• Journal of Korean Society on Water Environment
• /
• v.21 no.1
• /
• pp.21-28
• /
• 2005

The training and prediction modeling using an artificial neural network was implemented to predict the turbidity of treated water as well as to estimate the optimized feed concentration of polyaluminium chloride (PACl) in a water treatment plant. The parameters used in the input layers were pH, temperature, turbidity and alkalinity, while those in output layers were PACl and turbidity of treated water. Levenberg-Marquadt method of feedforward back-propagation perceptron in the neural network toolbox of MATLAB program was used in this study. Correlation coefficients of the training data with the measured data were 0.9997 for PACl and 0.6850 for turbidity and those of the testing data with measured data were 0.9140 for PACl and 0.3828 for turbidity, when four parameters at input layer, 12-12 nodes each at both the first and the second hidden layers, and two parameters(PACl and turbidity) at output layer were used. Although the predictability of PACl was improved, compared to that of the previous studies to use the only coagulant dose as output layer, turbidity in treated water could not be predicted well. Acquisition of more data through several years obtained with the advanced on-line measuring system could make the artificial neural network useful and practical in actual water treatment plants.

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.25-34
• /
• 2017

Autoencoder is a type of deep learning method where input layer and output layer are the same, and effectively extracts and restores characteristics of input vector using constraints of hidden layer. In this paper, we propose methods of Autoencoders to remove a natural background image which is a noise to the CAPTCHA and recover only a numerical images by applying various autoencoder models to a region where one number of CAPTCHA images and a natural background are mixed. The suitability of the reconstructed image is verified by using the softmax function with the output of the autoencoder as an input. And also, we compared the proposed methods with the other method and showed that our methods are superior than others.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.537-542
• /
• 2004

Multi-Layer Perceptron network has been mainly applied to many practical problems because of its nonlinear mapping ability. However the generalization ability of MLP networks may be affected by the number of hidden nodes, the initial values of weights and the training errors. These factors, if improperly chosen, may result in poor generalization ability of MLP networks. It is important to identify these factors and their interaction in order to control effectively the generalization ability of MLP networks. In this paper, we have empirically identified the factors that affect the generalization ability of MLP networks, and compared their relative effects on the generalization performance for the conventional and visualized weight selecting methods using the controller box.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.1
• /
• pp.90-97
• /
• 2004

DC motor requires a rotor speed sensor for accurate speed control. The speed sensors such as resolvers and encoders are used as speed detectors. but they increase cost and size of the motor and restrict the industrial drive applications. So in these days. many Papers have reported on the sensorless operation or DC motor(3)-(5). This paper Presents a new sensorless strategy using neural networks(6)-(8). Neural network structure has three layers which are input layer. hidden layer and output layer. The optimal neural network structure was tracked down by trial and error and it was found that 4-16-1 neural network has given suitable results for the instantaneous rotor speed. Also. learning method is very important in neural network. Supervised learning methods(8) are typically used to train the neural network for learning the input/output pattern presented. The back-propagation technique adjusts the neural network weights during training. The rotor speed is gained by weights and four inputs to the neural network. The experimental results were found satisfactory in both the independency on machine parameters and the insensitivity to the load condition.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.6
• /
• pp.89-97
• /
• 2022

Ultrasonic metal welding has been widely used for joining lithium-ion battery tabs. Weld quality monitoring has been an important issue in lithium-ion battery manufacturing. This study focuses on the weld quality monitoring in ultrasonic metal welding with the longitudinal-torsional vibration mode horn developed newly. As the quality of ultrasonic welding depends on welding parameters like pressure, time, and amplitude, the suitable values of these parameters were selected for experimentation. The welds were tested via tensile testing machine and weld strengths were investigated. The dataset collected for performance test was used to train the multi-layer perceptron neural network. The three layer neural network was used for the study and the optimum number of neurons in the first and second hidden layers were selected based on performances of each models. The best models were selected for the horn and then tested to see their performances on an unseen dataset. The neural network models for the longitudinal-torsional mode horn attained test accuracy of 90%. This result implies that proposed models has potential for the weld quality monitoring.

• International Journal of Korean Welding Society
• /
• v.1 no.2
• /
• pp.51-60
• /
• 2001

A prediction method for determining the welding residual stress by artificial neural network is proposed. A three-dimensional transient thermo-mechanical analysis has been performed for the $CO_2$ arc welding using the finite element method. The first part of numerical analysis performs a three-dimensional transient heat transfer analysis, and the second part then uses the results of the first part and performs a three-dimensional transient thermo-elastic-plastic analysis to compute transient and residual stresses in the weld. Data from the finite element method are used to train a back propagation neural network to predict the residual stress. Architecturally, the fully interconnected network consists of an input layer for the voltage and current, a hidden layer to accommodate the failure mechanism mapping, and an output layer for the residual stress. The trained network is then applied to the prediction of residual stress in the four specimens. It is concluded that the accuracy of the neural network predicting method is fully comparable with the accuracy achieved by the traditional predicting method.

