• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1181-1189
• /
• 2022

Clouds are composed of tiny water droplets, ice crystals, or mixtures suspended in the atmosphere and cover about two-thirds of the Earth's surface. Cloud detection in satellite images is a very difficult task to separate clouds and non-cloud areas because of similar reflectance characteristics to some other ground objects or the ground surface. In contrast to thick clouds, which have distinct characteristics, thin transparent clouds have weak contrast between clouds and background in satellite images and appear mixed with the ground surface. In order to overcome the limitations of transparent clouds in cloud detection, this study conducted cloud detection focusing on transparent clouds using machine learning techniques (Random Forest [RF], Convolutional Neural Networks [CNN]). As reference data, Cloud Mask and Cirrus Mask were used in MOD35 data provided by MOderate Resolution Imaging Spectroradiometer (MODIS), and the pixel ratio of training data was configured to be about 1:1:1 for clouds, transparent clouds, and clear sky for model training considering transparent cloud pixels. As a result of the qualitative comparison of the study, bothRF and CNN successfully detected various types of clouds, including transparent clouds, and in the case of RF+CNN, which mixed the results of the RF model and the CNN model, the cloud detection was well performed, and was confirmed that the limitations of the model were improved. As a quantitative result of the study, the overall accuracy (OA) value of RF was 92%, CNN showed 94.11%, and RF+CNN showed 94.29% accuracy.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.145-154
• /
• 2022

Automatic Target Recognition (ATR) technology is emerging as a core technology of Future Combat Systems (FCS). Conventional ATR is performed based on IMINT (image information) collected from the SAR sensor, and various image-based deep learning models are used. However, with the development of IT and sensing technology, even though data/information related to ATR is expanding to HUMINT (human information) and SIGINT (signal information), ATR still contains image oriented IMINT data only is being used. In complex and diversified battlefield situations, it is difficult to guarantee high-level ATR accuracy and generalization performance with image data alone. Therefore, we propose a knowledge graph-based ATR method that can utilize image and text data simultaneously in this paper. The main idea of the knowledge graph and deep model-based ATR method is to convert the ATR image and text into graphs according to the characteristics of each data, align it to the knowledge graph, and connect the heterogeneous ATR data through the knowledge graph. In order to convert the ATR image into a graph, an object-tag graph consisting of object tags as nodes is generated from the image by using the pre-trained image object recognition model and the vocabulary of the knowledge graph. On the other hand, the ATR text uses the pre-trained language model, TF-IDF, co-occurrence word graph, and the vocabulary of knowledge graph to generate a word graph composed of nodes with key vocabulary for the ATR. The generated two types of graphs are connected to the knowledge graph using the entity alignment model for improvement of the ATR performance from images and texts. To prove the superiority of the proposed method, 227 documents from web documents and 61,714 RDF triples from dbpedia were collected, and comparison experiments were performed on precision, recall, and f1-score in a perspective of the entity alignment..

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.925-938
• /
• 2022

Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.2
• /
• pp.78-95
• /
• 2024

For the establishment and comparison of environmental plans across various domains, considering climate change and urban issues, it is crucial to build spatial data at the regional scale classified with consistent criteria. This study mapping the Local Climate Zone (LCZ) of Changwon City, where active climate and environmental research is being conducted, using the protocol suggested by the World Urban Database and Access Portal Tools (WUDAPT). Additionally, to address the fragmentation issue where some grids are classified with different climate characteristics despite being in regions with homogeneous climate traits, a filtering technique was applied, and the LCZ classification characteristics were compared according to the filtering radius. Using satellite images, ground reference data, and the supervised classification machine learning technique Random Forest, classification maps without filtering and with filtering radii of 1, 2, and 3 were produced, and their accuracies were compared. Furthermore, to compare the LCZ classification characteristics according to building types in urban areas, an urban form index used in GIS-based classification methodology was created and compared with the ranges suggested in previous studies. As a result, the overall accuracy was highest when the filtering radius was 1. When comparing the urban form index, the differences between LCZ types were minimal, and most satisfied the ranges of previous studies. However, the study identified a limitation in reflecting the height information of buildings, and it is believed that adding data to complement this would yield results with higher accuracy. The findings of this study can be used as reference material for creating fundamental spatial data for environmental research related to urban climates in South Korea.

