• Journal of Biosystems Engineering
• /
• v.43 no.2
• /
• pp.148-159
• /
• 2018

Purpose: Unmanned air vehicle (UAV) remote sensing was applied to test various vegetation indices and make prediction models of protein content of rice for monitoring grain quality and proper management practice. Methods: Image acquisition was carried out by using NIR (Green, Red, NIR), RGB and RE (Blue, Green, Red-edge) camera mounted on UAV. Sampling was done synchronously at the geo-referenced points and GPS locations were recorded. Paddy samples were air-dried to 15% moisture content, and then dehulled and milled to 92% milling yield and measured the protein content by near-infrared spectroscopy. Results: Artificial neural network showed the better performance with $R^2$ (coefficient of determination) of 0.740, NSE (Nash-Sutcliffe model efficiency coefficient) of 0.733 and RMSE (root mean square error) of 0.187% considering all 54 samples than the models developed by PR (polynomial regression), SLR (simple linear regression), and PLSR (partial least square regression). PLSR calibration models showed almost similar result with PR as 0.663 ($R^2$) and 0.169% (RMSE) for cloud-free samples and 0.491 ($R^2$) and 0.217% (RMSE) for cloud-shadowed samples. However, the validation models performed poorly. This study revealed that there is a highly significant correlation between NDVI (normalized difference vegetation index) and protein content in rice. For the cloud-free samples, the SLR models showed $R^2=0.553$ and RMSE = 0.210%, and for cloud-shadowed samples showed 0.479 as $R^2$ and 0.225% as RMSE respectively. Conclusion: There is a significant correlation between spectral bands and grain protein content. Artificial neural networks have the strong advantages to fit the nonlinear problem when a sigmoid activation function is used in the hidden layer. Quantitatively, the neural network model obtained a higher precision result with a mean absolute relative error (MARE) of 2.18% and root mean square error (RMSE) of 0.187%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.572-578
• /
• 2020

The stock market is affected by unexpected factors, such as politics, society, and natural disasters, as well as by corporate performance and economic conditions. In recent days, artificial intelligence has become popular, and many researchers have tried to conduct experiments with that. Our study proposes an experiment using not only stock-related data but also other various economic data. We acquired a year's worth of data on stock prices, the percentage of foreigners, interest rates, and exchange rates, and combined them in various ways. Thus, our input data became diversified, and we put the combined input data into a nonlinear autoregressive network with exogenous inputs (NARX) model. With the input data in the NARX model, we analyze and compare them to the original data. As a result, the model exhibits a root mean square error (RMSE) of 0.08 as being the most accurate when we set 10 neurons and two delays with a combination of stock prices and exchange rates from the U.S., China, Europe, and Japan. This study is meaningful in that the exchange rate has the greatest influence on stock prices, lowering the error from RMSE 0.589 when only closing data are used.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.3
• /
• pp.849-858
• /
• 2014

The mount of antecedent 5-day rainfall (P5) is usually used to determine the antecedent soil moisture condition for estimating effective rainfall using the NRCS-CN method. In order to re-establish the threshold of P5 considering basin characteristics, this study investigated the sensitivity of the threshold of P5 to effective rainfall by comparing the corresponding observed direct runoff. The overall results indicate that the direct runoff estimated using the re-establihed threshold of P5 has smaller mean error (RMSE of 27.3 mm) than those using the conventional threshold (RMSE of 35.2 mm). In addition, after evaluating the effectiveness of threshold of P5 using the improvement index, the threshold re-established in this study improved the ability to estimate the direct runoff by 30% on average. This study also suggested to employ regression models using topographic indices to re-establish the threshold for ungauged basins. When using the re-established threshold from the regression model, the RMSE decreased ranging from 0.4 mm to 15.1 mm and the efficiency index of Nash and Sutcliffe increased up to 0.33.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.435-452
• /
• 2016

