• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.317-326
• /
• 2024

Biometric recognition is a technology that determines whether a person is identified by extracting information on a person's biometric and behavioral characteristics with a specific device. Cyber threats such as forgery, duplication, and hacking of biometric characteristics are increasing in the field of biometrics. In response, the security system is strengthened and complex, and it is becoming difficult for individuals to use. To this end, multiple biometric models are being studied. Existing studies have suggested feature fusion methods, but comparisons between feature fusion methods are insufficient. Therefore, in this paper, we compared and evaluated the fusion method of multiple biometric models using fingerprint, face, and iris images. VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, and Inception-v3 were used for feature extraction, and the fusion methods of 'Sensor-Level', 'Feature-Level', 'Score-Level', and 'Rank-Level' were compared and evaluated for feature fusion. As a result of the comparative evaluation, the EfficientNet-B7 model showed 98.51% accuracy and high stability in the 'Feature-Level' fusion method. However, because the EfficietnNet-B7 model is large in size, model lightweight studies are needed for biocharacteristic fusion.

• The Korean Journal of Nuclear Medicine
• /
• v.30 no.4
• /
• pp.541-547
• /
• 1996

The previous monoclonal antibody labeling method for bone marrow immunoscintigrapy was complicated and laborious for clinical application. Also it showed a relatively low labeling efficiency. To improve this procedure, we compared several direct labeling methods of $^{99m}Tc$. 1) The labeling efficiency in the method using gluconate as a transchelator was low (40-70%), but immunoscintigraphy using this radiotracer produced a clear image. 2) To improve labeling efficiency, ${\beta}$-mercaptoethanol was removed after reduction. The labeling efficiency was improved up to 70-80%, but the radioactivity of the blood pool was high. 3) The higest labeling efficiency (>90%) and best quality images could be obtained by using MDP as a transchelating agent. It did not require additional procedures for separation of labeled antibodies. The immunoreactivity of this antibody was 60%. Residual MDP which can be taken up by the bone could be removed by PD-10 column. The reduced antibodies were stable with a high labeling efficiency (>90%) for up to 47 days by deep freezing. We concluded that the improved procedure for $^{99m}Tc$ labeling of anti-NCA-95 monoclonal antibody using MDP as a transchelating agent will be a simple and useful method for clinical application.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.18 no.1
• /
• pp.98-103
• /
• 2014

Purpose: The effective half life of I-131 is useful to calculate radiation dose, period of hospitalization, and exposure dose of surrounding people from patient. However, it is difficult to measure. This study estimates the effective half life in whole body and thyroid in using of value of residual radioactivity obtained from the early and delay images of Dual time I-131 whole body scan. Also, the correlations between the effective half life and serum creatinine, GFR, and administration dose were investigated in this study. Materials and Methods: The targets were 50 patients administration high dose of I-131 from February to August in 2013, having normal range of serum creatinine and over $30{\mu}IU/mL$ of TSH levels. After administration radioactive I-131, the early scan in the 3rd day and the delay scan in the 5-6th days were performed. To measure the residual radioactivity in the whole body and thyroid, ROI was set and then background radioactivity was corrected to estimate. The effective half life was estimated by calculating the ratio of measured values between the early and delay images. To compare the effective half lives of the whole body and thyroid, it was analyzed by Independent t-test, and each correlation of the effective half life, GFR, serum creatinine, and the dose of administration were analyzed by calculating the pearson's correlation coefficient. All of the analysis were determined to be statistically significant when P<0.05. Results: The effective half life of the whole body was $17.06{\pm}5.50$ hours and of the thyroid was $17.22{\pm}5.41$ hours. The two effective half life did not show significant difference (P=0.887). As the value of GFR was increased, the effective half life of whole body (r=-0.407, P=0.003) and of thyroid (r=-0.473, P=0.001) were significantly decreased; as the value of serum creatinine was increased, the effective half life of whole body (r=0.309, P=0.029) and of thyroid (r=0.371, P=0.008) were significantly increased. In the administration dose, effective half life did not have correlations. Conclusion: The effective half life of I-131 of patients treated for their thyroids were estimated only by using the images of Dual time I-131 whole body scan. Also, the correlations with the effective life, GFR, and serum creatinine were examined. This study might be utilized for a study on optimization for the period of hospitalization of patients treated by high dose of I-131 and on evaluation for internal absorbed dose of MIRD schema in application of the effective half life.