• Journal of Korea Water Resources Association
• /
• v.45 no.3
• /
• pp.301-316
• /
• 2012

Two models, TANK and SWAT (Soil and Water Assessment Tool) were compared for simulating natural flows in the Paldang Dam upstream areas of the Han River basin in order to understand the limitations of TANK and to review the applicability and capability of SWAT. For comparison, simulation results from the previous research work were used. In the results for the calibrated watersheds (Chungju Dam and Soyanggang Dam), two models provided promising results for forecasting of daily flows with the Nash-Sutcliffe model efficiency of around 0.8. TANK simulated observations during some peak flood seasons better than SWAT, while it showed poor results during dry seasons, especially its simulations did not fall down under a certain value. It can be explained that TANK was calibrated for relatively larger flows than smaller ones. SWAT results showed a relatively good agreement with observed flows except some flood flows, and simulated inflows at the Paldang Dam considering discharges from upper dams coincided with observations with the model efficiency of around 0.9. This accounts for SWAT applicability with higher accuracy in predicting natural flows without dam operation or artificial water uses, and in assessing flow variations before and after dam development. Also, two model results were compared for other watersheds such as Pyeongchang-A, Dalcheon-B, Seomgang-B, Inbuk-A, Hangang-D, and Hongcheon-A to which calibrated TANK parameters were applied. The results were similar to the case of calibrated watersheds, that TANK simulated poor smaller flows except some flood flows and had same problem of keeping on over a certain value in dry seasons. This indicates that TANK application may have fatal uncertainties in estimating low flows used as an important index in water resources planning and management. Therefore, in order to reflect actually complex and complicated physical characteristics of Korean watersheds, and to manage efficiently water resources according to the land use and water use changes with urbanization or climate change in the future, it is necessary to utilize a physically based watershed model like SWAT rather than an existing conceptual lumped model like TANK.

• Journal of Life Science
• /
• v.18 no.8
• /
• pp.1132-1139
• /
• 2008

A CpG island is a short stretch of DNA in which the frequency of the CG dinucleotide is higher than other regions. CpG islands are present in the promoters and exonic regions of approximately $30{\sim}60$% of mammalian genes so they are useful markers for genes in organisms containing 5-methylcytosine in their genomes. Recent evidence supports the notion that the hypermethylation of CpG island, by silencing tumor suppressor genes, plays a major causal role in cancer, which has been described in almost every tumor types. In this respect, CpG island search by computational methods is very helpful for cancer research and computational promoter and gene predictions. I therefore developed a window program (called CpGi) on the basis of CpG island criteria defined by D. Takai and P. A. Jones. The program 'CpGi' was implemented in Visual C++ 6.0 and can determine the locations of CpG islands using diverse parameters (%GC, Obs (CpG)/Exp (CpG), window size, step size, gap value, # of CpG, length) specified by user. The analysis result of CpGi provides a graphical map of CpG islands and G+C% plot, where more detailed information on CpG island can be obtained through pop-up window. Two human contigs, i.e. AP00524 (from chromosome 22) and NT_029490.3 (from chromosome 21), were used to compare the performance of CpGi and two other public programs for the accuracy of search results. The two other programs used in the performance comparison are Emboss-CpGPlot and CpG Island Searcher that are web-based public CpG island search programs. The comparison result showed that CpGi is on a level with or outperforms Emboss-CpGPlot and CpG Island Searcher. Having a simple and easy-to-use user interface, CpGi would be a very useful tool for genome analysis and CpG island research. To obtain a copy of CpGi for academic use only, contact corresponding author.

• Journal of the Korean earth science society
• /
• v.40 no.6
• /
• pp.613-623
• /
• 2019

Over the past decades, daily sea surface temperature (SST) composite data have been produced using periodically and extensively observed satellite SST data, and have been used for a variety of purposes, including climate change monitoring and oceanic and atmospheric forecasting. In this study, we evaluated the accuracy and analyzed the error characteristic of the SST composite data in the sea around the Korean Peninsula for optimal utilization in the regional seas. We evaluated the four types of multi-satellite SST composite data including OSTIA (Operational Sea Surface Temperature and Sea Ice Analysis), OISST (Optimum Interpolation Sea Surface Temperature), CMC (Canadian Meteorological Centre) SST, and MURSST (Multi-scale Ultra-high Resolution Sea Surface Temperature) collected from January 2016 to December 2016 by using in-situ temperature data measured from the Ieodo Ocean Research Station (IORS). Each SST composite data showed biases of the minimum of 0.12℃ (OISST) and the maximum of 0.55℃ (MURSST) and root mean square errors (RMSE) of the minimum of 0.77℃ (CMC SST) and the maximum of 0.96℃ (MURSST) for the in-situ temperature measurements from the IORS. Inter-comparison between the SST composite fields exhibited biases of -0.38-0.38℃ and RMSE of 0.55-0.82℃. The OSTIA and CMC SST data showed the smallest error while the OISST and MURSST data showed the most obvious error. The results of comparing time series by extracting the SST data at the closest point to the IORS showed that there was an apparent seasonal variation not only in the in-situ temperature from the IORS but also in all the SST composite data. In spring, however, SST composite data tended to be overestimated compared to the in-situ temperature observed from the IORS.

