• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2016년도 학술발표회
• /
• pp.259-259
• /
• 2016

This study examined Artificial Neurons Networks model (ANNs) for forecast flash discharge at Southern part of Thailand by using rainfall data and discharge data. The Sungai Kolok River Basin has meant the border crossing between Thailand and Malaysia which watershed drains an area lies in Thailand 691.88 square kilometer from over all 2,175 square kilometer. The river originates in mountainous area of Waeng district then flow through Gulf of Thailand at Narathiwat Province, which the river length is approximately 103 kilometers. Almost every year, flooding seems to have increased in frequency and magnitude which is highly non-linear and complicated phenomena. The purpose of this study is to forecast runoff on Sungai Kolok at X.119A gauge station (Sungai Kolok district, Narathiwat province) for 3 days in advance by using Artificial Neural Networks model (ANNs). 3 daily rainfall stations and 2 daily runoff station have been measured by Royal Irrigation Department and Meteorological Department during flood period 2000-2014 were used as input data. In order to check an accuracy of forecasting, forecasted runoff were compared with observed data by pursuing Coefficient of determination ($R^2$). The result of the first day gets the highest accuracy and then decreased in day 2 and day 3, consequently. $R^2$values for first day, second day and third day of runoff forecasting is 0.71, 0.62 and 0.49 respectively. The results confirmed that the ANNs model can be used when the range of collected dataset is short and real-time operated. In conclusion, the ANNs model is suitable to runoff forecasting during flood incident of Sungai Kolok river because it is straightforward model and require with only a few parameters for simulation.

• Steel and Composite Structures
• /
• 제14권4호
• /
• pp.367-377
• /
• 2013

Damage in structures often leads to failure. Thus it is very important to monitor structures for the occurrence of damage. When damage happens in a structure the consequence is a change in its modal parameters such as natural frequencies and mode shapes. Artificial Neural Networks (ANNs) are inspired by human biological neurons and have been applied for damage identification with varied success. Natural frequencies of a structure have a strong effect on damage and are applied as effective input parameters used to train the ANN in this study. The applicability of ANNs as a powerful tool for predicting the severity of damage in a model steel girder bridge is examined in this study. The data required for the ANNs which are in the form of natural frequencies were obtained from numerical modal analysis. By incorporating the training data, ANNs are capable of producing outputs in terms of damage severity using the first five natural frequencies. It has been demonstrated that an ANN trained only with natural frequency data can determine the severity of damage with a 6.8% error. The results shows that ANNs trained with numerically obtained samples have a strong potential for structural damage identification.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.398-398
• /
• 2015

To estimate and forecast runoff by using Aritifitial Neaural Networks model (ANNs). it has been studied in Thailand for the past 10 years. The model was developed in order to be conformed with the conditions in which the collected dataset is short and the amount of dataset is inadequate. Every year, the Northerpart of Thailand faces river overflow and flood inundation. The most important basin in this area is Yom basin. The purpose of this study is to forecast runoff at Y.14 gauge station (Si-Satchanalai district, Sukhothai province) for 3 days in advance. This station located at the upstream area of Yom River basin. Daily rainfall and daily runoff from Royal Irrigation Department and Meteorological Department during flood period 2000-2012 were used as input data. In order to check an accuracy of forecasting, forecasted runoff were compared with observed data by pursuing Nash Sutcliffe Efficiency (NSE) and Coefficient of Determination ($R^2$). The result of the first day gets the highest accuracy and then decreased in day 2 and day 3, consequently. NSE and $R^2$ values for frist day of runoff forecasting is 0.76 and 0.776, respectively. On the second day, those values are 0.61 and 0.65, respectively. For the third day, the aforementioned valves are 0.51 and 0.52, respectively. The results confirmed that the ANNs model can be used when the range of collected dataset is short and insufficient. In conclusion, the ANNs model is suitable for applying during flood incident because it is easy to use and does not require numerous parameters for simulating.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.363-363
• /
• 2023

Artificial Neural Networks (ANN) is a powerful tool for addressing various practical problems and it has been extensively applied in areas of water resources. In this study, Artificial Neural Networks (ANNs) were developed for flood forecasting at specific locations on the Han River. The Partial Mutual Information (PMI) technique was used to select input variables for ANNs that are neither over-specified nor under-specified while adequately describing the underlying input-output relationships. Historical observations including discharges at the Paldang Dam, flows from tributaries, water levels at the Paldang Bridge, Banpo Bridge, Hangang Bridge, and Junryu gauge station, and time derivatives of the observed water levels were considered as input candidates. Lagged variables from current time t to the previous five hours were assumed to be sufficient in this study. A three-layer neural network with one hidden layer was used and the neural network was optimized by selecting the optimal number of hidden neurons given the selected inputs. Given an ANN architecture, the weights and biases of the network were determined in the model training. The use of PMI-based input variable selection and optimized ANNs for different sites were proven to successfully predict water levels during flood periods.

