• Journal of Korea Water Resources Association
• /
• v.53 no.6
• /
• pp.395-408
• /
• 2020

This paper aims to develop and apply three different machine learning approaches (i.e., artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), and wavelet-based neural networks (WNN)) combined with an evolutionary optimization algorithm and the k-fold cross validation for multi-step (days) streamflow forecasting at the catchment located in Algeria, North Africa. The ANN and ANFIS models yielded similar performances, based on four different statistical indices (i.e., root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), correlation coefficient (R), and peak flow criteria (PFC)) for training and testing phases. The values of RMSE and PFC for the WNN model (e.g., RMSE = 8.590 ㎥/sec, PFC = 0.252 for (t+1) day, testing phase) were lower than those of ANN (e.g., RMSE = 19.120 ㎥/sec, PFC = 0.446 for (t+1) day, testing phase) and ANFIS (e.g., RMSE = 18.520 ㎥/sec, PFC = 0.444 for (t+1) day, testing phase) models, while the values of NSE and R for WNN model were higher than those of ANNs and ANFIS models. Therefore, the new approach can be a robust tool for multi-step (days) streamflow forecasting in the Seybous River, Algeria.

• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.855-863
• /
• 2022

In this study, the Artificial Neural Network (ANN) was used to mapping air temperature in Seoul. MODerate resolution Imaging Spectroradiomter (MODIS) data was used as auxiliary data for mapping. For the ANN network topology optimizing, scatterplots and statistical analysis were conducted, and input-data was classified and combined that highly correlated data which surface temperature, Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), time (satellite observation time, Day of year), location (latitude, hardness), and data quality (cloudness). When machine learning was conducted only with data with a high correlation with air temperature, the average values of correlation coefficient (r) and Root Mean Squared Error (RMSE) were 0.967 and 2.708℃. In addition, the performance improved as other data were added, and when all data were utilized the average values of r and RMSE were 0.9840 and 1.883℃, which showed the best performance. In the Seoul air temperature map by the ANN model, the air temperature was appropriately calculated for each pixels topographic characteristics, and it will be possible to analyze the air temperature distribution in city-level and national-level by expanding research areas and diversifying satellite data.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.34 no.4
• /
• pp.277-282
• /
• 2014

Nutritive value analysis of feed is very important for the growth of livestock, and ensures the efficiency of feeds as well as economic status. However, general laboratory analyses require considerable time and high cost. Near-infrared reflectance spectroscopy (NIRS) is a spectroscopic technique used to analyze the nutritive values of seeds. It is very effective and less costly than the conventional method. The sample used in this study was a corn kernel and the partial least square regression method was used for evaluating nutrient composition, digestibility, and energy value based on the calibration equation. The evaluation methods employed were the coefficient of determination ($R^2$) and the root mean squared error of prediction (RMSEP). The results showed the moisture content ($R^2_{val}=0.97$, RMSEP=0.109), crude protein content ($R^2_{val}=0.94$, RMSEP=0.212), neutral detergent fiber content ($R^2_{val}=0.96$, RMSEP=0.763), acid detergent fiber content ($R^2_{val}=0.96$, RMSEP=0.142), gross energy ($R^2_{val}=0.82$, RMSEP=23.249), in vitro dry matter digestibility ($R^2_{val}=0.68$, RMSEP=1.69), and metabolizable energy (approximately $R^2_{val}$ >0.80). This study confirmed that the nutritive components of corn kernels can be predicted using near-infrared reflectance spectroscopy.

• Journal of applied mathematics & informatics
• /
• v.26 no.5_6
• /
• pp.1149-1159
• /
• 2008

Blind source extraction (BSE) is a special class of blind source separation (BSS) methods, which only extracts one or a subset of the sources at a time. Based on the time delay of the desired signal, a simple but important extraction algorithm (simplified " BC algorithm")was presented by Barros and Cichocki. However, the performance of this method is not satisfying in some cases for which it only carries out the constrained minimization of the mean squared error. To overcome these drawbacks, ICA with reference (ICA-R) based approach, which considers the higher-order statistics of sources, is added as the second stage for further source extraction. Specifically, BC algorithm is exploited to roughly extract the desired signal. Then the extracted signal in the first stage, as the reference signal of ICA-R method, is further used to extract the desired sources as cleanly as possible. Simulations on synthetic data and real-world data show its validity and usefulness.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1148-1155
• /
• 2020

Fire must be extinguished as quickly as possible because they cause a lot of economic loss and take away precious human lives. Especially, the detection of smoke, which tends to be found first in fire, is of great importance. Smoke detection based on image has many difficulties in algorithm research due to the irregular shape of smoke. In this study, we introduce a new real-time smoke detection algorithm that reduces the detection of false positives generated by irregular smoke shape based on faster r-cnn of factory-installed surveillance cameras. First, we compute the global frame similarity and mean squared error (MSE) to detect the movement of smoke from the input surveillance camera. Second, we use deep learning algorithm (Faster r-cnn) to extract deferred candidate regions. Third, the extracted candidate areas for acting are finally determined using space and temporal features as smoke area. In this study, we proposed a new algorithm using the space and temporal features of global and local frames, which are well-proposed object information, to reduce false positives based on deep learning techniques. The experimental results confirmed that the proposed algorithm has excellent performance by reducing false positives of about 99.0% while maintaining smoke detection performance.

