• 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 Geotechnical Society
• /
• v.22 no.8
• /
• pp.107-118
• /
• 2006

Among a variety of influencing components, time-variant seepage and long-term underground motion are important to understand the abnormal behavior of tunnels. Excessiveness of these two components could be the direct cause of severe damage on tunnels, however, it is not easy to quantify the effect of these on the behavior of tunnels. These parameters can be estimated by using inverse methods once the appropriate relationship between inputs and results is clarified. Various inverse methods or parameter estimation techniques such as artificial neural network and least square method can be used depending on the characteristics of given problems. Numerical analyses, experiments, or monitoring results are frequently used to prepare a set of inputs and results to establish the back analysis models. In this study, a back analysis method has been developed to estimate geotechnically hard-to-known parameters such as permeability of tunnel filter, underground water table, long-term rock mass load, size of damaged zone associated with seepage and long-term underground motion. The artificial neural network technique is adopted and the numerical models developed in the first part are used to prepare a set of data for learning process. Tunnel behavior, especially the displacements of the lining, has been exclusively investigated for the back analysis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.5
• /
• pp.1082-1090
• /
• 2009

Peak expiratory flow rate(PEF) is a very important diagnostic parameter obtained from the forced vital capacity(FVC) test. The expiratory flow rate increases during the short initial time period and may cause measurement error in PEF particularly due to non-ideal dynamic characteristic of the transducer. The present study evaluated the initial rise slope($S_r$) on the flow rate signal to compensate the transducer output data. The 26 standard signals recommended by the American Thoracic Society(ATS) were generated and flown through the velocity-type respiratory air flow transducer with simultaneously acquiring the transducer output signal. Most PEF and the corresponding output($N_{PEF}$) were well fitted into a quadratic equation with a high enough correlation coefficient of 0.9997. But only two(ATS#2 and 26) signals resulted significant deviation of $N_{PEF}$ with relative errors>10%. The relationship between the relative error in $N_{PEF}$ and $S_r$ was found to be linear, based on which $N_{PEF}$ data were compensated. As a result, the 99% confidence interval of PEF error was turned out to be approximately 2.5%, which was less than a quarter of the upper limit of 10% recommended by ATS. Therefore, the present compensation technique was proved to be very accurate, complying the international standards of ATS, which would be useful to calibrate respiratory air flow transducers.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.3
• /
• pp.75-85
• /
• 2009

This work proposes a 13b 100MS/s 0.13um CMOS ADC for 3G communication systems such as two-carrier W-CDMA applications simultaneously requiring high resolution, low power, and small size at high speed. The proposed ADC employs a four-step pipeline architecture to optimize power consumption and chip area at the target resolution and sampling rate. Area-efficient high-speed high-resolution gate-bootstrapping circuits are implemented at the sampling switches of the input SHA to maintain signal linearity over the Nyquist rate even at a 1.0V supply operation. The cascode compensation technique on a low-impedance path implemented in the two-stage amplifiers of the SHA and MDAC simultaneously achieves the required operation speed and phase margin with more reduced power consumption than the Miller compensation technique. Low-glitch dynamic latches in sub-ranging flash ADCs reduce kickback-noise referred to the differential input stage of the comparator by isolating the input stage from output nodes to improve system accuracy. The proposed low-noise current and voltage references based on triple negative T.C. circuits are employed on chip with optional off-chip reference voltages. The prototype ADC in a 0.13um 1P8M CMOS technology demonstrates the measured DNL and INL within 0.70LSB and 1.79LSB, respectively. The ADC shows a maximum SNDR of 64.5dB and a maximum SFDR of 78.0dB at 100MS/s, respectively. The ABC with an active die area of $1.22mm^2$ consumes 42.0mW at 100MS/s and a 1.2V supply, corresponding to a FOM of 0.31pJ/conv-step.