• Steel and Composite Structures
• /
• 제47권6호
• /
• pp.759-779
• /
• 2023

The paper proposes two hybrid metaheuristic optimization and artificial neural network (ANN) methods for the close prediction of the ultimate axial compressive capacity of concentrically loaded concrete filled double skin steel tube (CFDST) columns. Two metaheuristic optimization, namely genetic algorithm (GA) and particle swarm optimization (PSO), approaches enable the dynamic training architecture underlying an ANN model by optimizing the number and sizes of hidden layers as well as the weights and biases of the neurons, simultaneously. The former is termed as GA-ANN, and the latter as PSO-ANN. These techniques utilize the gradient-based optimization with Bayesian regularization that enhances the optimization process. The proposed GA-ANN and PSO-ANN methods construct the predictive ANNs from 125 available experimental datasets and present the superior performance over standard ANNs. Both the hybrid GA-ANN and PSO-ANN methods are encoded within a user-friendly graphical interface that can reliably map out the accurate ultimate axial compressive capacity of CFDST columns with various geometry and material parameters.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.125-125
• /
• 2020

European Space Agency's Sentinel-1 has an improved spatial and temporal resolution, as compared to previous satellite data such as Envisat Advanced SAR (ASAR) or Advanced Scatterometer (ASCAT). Thus, the assumption used for low-resolution retrieval algorithms used by ENVISAT ASAR or ASCAT is not applicable to Sentinel-1, because a higher degree of land surface heterogeneity should be considered for retrieval. The assumption of homogeneity over land surface is not valid any more. In this study, considering that soil roughness is one of the key parameters sensitive to soil moisture retrievals, various approaches are discussed. First, soil roughness is spatially inverted from Sentinel-1 backscattering over Yanco sites in Australia. Based upon this, Artificial Neural Networks data (feedforward multiplayer perception, MLP, Levenberg-Marquadt algorithm) are compared with Fractal approach (brownian fractal, Hurst exponent of 0.5). When using ANNs, training data are achieved from theoretical forward scattering models, Integral Equation Model (IEM). and Sentinel-1 measurements. The network is trained by 20 neurons and one hidden layer, and one input layer. On the other hand, fractal surface roughness is generated by fitting 1D power spectrum model with roughness spectra. Fractal roughness profile is produced by a stochastic process describing probability between two points, and Hurst exponent, as well as rms heights (a standard deviation of surface height). Main interest of this study is to estimate a spatial variability of roughness without the need of local measurements. This non-local approach is significant, because we operationally have to be independent from local stations, due to its few spatial coverage at the global level. More fundamentally, SAR roughness is much different from local measurements, Remote sensing data are influenced by incidence angle, large scale topography, or a mixing regime of sensors, although probe deployed in the field indicate point data. Finally, demerit and merit of these approaches will be discussed.

• Structural Engineering and Mechanics
• /
• 제85권3호
• /
• pp.315-335
• /
• 2023

Limited studies are available on the mathematical estimates of the compressive strength (CS) of glass fiber-embedded polymer (glass-FRP) compressive elements. The present study has endeavored to estimate the CS of glass-FRP normal strength concrete (NSTC) compression elements (glass-FRP-NSTC) employing two various methodologies; mathematical modeling and artificial neural networks (ANNs). The dataset of 288 glass-FRP-NSTC compression elements was constructed from the various testing investigations available in the literature. Diverse equations for CS of glass-FRP-NSTC compression elements suggested in the previous research studies were evaluated employing the constructed dataset to examine their correctness. A new mathematical equation for the CS of glass-FRP-NSTC compression elements was put forwarded employing the procedures of curve-fitting and general regression in MATLAB. The newly suggested ANN equation was calibrated for various hidden layers and neurons to secure the optimized estimates. The suggested equations reported a good correlation among themselves and presented precise estimates compared with the estimates of the equations available in the literature with R²= 0.769, and R² =0.9702 for the mathematical and ANN equations, respectively. The statistical comparison of diverse factors for the estimates of the projected equations also authenticated their high correctness for apprehending the CS of glass-FRP-NSTC compression elements. A broad parametric examination employing the projected ANN equation was also performed to examine the effect of diverse factors of the glass-FRP-NSTC compression elements.

• Korean Chemical Engineering Research
• /
• 제61권1호
• /
• pp.123-141
• /
• 2023

인공신경망을 이용한 모델 개발에서 데이터의 품질은 모델 성능에 큰 영향을 주고, 양질의 충분한 데이터가 인공신경망 훈련을 위해 필요하다. 하지만, 공학 분야에서는 적은 양의 데이터로 모델을 개발해야 하는 경우가 자주 발생한다. 본 논문은 토양에 살포된 축산 분뇨로부터 암모니아 방출량에 대한 적은 수의 데이터(83 개)를 사용하여 인공신경망 모델의 예측 성능을 향상할 수 있는 방안을 제시하였다. Michaelis-Menten 식으로 표현되는 암모니아 방출량 문제는 11개 입력변수에 대하여 2개 출력변수로 구성되었다. 출력변수는 최대 질소 발생량(N_max, kg/ha)과 N_max의 절반에 도달하는 시간(K_m, h) 이다. 범주형 입력변수에 대해 다차원 등간격 기법인 one-hot encoding 을 이용하여 데이터 전처리를 수행하였고, 훈련데이터 66개에 대하여 generative adversarial network (GAN)을 이용하여 13개 데이터를 추가로 보강하였다. 또한, 인공신경망의 초매개변수인 은닉층 수, 각 은닉층 내 뉴런 수, 활성화 함수의 최적 조합을 찾기 위하여 Gaussian process (GP)를 사용하였다. 기존의 인공신경망 구조(Lim et al., 2007) 는 17개 평가데이터에 대하여 mean absolute error (MAE)는 K_m에서 0.0668, N_max에서 0.1860이었다. 본 연구에서 제시된 인공신경망 모델은 K_m에서 0.0414, N_max에서 0.0818로 MAE 가 기존 모델 대비 각각 38%, 56% 감소하였다. 본 연구에서 제시된 방법은 적은 양의 데이터를 갖는 문제에서 인공신경망 성능을 향상하기 위하여 활용할 수 있을 것이다.