• 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.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.551-561
• /
• 2023

In this study, we investigated the effects of the spectral fitting window and absorption cross-section on the retrieval of the formaldehyde (HCHO) slant column density (SCD) from the direct-sun measurement of pandora spectrometer system using differential optical absorption spectroscopy (DOAS). Pandora Level 1 data observed at Yonsei University in Seoul from October 12 to 31, 2022 were used. The HCHO column density was retrieved under eight ranges including the spectral fitting window used in the Second Cabauw Intercomparison campaign for Nitrogen Dioxide measuring Instruments (CINDI-2) and seven types of absorption cross-section composition. The spectral fitting window was selected from 336.5 to 359.0 nm with minimum residual and HCHO SCD error. When the nitrogen dioxide (NO2) absorption cross-section at 220 K was added to the cross-section composition used in the CINDI-2 campaign among seven types, the residual and HCHO SCD error were the smallest and the HCHO column density wasstably retrieved. The average HCHO SCD with the highest retrieval accuracy and the values retrieved under other conditions differed from a minimum of 4% to a maximum of 40%.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.3
• /
• pp.182-196
• /
• 2023

Accurate and timely estimation of crop yields is crucial for various purposes, including global food security planning and agricultural policy development. Remote sensing techniques, particularly using vegetation indices (VIs), have show n promise in monitoring and predicting crop conditions. However, traditional VIs such as the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) have limitations in capturing rapid changes in vegetation photosynthesis and may not accurately represent crop productivity. An alternative vegetation index, the near-infrared reflectance of vegetation (NIRv), has been proposed as a better predictor of crop yield due to its strong correlation with gross primary productivity (GPP) and its ability to untangle confounding effects in canopies. In this study, we investigated the potential of NIRv in estimating crop yield, specifically for corn and soybean crops in major crop-producing regions in 14 states of the United States. Our results demonstrated a significant correlation between the peak value of NIRv and crop yield/area for both corn and soybean. The correlation w as slightly stronger for soybean than for corn. Moreover, most of the target states exhibited a notable relationship between NIRv peak and yield, with consistent slopes across different states. Furthermore, we observed a distinct pattern in the yearly data, where most values were closely clustered together. However, the year 2012 stood out as an outlier in several states, suggesting unique crop conditions during that period. Based on the established relationships between NIRv peak and yield, we predicted crop yield data for 2022 and evaluated the accuracy of the predictions using the Root Mean Square Percentage Error (RMSPE). Our findings indicate the potential of NIRv peak in estimating crop yield at the county level, with varying accuracy across different counties.

• Journal of Digital Convergence
• /
• v.21 no.3
• /
• pp.33-39
• /
• 2023

This study is a performance evaluation of a blood sugar monitoring system that combines a PPG sensor, which is an evaluation device for blood glucose monitoring, and a DNN algorithm when monitoring capillary blood glucose. The study is a researcher-led clinical trial conducted on participants from September 2023 to November 2023. PPG-BGMS compared predicted blood sugar levels for evaluation using 1-minute heart rate and heart rate variability information and the DNN prediction algorithm with capillary blood glucose levels measured with a blood glucose meter of the standard personal blood sugar management system. Of the 100 participants, 50 had type 2 diabetes (T2DM), and the average age was 67 years (range, 28 to 89 years). It was found that 100% of the predicted blood sugar level of PPG-BGMS was distributed in the A+B area of the Clarke error grid and Parker(Consensus) error grid. The MARD value of PPG-BGMS predicted blood glucose is 5.3 ± 4.0%. Consequentially, the non-blood-based PPG-BGMS was found to be non-inferior to the instantaneous blood sugar level of the clinical standard blood-based personal blood glucose measurement system.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1053-1066
• /
• 2020

Sulfur dioxide (SO₂) is primarily released through industrial, residential, and transportation activities, and creates secondary air pollutants through chemical reactions in the atmosphere. Long-term exposure to SO₂ can result in a negative effect on the human body causing respiratory or cardiovascular disease, which makes the effective and continuous monitoring of SO₂ crucial. In South Korea, SO₂ monitoring at ground stations has been performed, but this does not provide spatially continuous information of SO₂ concentrations. Thus, this research estimated spatially continuous ground-level SO₂ concentrations at 1 km resolution over South Korea through the synergistic use of satellite data and numerical models. A stacking ensemble approach, fusing multiple machine learning algorithms at two levels (i.e., base and meta), was adopted for ground-level SO₂ estimation using data from January 2015 to April 2019. Random forest and extreme gradient boosting were used as based models and multiple linear regression was adopted for the meta-model. The cross-validation results showed that the meta-model produced the improved performance by 25% compared to the base models, resulting in the correlation coefficient of 0.48 and root-mean-square-error of 0.0032 ppm. In addition, the temporal transferability of the approach was evaluated for one-year data which were not used in the model development. The spatial distribution of ground-level SO₂ concentrations based on the proposed model agreed with the general seasonality of SO₂ and the temporal patterns of emission sources.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.6 no.1
• /
• pp.88-96
• /
• 1996

