• Journal of Biosystems Engineering
• /
• v.37 no.5
• /
• pp.319-326
• /
• 2012

Purpose: Cheese texture is an important sensory attribute mainly considered for consumers' acceptance. The feasibility of nondestructive measurements of cheese texture was explored using non-contact ultrasonic sensors. Methods: A novel non-contact air instability compensation ultrasonic technique was used for five varieties of hard cheeses to measure ultrasonic parameters, such as velocity and attenuation coefficient. Five texture properties, such as fracturability, hardness, springiness, cohesiveness, and chewiness were assessed by a texture profile analysis (TPA) and correlated with the ultrasonic parameters. Results: Texture properties of five varieties of hard cheese were estimated using ultrasonic parameters with regression analysis models. The most effective model predicted the fracturability, hardness, springiness, and chewiness, with the determination coefficients of 0.946 (RMSE = 21.82 N), 0.944 (RMSE = 63.46 N), 0.797 (RMSE = 0.06 ratio), and 0.833 (RMSE = 17.49 N), respectively. Conclusions: This study demonstrated that the non-contact air instability compensation ultrasonic sensing technique can be an effective tool for rapid and non-destructive determination of cheese texture.

• 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.

• Journal of Radiation Industry
• /
• v.17 no.4
• /
• pp.551-557
• /
• 2023

In recent years, radiation has become a socially important issue, increasing the need for accurate prediction of radiation levels. In this study, machine learning-based models such as Multiple Linear Regression (MLR), Random Forest (RF), XGBoost, and LightGBM, which predict the dose rate by time(nSv h^-1) by selecting only important variables, were used, and the correlation between temperature, humidity, cumulative precipitation, wind direction, wind speed, local air pressure, sea pressure, solar radiation, and radiation dose rate (nSv h^-1) was analyzed by collecting weather data and radiation dose rate for about 6 months in Jangseong, Jeollanam-do. As a result of the evaluation based on the RMSE (Root Mean Squared Error) and R-Squared (R-Squared coefficient of determination) scores, the RMSE of the XGBoost model was 22.92 and the R-Squared was 0.73, showing the best performance among the models used. As a result of optimizing hyperparameters of all models using the GridSearch method and comparing them by adding variables inside the measuring instrument, it was confirmed that the performance improved to 2.39 for RMSE and 0.99 for R-Squared in both XGBoost and LightGBM.

• 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.