• Journal of radiological science and technology
• /
• v.28 no.4
• /
• pp.293-299
• /
• 2005

In the present investigation, we analyzed the data of 1,318 patients (2,636 images) who underwent mammographic examinations and obtained the distribution of the patient age and compressed breast thickness. We measured also average glandular doses (AGD) as function of compressed breast thickness. In order to obtain the values of AGD, we measured half value layer (HVL) and tube output (mR/mAs) for each kVp and target/filter combination. Entrance surface air kerma (ESAK) was calculated from the tube output as measured for each voltage used under clinical conditions and from the tube loading (mAs). AGD per exposure were calculated by multiplying the ESAK values by the conversion factors tabulated by Dance. We obtained in this study the following conclusions. The mean value of compressed breast thickness for cranio-caudal (CC) view was 35.8mm and that for medio-lateral oblique (MLO) view was 43.3 mm. The mean value of AGD for CC view was 1.55 mGy and that for MLO view was 1.70 mGy. The AGD for MLO view was 0.15 mGy (10%) higher than that for CC view because the thickness for MLO view was on average 4.8 mm higher than that for CC view. The values of AGD increased with increasing compressed brest thickness. The increased AGD value was on average 0.34 mGy per 10 mm in the thickness ranges $10{\sim}80\;mm$, therefore differences between the AGD values of each thickness were relative large. Thus, it is considered to need limited doses for mammography with the upper end of exposure range at several different compressed brest thickness.

• Journal of radiological science and technology
• /
• v.37 no.3
• /
• pp.187-193
• /
• 2014

The purpose of this study was to analyze the effect on the selectivity on of high-voltage rectification device that measured the performance of the grid, and the contrast improvement ability (K factor) by measuring the scattered radiation content of the transmitted X-rays. The scattered radiation generated when the X-ray flux comes from the diagnostic X-ray generator that passes through an object. Targeting four different rectifications of X-ray generators, the mean value of the tube voltage and the tube current was measured in order to maximize the accuracy of the generating power dose within the same exposure condition. Using fluorescence meter, the content of the scattered rays that are transmitted through the acrylic was measured depending on the grid usage. When grid is not used, the content of the scattered rays was the lowest (34.158%) with the single-phase rectifier, was increased with the inverter rectifier (37.043%) and the three-phase 24-peak rectification method (37.447%). The difference of the scattered radiation content of each device was significant from the lowest 0.404% to the highest 3.289% while using 8:1 grid, the content of the scattered ray was the lowest with the single content of the scattered ray was the lowest with the single-phase rectifier (18.258%), was increased with the rectifier (25.502%) and the 24-peaks rectification (24.217%). Furthermore, there was difference up to content 7.244% to the lowest content 1.285% within three-phase 24-peaks rectification, inverter rectifications, and single-phase rectifier depending on the selectivity of the grid. Drawn from the statistical analysis, there was a similar relationship between the contrast improvement factor and the K factor. As a result, the grid selectivity and the contrast were increased within the single-phase rectifier rather than the constant voltage rectifier.

• Progress in Medical Physics
• /
• v.22 no.3
• /
• pp.107-116
• /
• 2011

Respiratory gated radiation therapy and stereotactic body radiation therapy require identical tumor motions during each treatment with the motion detected in treatment planning CT. Therefore, this study developed a tumor motion monitoring and analysis system during the treatments employing RPM data, gated setup OBI images and a data analysis software. A respiratory training and guiding program which improves the regularity of breathing was used to patients. The breathing signal was obtained by RPM and the recorded data in the 4D console was read after treatment. The setup OBI images obtained gated at 0% and 50% of breathing phases were used to detect the tumor motion range in crenio-caudal direction. By matching the RPM data recorded at the OBI imaging time, a factor which converts the RPM motion to the tumor motion was computed. RPM data was entered to the institute developed data analysis software and the maximum, minimum, average of the breathing motion as well as the standard deviation of motion amplitude and period was computed. The computed result is exported in an excel file. The conversion factor was applied to the analyzed data to estimate the tumor motion. The accuracy of the developed method was tested by using a moving phantom, and the efficacy was evaluated for 10 stereotactic body radiation therapy patients. For the sine wave motion of the phantom with 4 sec of period and 2 cm of peak-to-peak amplitude, the measurement was slightly larger (4.052 sec) and the amplitude was smaller (1.952 cm). For patient treatment, one patient was evaluated not to qualified to SBRT due to the usability of the breathing, and in one patient case, the treatment was changed to respiratory gated treatment due the larger motion range of the tumor than treatment planed motion. The developed method and data analysis program was useful to estimate the tumor motion during treatment.