Land Surface Temperature (LST) has been operationally retrieved from the Communication, Ocean, and Meteorological Satellite (COMS) data by the spilt-window method (CSW_v2.0) developed by Cho et al. (2015). Although the CSW_v2.0 retrieved the LST with a reasonable quality compared to the Moderate Resolution Imaging Spectroradiometer (MODIS) LST data, it showed a relatively poor performance for the strong inversion and lapse rate conditions. To solve this problem, the LST retrieval algorithm (CSW_v2.0) was updated using the simulation results of radiative transfer model (MODTRAN 4.0) by considering the diurnal variations of air temperature. In general, the upgraded version, CSW_v3.0 showed a similar correlation coefficient between the prescribed LSTs and retrieved LSTs (0.99), the relatively smaller bias (from -0.03 K to-0.012 K) and the Root Mean Square Error (RMSE) (from 1.39 K to 1.138 K). Particularly, CSW_v3.0 improved the systematic problems of CSW_v2.0 that were encountered when temperature differences between LST and air temperature are very large and/or small (inversion layers and superadiabatic lapse rates), and when the brightness temperature differences and surface emissivity differences were large. The bias and RMSE of CSW_v2.0 were reduced by 10-30% in CSW_v3.0. The indirect validation results using the MODIS LST data showed that CSW_3.0 improved the retrieval accuracy of LST in terms of bias (from -0.629 K to -0.049 K) and RMSE (from 2.537 K to 2.502 K) compared to the CSW_v2.0.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.4
• /
• pp.221-228
• /
• 2019

The effects of wind speed on the temperature change during day time could be insignificant in a region with a complex terrain. The objective of this study was to derive empirical relationship between solar radiation and hourly temperature under a windy condition for the period from sunrise to sunset in order to improve hourly air temperature at a site-specific scale. The deviation of the temperature measurements was analyzed along with the changes of the hourly sunlight at weather observation sites located on the east and west slopes under given wind speed. An empirical model where wind speed use used as an independent variable was obtained to quantify the solar effects on the temperature change (MJ/㎡). This model was verified estimating the hourly temperature during the daytime (0600-1900 h) at 25 weather observation sites located in the study area that has complex topography for the period from January to December 2018. The mean error (ME) and root mean square error (RMSE)of the estimated and measured values ranged from -0.98 to 0.67 ℃, and from 0.95 to 2.04 ℃, respectively. The daytime temperature at 1500 h were estimated using new and previous models. It was found that to the model proposed in the present study reduced the measurement errors of the hourly temperature in the afternoon in comparison with the previous model. For example, the ME and RMSE of the previous model were (ME -0.91 ℃ and 1.47 ℃, respectively. In contrast, the values of ME and RMSE were -0.45 ℃ and 1.22 ℃ for the new model, respectively. Our results suggested that the reliability of hourly temperature estimates at a specific site could be improved taking into account the effect of wind as well as solar radiation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.3
• /
• pp.175-186
• /
• 2017

In this study was to survey method of national/public land actual condition survey to utilization of UAV, in order to evaluate the economic and accuracy. we carried out the comparative evaluation of the cadastral status surveying in terms of accuracy of parcel checkpoint, economical costs. The results are summarized as follows. First, average position error of the orthoimage was 0.033m in X error, 0.023m in Y error when the RMSE average calculated 0.046m from the intersection of plane distance connections. Secondly, it was appeared the accuracy of the orthophotograph is 0.076m at the maximum RMSE of the UAV orthoimage check point and 0.042m at the minimum RMSE compared with the VRS-GNSS survey results. Thirdly, when the allowable error specified in the implementing regulation of the current cadastral survey is applied, all of the checkpoint of 0.360m tolerance corresponding to the scale of 1/1,200 is satisfied. Finally, UAV utilization method in national/public land actual condition survey is 26,497,436(KRW) cheaper than cadastral survey method for In the economic evaluation of national/public land actual condition survey. Therefore, as a result of this study shows that the method of utilizing UAV in the national/public land actual condition survey satisfies legal standards in terms of accuracy and economical aspect is a way to further reduce the local government budget.