• Journal of radiological science and technology
• /
• v.39 no.2
• /
• pp.149-156
• /
• 2016

Measurement of cardiac blood flow using the magnetic resonance imaging has been limited due to breathing and involuntary movements of the heart. The present study attempted to improve the accuracy of cardiac blood flow testing through phase contrast magnetic resonance imaging by presenting the adequate breathing method and imaging variables by comparing the measurement values of cardiac blood flow. Each was evaluated by comparing the breath hold retrospective 1NEX and non breath hold retrospective 1-3NEX in the ascending aorta and descending aorta. As a result, the average blood flow amount/velocity of the breath hold retrosepctive 1NEX method in the ascending aorta were $96.17{\pm}19.12ml/sec$, $17.04{\pm}4.12cm/sec$ respectively, which demonstrates a statistically significant difference(p<0.05) with the non-breath hold retrospective method 1NEX of $72.31{\pm}13.27ml$ and $12.32{\pm}3.85$. On the other hand, the average 2NEX blood flow and mean flow velocity is $101.90{\pm}24.09$, $16.84{\pm}4.32$, 3NEX $103.06{\pm}25.49$, $16.88{\pm}4.19$ did not show statistically significant differences(p>0.05).The average blood flow amount/ velocity of the breath hold retrospective 1NEX method in the descending aorta were $76.68{\pm}19.72ml/s$, and $22.23{\pm}4.8$, which did not demonstrate a significant difference in comparison to non-breath hold retrospective method 1-3 NEX. Therefore, the non breath hold retrospective method does not significantly differ in terms of cardiac blood flow in comparison with the breath hold retrospective method in accordance with the increase of NEX, so pediatric patients or patients who are not able to breathe well must have the diagnostic value of their cardiac blood flow tests improved.

• Radiation Oncology Journal
• /
• v.17 no.1
• /
• pp.78-83
• /
• 1999

Purpose : We have compared the characteristics of Siemens virtual wedge device with physical wedges for clinical application. Materials and Methods : We investigated the characteristics of virtual and physical wedges for various wedge angles (15, 30, 45, and 60$^{\circ}$) using 6- and 15MV photon beams. Wedge factors were measured in water using an ion chamber for various field sizes and depths. In case of virtual wedge device, as upper jaw moves during irradiation, wedge angles were estimated by accumulated doses. These measurements were performed at off-axis points perpendicular to the beam central axis in water for a 15cm${\times}$20cm radiation field size at the depth of loom. Surface doses without and with virtual or physical wedges were measured using a parallel plate ion chamber at surface. Field size was 15cm H20cm and a polystyrene phantom was used. Results : For various field sizes, virtual and physical wedge factors were changed by maximum 2.1% and 3.9%) , respectively. For various depths, virtual and physical wedge factors were changed by maximum 1.9% and 2.9%, respectively. No major difference was found between the virtual and physical wedge angles and the difference was within 0.5$^{\circ}$ . Suface dose with physical wedge was reduced by maximum 20% (x-ray beam :6 MV, wedge angle:45$^{\circ}$, 550: 80 cm) relative to one with virtual wedge or without wedge. Conclusions : Comparison of the characteristics of Siemens virtual wedge device with physical wedges was performed. Depth dependence of virtual wedge factor was smaller than that of physical wedge factor. Virtual and physical wedge factors were nearly independent of field sizes. The accuracy of virtual and physical wedge angles was excellent. Surface dose was found to be reduced using physical wedge.

• Nuclear Medicine and Molecular Imaging
• /
• v.43 no.5
• /
• pp.436-442
• /
• 2009

Purpose: We underwent this study to evaluate the diagnostic potential of I-123/I-131 metaiodobenzylguanidine (MIBG) scintigraphy alone in the initial diagnosis of pheochromocytoma, compared with biochemical test and anatomic imaging. Materials & Methods: Twenty two patients (M:F=13:9, Age: $44.3{\pm}\;19.3$ years) having the clinical evaluation due to suspicious pheochromocytoma received the biochemical test, anatomic imaging modality (CT and/or MRI) and I-123/I-131 MIBG scan for diagnosis of pheochromocytoma, prior to histopathological confirmation. MIBG scans were independently reviewed by 2 nuclear medicine physicians. Results: All patients were confirmed histopathologically by operation or biopsy (incisional or excisonal). In comparison of final diagnosis and findings of each diagnostic modality, the sensitivities of the biochemical test, anatomic imaging, and MIBG scan were 88.9%, 55.6%, and 88.9%, respectively. And the specificities of the biochemical test, anatomic imaging, and MIBG scan also were 69.2%, 69.2%, and 92.3%, respectively. MIBG scan showed one false positive (neuroblastoma) and one false negative finding. There was one patient with positive MIBG scan and negative findings of the biochemical test, anatomic imaging. Conclusion: Our data suggest that I-123/I-131 MIBG scan has higher sensitivity, specificity, positive predictive value, negative predictive value and accuracy than those of biochemical test and anatomic imaging. Thus, we expect that MIBG scan is e tectively used for initial diagnosis of pheochromocytoma alone as well as biochemical test and anatomic imaging.