• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.280-282
• /
• 2021

A particular matter prediction model was designed using a deep learning algorithm to solve the problem of particular matter forecast with subjective judgment applied. RNN and LSTM were used among deep learning algorithms, and it was designed by applying optimal parameters by proceeding with hyperparametric navigation. The predicted performance of the two models was evaluated through RMSE and predicted accuracy. The performance assessment confirmed that there was no significant difference between the RMSE and accuracy, but there was a difference in the detailed forecast accuracy.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.337-343
• /
• 2004

Spatial information could be obtained from spaceborne high resolution optical and synthetic aperture radar(SAR) images. However, some satellite images do not provide physical sensor information instead, rational polynomial coefficients(RPC) are available. The objectives of this study are: (1) 3-dimensional ground coordinates were computed by applying rational function model(RFM) with the RPC for the stereo pair of Ikonos images and their accuracy was evaluated. (2) Interferometric SAR(InSAR) was applied to JERS-1 images to generate DEM and its accuracy was analysis. (3) Quality of the DEM generated automatically also analyzed for different types of terrain in the study site. The overall accuracy was evaluated by comparing with GPS surveying data. The height offset in the RPC was corrected by estimating bias. In consequence, the accuracy was improved. Accuracy of the DEMs generated from InSAR with different selection of GCP was analyzed. In case of the Ikonos images, the results show that the overall RMSE was 0.23327", 0.l1625" and 13.70m in latitude, longitude and height, respectively. The height accuracy was improved after correcting the height offset in the RPC. i.e., RMSE of the height was 1.02m. As for the SAR image, RMSE of the height was 10.50m with optimal selection of GCP. For the different terrain types, the RMSE of the height for urban, forest and flat area was 23.65m, 8.54m, 0.99m, respectively for Ikonos image while the corresponding RMSE was 13.82m, 18.34m, 10.88m, respectively lot SAR image.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.402-411
• /
• 2020

Power line noise in electrocardiogram signals makes it difficult to diagnose cardiovascular disease. ECG signals without power line noise are needed to increase the accuracy of diagnosis. In this paper, it is proposed DNN(Deep Neural Network) model to remove the power line noise in ECG. The proposed model is learned with noisy ECG, and clean ECG. Performance of the proposed model were performed in various environments(varying amplitude, frequency change, real-time amplitude change). The evaluation used signal-to-noise ratio and root mean square error (RMSE). The difference in evaluation metrics between the noisy ECG signals and the de-noising ECG signals can demonstrate effectiveness as the de-noising model. The proposed DNN model learning result was a decrease in RMSE 0.0224dB and a increase in signal-to-noise ratio 1.048dB. The results performed in various environments showed a decrease in RMSE 1.7672dB and a increase in signal-to-noise ratio 15.1879dB in amplitude changes, a decrease in RMSE 0.0823dB and a increase in signal-to-noise ratio 4.9287dB in frequency changes. Finally, in real-time amplitude changes, RMSE was decreased 0.3886dB and signal-to-noise ratio was increased 11.4536dB. Thus, it was shown that the proposed DNN model can de-noise power line noise in ECG.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.4
• /
• pp.31-39
• /
• 2007

As the availability of images from airborne digital camera with high resolution is expanded, a lot of concern are shown about the production of orthoimage and digital map. This study presents the method of updating digital map using orthoimage from airborne digital camera image. Images were georectified using GPS surveying data. For the generation of orthoimage, Lidar DEM was used. The absolute positional accuracy of orthoimage was evaluated using GPS surveying data. And that of the building layer of digital map was estimated using the existed digital map at the scale of 1:1,000. The absolute positional accuracy of orthoimage was as followed: RMSE in X and Y were ${\pm}0.076m$ and ${\pm}0.294m$. The RMSE of the building layer were ${\pm}0.250m$ and ${\pm}0.210m$ in X and Y directions, respectively. The RMSE of the digital map using orthoimage from Aerial Digital Camera image fell within allowable error range established by NGII. Consequently, updating digital map using orthoimage from Aerial Digital Camera image can be applied to various fields including the construction of the framework data and the GIS of local government.

• Journal of Navigation and Port Research
• /
• v.37 no.5
• /
• pp.463-469
• /
• 2013

This paper focuses on GPS positioning accuracy variations according to locations of obstacles which surround GPS station. We derived precise coordinates of a GPS station which has a good visibility. Its observation data was rewritten by assuming signal blocking due to obstacle in the elevation angle of $10^{\circ}$ to $70^{\circ}$. We processed daily and hourly data for 10 days. In the results using daily data, RMSE was at 10mm level. And RMSE increased to 100mm levels in case of hourly data. As the elevation angle of obstacle increased, the horizontal and vertical RMSE increased, while the height estimates decreased. These results showed the higher the elevation angle of the obstacle increased the loss of large amounts of data by blocking satellite signals direction. In terms of the direction, when the blocking thing was located in the east or west, the coordinate has larger error in the east-west direction. And if signal was blocked at the south direction, the difference between the east-west error and the south-north position error was reduced.