• Food Science of Animal Resources
• /
• v.30 no.3
• /
• pp.487-494
• /
• 2010

Cooked pork can be easily contaminated with Staphylococcus aureus during carriage and serving after cooking. This study was performed to develop growth prediction models of S. aureus to assure the safety of cooked pork. The Baranyi and Gompertz primary predictive models were compared. These growth models for S. aureus in cooked pork were developed at storage temperatures of 5, 15, and $25^{\circ}C$. The specific growth rate (SGR) and lag time (LT) values were calculated. The Baranyi model, which displayed a $R^2$ of 0.98 and root mean square error (RMSE) of 0.27, was more compatible than the Gompertz model, which displayed 0.84 in both $R^2$ and RMSE. The Baranyi model was used to develop a response surface secondary model to indicate changes of LT and SGR values according to storage temperature. The compatibility of the developed model was confirmed by calculating $R^2$, $B_f$, $A_f$, and RMSE values as statistic parameters. At 5, 15 and $25^{\circ}C$, $R^2$ was 0.88, 0.99 and 0.99; RMSE was 0.11, 0.24 and 0.10; $B_f$ was 1.12, 1.02 and 1.03; and $A_f$ was 1.17, 1.03 and 1.03, respectively. The developed predictive growth model is suitable to predict the growth of S. aureus in cooked pork, and so has potential in the microbial risk assessment as an input value or model.

• Korean Journal of Remote Sensing
• /
• v.15 no.1
• /
• pp.1-8
• /
• 1999

The estimation technique of surface water temperature by satellite remote sensing has been applied to ocean and large lakes using AVHRR. However, the spatial resolution AVHBR is not abquate for coastal region and small lakes. Landsat 5 TM has 120 m spatial resolution, which suits better. We carried out analysis of surface water temperature in Lake Sihwa and near coastal area using Landsat 5 TM. To relate digital number to the brightness temperature, we applied Empirical, NASA, RESTEC, Quadratic methods. Comparing calculated and observed value, we obtained as follows; NASA method, $R^2=0.9343$, RMSE(Root Mean Square Error)=3.5876$^{\circ}C$; RESTEC method, $R^2=0.8937$, RMSE=3.76$^{\circ}C$; Quadratic method, $R^2=0.8967$, RMSE=2.949$^{\circ}C$. Because Landsat TM has only one band for extracting surface temperature, it was difficult to correct for the atmospheric errors. For improving the accuracy of surface temperature detection using Landsat TM, there is a need for a method to decrease the effect of atmospheric contents.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.861-870
• /
• 2021

In this study, fused Aerosol Optical Depth (AOD) data were produced using AOD products from the Geostationary Ocean Color Imager (GOCI) onboard Communication, Oceanography and Meteorology Satellite (COMS)satellite and the Advanced Himawari Imager (AHI) onboard Himawari-8. Since the spatial resolution and the coordinate system between the satellite sensors are different, a preprocessing was first preceded. After that, using the level 1.5 AOD dataset of AErosol RObotic NETwork (AERONET), which is ground-based observation, correlations and trends between each satellite AOD and AERONET AOD were utilized to produce more accurate satellite AOD data than the originalsatellite AODs. The fused AOD were found to be more accurate than the originalsatellite AODs. Root Mean Square Error (RMSE) and mean bias of the fused AODs were calculated to be 0.13 and 0.05, respectively. We also compared errors of the fused AODs against those of the original GOCI AOD (RMSE: 0.15, mean bias: 0.11) and the original AHI AOD (RMSE: 0.15, mean bias: 0.05). It was confirmed that the fused AODs have betterspatial coverage than the original AODsin areas where there are no observations due to the presence of cloud from a single satellite.