• Nutrition Research and Practice
• /
• v.17 no.6
• /
• pp.1255-1266
• /
• 2023

BACKGROUND/OBJECTIVES: This study aimed to predict the association between nutritional intake and diabetes mellitus (DM) by developing an artificial neural network (ANN) model for older adults. SUBJECTS/METHODS: Participants aged over 65 years from the 7th (2016-2018) Korea National Health and Nutrition Examination Survey were included. The diagnostic criteria of DM were set as output variables, while various nutritional intakes were set as input variables. An ANN model comprising one input layer with 16 nodes, one hidden layer with 12 nodes, and one output layer with one node was implemented in the MATLAB^® programming language. A sensitivity analysis was conducted to determine the relative importance of the input variables in predicting the output. RESULTS: Our DM-predicting neural network model exhibited relatively high accuracy (81.3%) with 11 nutrient inputs, namely, thiamin, carbohydrates, potassium, energy, cholesterol, sugar, vitamin A, riboflavin, protein, vitamin C, and fat. CONCLUSIONS: In this study, the neural network sensitivity analysis method based on nutrient intake demonstrated a relatively accurate classification and prediction of DM in the older population.

• Journal of Korea Water Resources Association
• /
• v.56 no.1
• /
• pp.63-74
• /
• 2023

High-reliability prediction of dam inflow is necessary for efficient dam operation. Recently, studies were conducted to predict the inflow of dams using Multi Layer Perceptron (MLP). Existing studies used the Gradient Descent (GD)-based optimizer as the optimizer among MLP operators to find the optimal correlation between data. However, the GD-based optimizers have disadvantages in that the prediction performance is deteriorated due to the possibility of convergence to the local optimal value and the absence of storage space. This study improved the shortcomings of the GD-based optimizer by developing Adaptive moments combined with Improved Harmony Search (AdamIHS), which combines Adaptive moments among GD-based optimizers and Improved Harmony Search (IHS). In order to evaluate the learning and prediction performance of MLP using AdamIHS, Daecheong Dam inflow was learned and predicted and compared with the learning and prediction performance of MLP using GD-based optimizer. Comparing the learning results, the Mean Squared Error (MSE) of MLP, which is 5 hidden layers using AdamIHS, was the lowest at 11,577. Comparing the prediction results, the average MSE of MLP, which is one hidden layer using AdamIHS, was the lowest at 413,262. Using AdamIHS developed in this study, it will be possible to show improved prediction performance in various fields.

• Journal of Korea Water Resources Association
• /
• v.37 no.9
• /
• pp.771-780
• /
• 2004

The purpose of this study is to test a development of system for flood runoff forecasting using neural network model. As the forecasting models for flood runoff the neural network model was tested with the observed flood data at Gongju and Buyeo stations. The neural network model consists of input layer, hidden layer, and output layer. For the flood events tested rainfall and runoff data were the input to the input layer and the flood runoff data were used in the output layer. To make a choice the forecasting model which would make up of runoff forecasting system properly, real-time runoff of river when flood periods were forecasted by using neural network model and state-space model. A comparison of the results obtained by the two forecasting models indicated the superiority and reliability of the neural network model over the state-space model. The neural network model was modified to work in the Web and developed to be the basic model of the forecasting system for the flood runoff. The neural network model developed to be used in the Web was loaded into the server and was applied to the main stream of Geum river. For the main stage gauging stations mentioned above the applicability of the selected forecasting model, the Neural Network Model, was verified in the Web.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.31-38
• /
• 2021

In this paper, in order to obtain the optimization of the RNN model used for sentiment analysis, the correlation of each model was studied by observing the trend of loss and accuracy according to hyperparameter tuning. As a research method, after configuring the hidden layer with LSTM and the embedding layer that are most optimized to process sequential data, the loss and accuracy of each model were measured by tuning the unit, batch-size, and embedding size of the LSTM. As a result of the measurement, the loss was 41.9% and the accuracy was 11.4%, and the trend of the optimization model showed a consistently stable graph, confirming that the tuning of the hyperparameter had a profound effect on the model. In addition, it was confirmed that the decision of the embedding size among the three hyperparameters had the greatest influence on the model. In the future, this research will be continued, and research on an algorithm that allows the model to directly find the optimal hyperparameter will continue.