• Journal of Korean Society of Transportation
• /
• v.29 no.1
• /
• pp.113-123
• /
• 2011

The application of micro-simulation model has been extended farther with improvement of computer performance and development of complicated model. To make a micro-simulation model accurately replicate field traffic conditions, model calibration is very crucial. Studies on calibration of micro-simulation model have not been enough while lots of studies on calibration of macro-simulation model have been continued in our country. This paper presents an auto-calibration of parameter values in micro-simulation model(VISSIM) using genetic algorithm. RMSE(Root Mean Square Error) of collected volume on the urban expressway versus simulated volume is set as MOP(measure of performance) and objective function of optimization is set as to minimize the RMSE. Applying to urban expressway(Nae-bu circular) as a case study, it shows that RMSE of optimized parameter values decrease 60.4%($19.3{\longrightarrow}7.6$) compared to default parameter values and the proposed auto-calibration system is very effective.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.62 no.1
• /
• pp.39-50
• /
• 2020

The objective of this study was to assess the livestock nonpoint source pollutant impact on water quality in Namgang dam watershed using the HSPF (Hydrological Simulation Program-Fortran) model. The input data for the HSPF model was established using the landcover, digital elevation, and watershed and river maps. In order to apply the pollutant load to the HSPF model, the delivery load of the livestock nonpoint source in the Namgang dam watershed was calculated and used as a point pollutant input data for the HSPF model. The hydrologic and water quality parameters of HSPF model were calibrated and validated using the observed runoff data from 2007 to 2015 at Sancheong station. The R² (Determination Coefficient), RMSE (Root Mean Square Error), NSE (Nash-Sutcliffe efficiency coefficient), and RMAE (Relative Mean Absolute Error) were used to evaluate the model performance. The simulation results for annual mean runoff showed that R² ranged 0.79~0.81, RMSE 1.91~2.73 mm/day, NSE 0.7~0.71 and RMAE 0.37~0.49 mm/day for daily runoff. The simulation results for annual mean BOD for RMSE ranged 0.99~1.13 mg/L and RMAE 0.49~0.55 mg/L, annual mean TN for RMSE ranged 1.65~1.72 mg/L and RMAE 0.55 mg/L, and annual mean TP for RMSE ranged 0.043~0.055 mg/L and RMAE 0.552~0.570 mg/L. As a result of livestock nonpoint pollutant loading simulation for each sub-watersehd using the HSPF model, the BOD ranged 16.6~163 kg/day, TN ranged 27.5~337 kg/day, TP ranged 1.22~14.1 kg/day.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.24 no.5
• /
• pp.333-342
• /
• 2012

We studied the characteristics of spatial distribution of global wave height and carried out the modelsensitivity test by changing the input field, model resolution and physical factor (effective wind factor) since the spatial and temporal resolution in wind wave forecasting is one of most important factors. Comparisons among the different cases, and also between model, buoy and satellite data have been made. As a results of the wind-wave model run using the high resolution wind field, the bias of significant wave height showed the positive tendency and the Root-Mean Square Error(RMSE) was a bit decreased based on the comparison with buoy data. When the model resolution was changed to higher, the bias and RMSE was increased, and as the effective wind factor was smaller than default value(= 1.4) the bias and RMSE showed also decreasing pattern.

• Journal of Ocean Engineering and Technology
• /
• v.36 no.2
• /
• pp.101-107
• /
• 2022

Dean (1965) proposed the use of the root mean square error (RMSE) in the dynamic free surface boundary condition (DFSBC) and kinematic free-surface boundary condition (KFSBC) as an error evaluation criterion for wave theories. There are well known wave theories with RMSE more than 1%, such as Airy theory, Stokes theory, Dean's stream function theory, Fenton's theory, and trochodial theory for deep-water waves. However, none of them can be applied for deep-water breaking waves. The purpose of this study is to provide a closed-form solution for deep-water waves with RMSE less than 1% even for breaking waves. This study is based on a previous study (Shin, 2016), and all flow fields were simplified for deep-water waves. For a closed-form solution, all Fourier series coefficients and all related parameters are presented with Newton's polynomials, which were determined by curve fitting data (Shin, 2016). For verification, a wave in Miche's limit was calculated, and, the profiles, velocities, and the accelerations were compared with those of 5^th-order Stokes theory. The results give greater velocities and acceleration than 5^th-order Stokes theory, and the wavelength depends on the wave height. The results satisfy the Laplace equation, bottom boundary condition (BBC), and KFSBC, while Stokes theory satisfies only the Laplace equation and BBC. RMSE in DFSBC less than 7.25×10^-2% was obtained. The series order of the proposed method is three, but the series order of 5^th-order Stokes theory is five. Nevertheless, this study provides less RMSE than 5^th-order Stokes theory. As a result, the method is suitable for offshore structural design.

• Journal of radiological science and technology
• /
• v.46 no.2
• /
• pp.131-139
• /
• 2023

High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R² to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R² 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R² 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R² 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R² 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.