• Journal of Drive and Control
• /
• v.20 no.3
• /
• pp.25-34
• /
• 2023

In this study, we conducted a research on optimizing the spraying performance of agricultural drones and predicted the spraying performance in various flight conditions using the multi-layer perceptron (MLP). Data was collected using a test device for pesticide spraying performance according to the water sensitive paper (WSP) evaluation. MLP training involved supervised learning to achieve a coefficient of variation (CV), which indicates the degree of uniform spraying. The performance evaluation was conducted using R-squared (R²), the test samples showed an R² of 0.80. The results of this study showed that drone spraying performance can be predicted under various flight environments. In addition, the correlation analysis between flight conditions and predicted spraying performance will be useful for further research on optimizing the spraying performance of agricultural drones.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.67-75
• /
• 2011

This paper presents a scale and rotation-invariant gait recognition method using R-transform, which is computed by projecting squared coefficients of Radon transform. Since R-transform is invariant to translation, rotation, and scaling, it particularly suitable for extracting object poses without camera calibration. Coefficients of R-transform are used to compute correlation, and the maximum correlation value determines the similarity between two gait images. The proposed method requires neither camera calibration nor geometric compensation, and as a result, it makes robust gait recognition possible without additional compensation for translation, rotation, and scaling.

• Journal of Environmental Science International
• /
• v.24 no.11
• /
• pp.1393-1404
• /
• 2015

Ten empirical disinfection models for the plasma process were used to find an optimum model. The variation of model parameters in each model according to the operating conditions (first voltage, second voltage, air flow rate, pH, incubation water concentration) were investigated in order to explain the disinfection model. In this experiment, the DBD (dielectric barrier discharge) plasma reactor was used to inactivate Phytophthora capsici which cause wilt in tomato plantation. Optimum disinfection models were chosen among ten models by the application of statistical SSE (sum of squared error), RMSE (root mean sum of squared error), $r^2$ values on the experimental data using the GInaFiT software in Microsoft Excel. The optimum models were shown as Log-linear+Tail model, Double Weibull model and Biphasic model. Three models were applied to the experimental data according to the variation of the operating conditions. In Log-linear+Tail model, $Log_{10}(N_o)$, $Log_{10}(N_{res})$ and $k_{max}$ values were examined. In Double Weibull model, $Log_{10}(N_o)$, $Log_{10}(N_{res})$, ${\alpha}$, ${\delta}_1$, ${\delta}_2$, p values were calculated and examined. In Biphasic model, $Log_{10}(N_o)$, f, $k_{max1}$ and $k_{max2}$ values were used. The appropriate model parameters for the calculation of optimum operating conditions were $k_{max}$, ${\alpha}$, $k_{max1}$ at each model, respectively.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.23-31
• /
• 2023

Research and interest in sustainable printing are increasing in the packaging printing industry. Currently, predicting the amount of ink required for each work is based on the experience and intuition of field workers. Suppose the amount of ink produced is more than necessary. In this case, the rest of the ink cannot be reused and is discarded, adversely affecting the company's productivity and environment. Nowadays, machine learning models can be used to figure out this problem. This study compares the ink usage prediction machine learning models. A simple linear regression model, Multiple Regression Analysis, cannot reflect the nonlinear relationship between the variables required for packaging printing, so there is a limit to accurately predicting the amount of ink needed. This study has established various prediction models which are based on CART (Classification and Regression Tree), such as Decision Tree, Random Forest, Gradient Boosting Machine, and XGBoost. The accuracy of the models is determined by the K-fold cross-validation. Error metrics such as root mean squared error, mean absolute error, and R-squared are employed to evaluate estimation models' correctness. Among these models, XGBoost model has the highest prediction accuracy and can reduce 2134 (g) of wasted ink for each work. Thus, this study motivates machine learning's potential to help advance productivity and protect the environment.

• Geomechanics and Engineering
• /
• v.33 no.3
• /
• pp.279-289
• /
• 2023

Brittleness index (BI) is an important property of rocks because it is a good index to predict rockburst. Due to its importance, several empirical and soft computing (SC) models have been proposed in the literature based on the punch penetration test (PPT) results. These models are very important as there is no clear-cut experimental means for measuring BI asides the PPT which is very costly and time consuming to perform. This study used a novel Multivariate Adaptive regression spline (MARS), M5P, and white-box ANN to predict the BI of rocks using the available data in the literature for an improved BI prediction. The rock density, uniaxial compressive strength (σ_c) and tensile strength (σ_t) were used as the input parameters into the models while the BI was the targeted output. The models were implemented in the MATLAB software. The results of the proposed models were compared with those from existing multilinear regression, linear and nonlinear particle swarm optimization (PSO) and genetic algorithm (GA) based models using similar datasets. The coefficient of determination (R²), adjusted R² (Adj R²), root-mean squared error (RMSE) and mean absolute percentage error (MAPE) were the indices used for the comparison. The outcomes of the comparison revealed that the proposed ANN and MARS models performed better than the other models with R² and Adj R² values above 0.9 and least error values while the M5P gave similar performance to those of the existing models. Weight partitioning method was also used to examine the percentage contribution of model predictors to the predicted BI and tensile strength was found to have the highest influence on the predicted BI.