• Progress in Medical Physics
• /
• v.16 no.2
• /
• pp.62-69
• /
• 2005

The purpose of this study has been performed to investigate the possibility of external audit program using thermoluminescence dosimetry for electron beam in korea. The TLD system consists of LiF powder, type TLD-700 read with a PCL 3 reader. In order to determine a calibration coefficient of the TLD system, the reference dosimeters are irradiated to 2 Gy in a $^{60}CO$ beam at the KFDA The irradiation is performed under reference conditions is water phantom using the IAEA standard holder for TLD of electron beam. The energy correction factor is determined for LiF powder irradiated of dose to water 2 Gy in electron beams of 6, 9, 12, 16 and 20 MeV (Varian CL 2100C). The dose is determined according to the IAEA TRS-398 and by measurement with a PTW Roos type plane-parallel chamber. The TLD for each electron energy are positioned in water at reference depth. In this study, to verify of the accuracy of dose determination by the TLD system are performed through a 'blind' TLD irradiation. The results of blind test are $2.98\%,\;3.39\%\;and\;0.01\%(1\sigma)$ at 9, 16, 20 MeV, respectively. The value generally agrees within the acceptance level of $5\%$ for electron beam. The results of this study prove the possibility of the TLD quality assurance program for electron beams. It has contributed to the improvement of clinical electron dosimetry in radiotherapy centers.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1107-1118
• /
• 2021

Climate change brought on by global warming increased the frequency of flood and drought on the Korean Peninsula, along with the casualties and physical damage resulting therefrom. Preparation and response to these water disasters requires national-level planning for water resource management. In addition, watershed-level management of water resources requires flow duration curves (FDC) derived from continuous data based on long-term observations. Traditionally, in water resource studies, physical rainfall-runoff models are widely used to generate duration curves. However, a number of recent studies explored the use of data-based deep learning techniques for runoff prediction. Physical models produce hydraulically and hydrologically reliable results. However, these models require a high level of understanding and may also take longer to operate. On the other hand, data-based deep-learning techniques offer the benefit if less input data requirement and shorter operation time. However, the relationship between input and output data is processed in a black box, making it impossible to consider hydraulic and hydrological characteristics. This study chose one from each category. For the physical model, this study calculated long-term data without missing data using parameter calibration of the Soil Water Assessment Tool (SWAT), a physical model tested for its applicability in Korea and other countries. The data was used as training data for the Long Short-Term Memory (LSTM) data-based deep learning technique. An anlysis of the time-series data fond that, during the calibration period (2017-18), the Nash-Sutcliffe Efficiency (NSE) and the determinanation coefficient for fit comparison were high at 0.04 and 0.03, respectively, indicating that the SWAT results are superior to the LSTM results. In addition, the annual time-series data from the models were sorted in the descending order, and the resulting flow duration curves were compared with the duration curves based on the observed flow, and the NSE for the SWAT and the LSTM models were 0.95 and 0.91, respectively, and the determination coefficients were 0.96 and 0.92, respectively. The findings indicate that both models yield good performance. Even though the LSTM requires improved simulation accuracy in the low flow sections, the LSTM appears to be widely applicable to calculating flow duration curves for large basins that require longer time for model development and operation due to vast data input, and non-measured basins with insufficient input data.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.