss models of S. trifolia and B. frondosa were predicted as Y = 497.0/(1+0.003760x), $R^2$=0.869 and Y = 486.0/(1+0.007612x), $R^2$ = 0.887, respectively. In comparison of the competitiveness represented by parameter ${\beta}$, it was 0.003760 in S. trifolia and 0.007612 in B. frondosa, respectively. Economic thresholds calculated using Cousens' equation was negatively related with the competitiveness of weed. The economic thresholds of S. trifolia and B. frondosa were 7.6 and 3.9 plants per $m^2$, respectively.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.8
• /
• pp.765-770
• /
• 2017

GTD111 DS of nickel base superalloy has been used for gas turbine blades. In this study, low cycle fatigue test was conducted on the GTD111 DS alloy by setting conditions similar to the real operating environment. The low cycle fatigue tests were conducted at room temperature, $760^{\circ}C$, $870^{\circ}C$, and various strain amplitudes. Test results showed that fatigue life decreased with increasing total strain amplitude. Cyclic hardening response was observed at room temperature and $760^{\circ}C$; however, tests conducted at $870^{\circ}C$ showed cyclic softening response. Stress relaxation was observed at $870^{\circ}C$ because creep effects occurred from holding time. A relationship between fatigue life and total strain range was obtained from the Coffin-Manson method. The fratography using a SEM was carried out at the crack initiation and propagation regions.

• Journal of Advanced Navigation Technology
• /
• v.17 no.5
• /
• pp.516-523
• /
• 2013

In this paper, The path loss model of Air Traffic Control(ATC) telecommunication radio channel has been studied at the Incheon International Airport(IIA) with the terminal with two antlers. We measured two frequencies among VHF/UHF channel bands. The transmitting site radiated the Continuous Wave(CW). The propagation measurement was taken using the moving vehicle equipped with receiver and antenna. The transmitting power, frequency and antenna height are the same as the current operating condition. The path loss exponent and intercept parameters were extracted by the basic path loss model and hata model. The path loss exponents at passager terminal areas were 3.32 and 3.10 respectively in 128.2 MHz and 269.1 MHz. The deviation of prediction error is 9.69 and 9.65. The new path loss equation at the terminal area was also developed using the derived path loss parameters. The new path loss was compared with other models. This result will be helpful for the ATC site selection and service quality evaluation.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1261-1269
• /
• 1999

다층 퍼셉트론은 다양한 응용 분야에 성공적으로 적용되고 있는 대표적인 신경회로망 모델이다. 그러나 다층 퍼셉트론의 학습에서 나타나는 플라토에 기인한 느린 학습 속도와 지역 극소는 실제 응용문제에 적용함에 있어서 가장 큰 문제로 지적되어왔다. 이 문제를 해결하기 위해 여러 가지 다양한 학습알고리즘들이 개발되어 왔으나, 계산의 비효율성으로 인해 실제 문제에는 적용하기 힘든 예가 많은 등, 현재까지 만족할 만한 해결책은 제시되지 못하고 있다. 본 논문에서는 다층퍼셉트론의 베이시스 함수로 사용되는 시그모이드 함수를 보다 일반화된 형태로 정의하여 사용함으로써 학습에 있어서의 플라토를 완화하고, 지역극소에 빠지는 것을 줄이는 접근방법을 소개한다. 본 방법은 기존의 변형된 가중치 수정식을 사용한 학습 속도 향상의 방법들과는 다른 접근 방법을 택함으로써 기존의 방법들과 함께 사용하는 것이 가능하다는 특징을 갖고 있다. 제안하는 방법의 성능을 확인하기 위하여 간단한 패턴 인식 문제들에의 적용 실험 및 기존의 학습 속도 향상 방법을 함께 사용하여 시계열 예측 문제에 적용한 실험을 수행하였고, 그 결과로부터 제안안 방법의 효율성을 확인할 수 있었다. Abstract A multilayer perceptron is the most well-known neural network model which has been successfully applied to various fields of application. Its slow learning caused by plateau and local minima of gradient descent learning, however, have been pointed as the biggest problems in its practical use. To solve such a problem, a number of researches on learning algorithms have been conducted, but it can be said that none of satisfying solutions have been presented so far because the problems such as computational inefficiency have still been existed in these algorithms. In this paper, we propose a new learning approach to minimize the effect of plateau and reduce the possibility of getting trapped in local minima by generalizing the sigmoidal function which is used as the basis function of a multilayer perceptron. Adapting a new approach that differs from the conventional methods with revised updating equation, the proposed method can be used together with the existing methods to improve the learning performance. We conducted some experiments to test the proposed method on simple problems of pattern recognition and a problem of time series prediction, compared our results with the results of the existing methods, and confirmed that the proposed method is efficient enough to apply to the real problems.