This study was conducted to establish model between lead and ZPP concentration in blood of workers exposed to lead. Workers employed in secondary smelting manufacturing industry showed $85.1{\mu}g/dl$ of blood lead level, exceeding $60{\mu}g/dl$, the Criteria for Removal defined by Occupational Safety and Health Act of Korea. Average blood lead level of workers in the battery manufacturing industry was $51.3{\mu}g/dl$, locating between $40{\mu}g/dl$ and $60{\mu}g/dl$, the Criteria for Requiring Medical Removal. Blood lead level of in the litharge and radiator manufacturing industry was below $40{\mu}g/dl$, the Criteria Requiring Temporary Medical Removal. Blood lead levels of workers by industry were Significantly different(p<0.05). 50(21 %) showed blood lead levels above $60{\mu}g/dl$, the Criteria for Removal and 66(27.7 %) showed blood lead levels between the Criteria for Requiring Medical Removal, $40-60{\mu}g/dl$. Thus, approximately 50 percent of workers indicated blood lead levels above $40{\mu}g/dl$, the Criteria Requiring Temporary Medical Removal and should receive medical examination and consultation including biological monitoring. Average ZPP level of workers employed in the secondary smelting industry was $186.2{\mu}g/dl$, exceeding above $150{\mu}g/dl$, the Criteria for Removal. Seventy seven of all workers(32.3 %) showed ZPP level above $100-150{\mu}g/dl$, the Criteria for Requiring Medical Removal. The most appropriate model for predicting ZPP in blood was log-linear regression model. Log linear regression models between lead and ZPP concentrations in blood was Log ZPP(${\mu}g/dl$) = -0.2340 + 1.2270 Log Pb-B(${\mu}g/dl$)(standard error of estimate: 0,089, ${\gamma}^2=0.4456$, n=238, P=0.0001), Blood-in-lead explained 44.56 % of the variance in log(ZPP in blood).

• Journal of Korean Society of Environmental Engineers
• /
• v.28 no.2
• /
• pp.223-228
• /
• 2006

High-performance liquid chromatography(HPLC) and fluorescence derivatization were applied for a trace-level N-nitrosodimethylamine(NDMA) analysis of water samples. Fluorescence intensity was optimized with the excitation wavelength of 340 nm and the emission wavelength of 530 nm. pH adjustment after denitrosation was necessary to get a maximum intensity at pH between 9 and 12. Maximum intensity was found with a dansyl chloride concentration of 330 to 500 mg/L. Percentile error in the water sample analyses through solid phase extraction was 12-162% and 6-23% for the lower concentration level(10-200 ng/L NDMA) and the higher level(100-1000 ng/L NDMA), respectively, showing more discrepancy in lower level. However, the average ratios of estimated NDMA to the standard NDMA were close to 1 for both concentration ranges, presenting this HPLC method could detect from tens to hundreds nanograms NDMA per liter. Accurate determination of NDMA, which was injected to a wastewater effluent, revealed the selectivity of fluorescence derivatization for the target compound(NDMA) in the presence of complex interfering compounds. The HPLC with fluorescence derivatization may be applicable for determining NDMA of water and wastewater samples fur various research purposes.

• The Journal of Society for e-Business Studies
• /
• v.22 no.1
• /
• pp.1-13
• /
• 2017

Though digital imaging devices such as smart phones, digital cameras and office scanners have improved significantly over the past years, they are seldom used for industrial application. This may be attributable to high level of quality and performance requirement for industrial application, but there lacks a test or an objective evaluation whether the upgraded performance of entry-level device is sufficiently enough to replace existing industrial equipments or not. If there exists an industrial application area where the applicability of entry-level equipment is proved by some objective tests, then companies will be able to reduce investment on expensive industrial equipment. In this study, applicability of entry-level digital devices for color difference discrimination of PVC (Polyvinyl chloride) color sheet is tested. By testing smart phone, digital camera, and office scanner for color difference discrimination, authors have found that office scanner shows consistent result with less measurement error. Additional experiment on comparing office scanner with industrial spectrophotometer has confirmed that there exists high correlation between the two devices' results. Based on this result, office scanner may be applicable to discriminate the color difference of PVC sheet instead of expensive industrial spectrophotometer if proper management criteria are established.

• Journal of Korea Water Resources Association
• /
• v.50 no.2
• /
• pp.111-119
• /
• 2017

The underflow type movable weirs were arranged in a multi-stage way along a reach at the Chiseong River, where flooding has been observed frequently. With management water level of the movable weirs the control effects of storage and flood were suggested and the control effects were compared with those of existed weir system. The water level for the targeted storage and flood elevation was suggested by building the artificial neural network model. When the underflow type of movable weirs were arranged in a multi-stage way, the peak flood elevation decreased by 68.28% in the downstream compared with the existed weir system, and the total storage of the target section of multi-stage movable weirs increased by 216%. As a result of numerical simulation to build the artificial neural network model, 60%, 20%, and 20% among 216 data were used for the training, validation, and test, respectively. The training result of mean square error was $0.1681m^2$ and the high coefficients of determination were 0.9961, 0.9967, and 0.9943 in the training, validation, and test, respectively. As a result the water level management of each movable weir for the controls of flood elevation in the targeted downstream and targeted storage was suggested by using the artificial neural network.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.49-56
• /
• 1999

In many continuous speech recognition systems based on HMMs, decision tree-based state tying has been used for not only improving the robustness and accuracy of context dependent acoustic modeling but also synthesizing unseen models. To construct the phonetic decision tree, standard method performs one-level pruning using just single Gaussian triphone models. In this paper, two novel approaches, two-level decision tree and multi-mixture decision tree, are proposed to get better performance through more accurate acoustic modeling. Two-level decision tree performs two level pruning for the state tying and the mixture weight tying. Using the second level, the tied states can have different mixture weights based on the similarities in their phonetic contexts. In the second approach, phonetic decision tree continues to be updated with training sequence, mixture splitting and re-estimation. Multi-mixture Gaussian as well as single Gaussian models are used to construct the multi-mixture decision tree. Continuous speech recognition experiment using these approaches on BN-96 and WSJ5k data showed a reduction in word error rate comparing to the standard decision tree based system given similar number of tied states.