• Journal of the Korean Society for Railway
• /
• v.17 no.5
• /
• pp.328-335
• /
• 2014

Numerical prediction methods were applied to investigate the turbulent air currents and air-conditioning efficiency in an underground subway station, and the results compared to experimental data. The Shin-gumho Station($8^{th}$ floor underground and 43.6m in depth) in Seoul was selected for the analysis. The entire station was covered for simulation and the ventilation mode was ordinary. The ventilation diffusers were modeled as 95 square shapes of $0.6m{\times}0.6m$ in the lobby and as 222 square shapes in the platform. Cooling air of $47,316m^3/h$ was supplied and the returned air of $33,980m^3/h$ is exhausted in the lobby and the cooling air of $33,968m^3/h$ is supplied and the returned air of $76,190m^3/h$ was exhausted in the platform which is the same as the experimental data. The cases of the screen-door-closed and open were respectively investigated. A total of 7.5million grids were generated and the whole domain divided into 22 blocks for MPI efficiency of calculation. Large eddy simulation (LES) was applied to solve the momentum and energy equation.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.7 no.2
• /
• pp.109-115
• /
• 2019

In case of the cracks in concrete, the penetration of deterioration ions such as chloride ions in to cracks is accelerated. According to the penetration of chloride ions, structural and durability problems to RC(Reinforced Concrete) structures are caused. In this study, the accelerated chloride diffusion coefficient which is in steady state is evaluated for 2 year aged normal and high strength FA(Fly Ash) concrete, after a range of crack depths are induced up to 1.0 mm in 56 aged day. Considering crack effect by linear regression analysis, high strength concrete has slightly less increasing ratio of diffusion coefficient by crack than normal strength concrete, and diffusion coefficient increases non-linearly as crack width is increased. Also, In two types of concrete, crack effect decrease as the curing period increase. In the case of quantifying crack and curing effect by using exponential function form, the coefficients of determination are higher than those of linear regression analysis. Under steady state, it is thought that there is not a high correlation between the crack effect and the curing effect, and considering the two independent effects, it is believed that reasonable prediction equation for diffusion of concrete with crack can be proposed.

• The Journal of the Korea Contents Association
• /
• v.19 no.5
• /
• pp.104-114
• /
• 2019

In the global market competition, countries and businesses are actively engaged in technology prediction activities to maximize their profits by attempting to enter and preempting the core technology of the future. In this paper, we propose a growth model based on patent application trends to predict the time to replace a product with a promising new technology to dominate the market. Although the Fisher-Pry model that Bhargava generalized to predict the emergence of promising alternative technologies was relatively satisfactory compared to the original Fisher-Pry model, it was difficult to predict the replacement rate behavior properly due to a parameter problem. The application of the Fisher-Pry Modification Model in the form of a quadratic equation through the patent trend analysis of the optical storage system for the purpose of verifying the time alternative to the light storage technology has resulted in satisfactory verification results. It is expected that small and medium-sized companies and individual researchers will apply this model and use it more easily to predict the time to replace the market for promising replacement technologies.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.2
• /
• pp.93-101
• /
• 2019

The objective of this study is to develop a model which can predict the seismic performance of the slope relatively accurately and efficiently by using artificial neural network(ANN) technique. The quantification of such the seismic performance of the slope is not easy task due to the randomness and the uncertainty of the earthquake input and slope model. Under these circumstances, probabilistic seismic fragility analyses of slope have been carried out by several researchers, and a closed-form equation for slope seismic performance was proposed through a multiple linear regression analysis. However, a traditional statistical linear regression analysis has shown a limit that cannot accurately represent the nonlinearistic relationship between the slope of various conditions and seismic performance. In order to overcome these problems, in this study, we attempted to apply the ANN to generate prediction models of the seismic performance of the slope. The validity of the derived model was verified by comparing this with the conventional multi-linear and multi-nonlinear regression models. As a result, the models obtained through the ANN basically showed excellent performance in predicting the seismic performance of the slope, compared to the models obtained by the statistical regression analyses of the previous study.