• Journal of the Korean earth science society
• /
• v.40 no.5
• /
• pp.447-463
• /
• 2019

Sea surface wind is a fundamental element for understanding the oceanic phenomena and for analyzing changes of the Earth environment caused by global warming. Global research institutes have developed and operated scatterometers to accurately and continuously observe the sea surface wind, with the accuracy of approximately ${\pm}20^{\circ}$ for wind direction and ${\pm}2m\;s^{-1}$ for wind speed. Given that the spatial resolution of the scatterometer is 12.5-25.0 km, the applicability of the data to the coastal area is limited due to complicated coastal lines and many islands around the Korean Peninsula. In contrast, Synthetic Aperture Radar (SAR), one of microwave sensors, is an all-weather instrument, which enables us to retrieve sea surface wind with high resolution (<1 km) and compensate the sparse resolution of the scatterometer. In this study, we investigated the Geophysical Model Functions (GMF), which are the algorithms for retrieval of sea surface wind speed from the SAR data depending on each band such as C-, L-, or X-band radar. We reviewed in the simulation of the backscattering coefficients for relative wind direction, incidence angle, and wind speed by applying LMOD, CMOD, and XMOD model functions, and analyzed the characteristics of each GMF. We investigated previous studies about the validation of wind speed from the SAR data using these GMFs. The accuracy of sea surface wind from SAR data changed with respect to observation mode, GMF type, reference data for validation, preprocessing method, and the method for calculation of relative wind direction. It is expected that this study contributes to the potential users of SAR images who retrieve wind speeds from SAR data at the coastal region around the Korean Peninsula.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1475-1490
• /
• 2021

Detecting oil spill area using statistical characteristics of SAR images has limitations in that classification algorithm is complicated and is greatly affected by outliers. To overcome these limitations, studies using neural networks to classify oil spills are recently investigated. However, the studies to evaluate whether the performance of model shows a consistent detection performance for various oil spill cases were insufficient. Therefore, in this study, two CNNs (Convolutional Neural Networks) with basic structures(Simple CNN and U-net) were used to discover whether there is a difference in detection performance according to the structure of CNN and distribution characteristics of oil spill. As a result, through the method proposed in this study, the Simple CNN with contracting path only detected oil spill with an F1 score of 86.24% and U-net, which has both contracting and expansive path showed an F1 score of 91.44%. Both models successfully detected oil spills, but detection performance of the U-net was higher than Simple CNN. Additionally, in order to compare the accuracy of models according to various oil spill cases, the cases were classified into four different categories according to the spatial distribution characteristics of the oil spill (presence of land near the oil spill area) and the clarity of border between oil and seawater. The Simple CNN had F1 score values of 85.71%, 87.43%, 86.50%, and 85.86% for each category, showing the maximum difference of 1.71%. In the case of U-net, the values for each category were 89.77%, 92.27%, 92.59%, and 92.66%, with the maximum difference of 2.90%. Such results indicate that neither model showed significant differences in detection performance by the characteristics of oil spill distribution. However, the difference in detection tendency was caused by the difference in the model structure and the oil spill distribution characteristics. In all four oil spill categories, the Simple CNN showed a tendency to overestimate the oil spill area and the U-net showed a tendency to underestimate it. These tendencies were emphasized when the border between oil and seawater was unclear.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.609-625
• /
• 2022

Validation of satellite data products is critical for subsequent analysis that is based on the data. Particularly, performance of ocean color products in turbid and shallow near-land ocean areas has been questioned for long time for its difficulty that stems from the complex optical environment with varying distribution of water constituents. Furthermore, validation with ship-based or station-based measurements has also exhibited clear limitation in its spatial scale that is not compatible with that of satellite data. This study firstly performed validation of major GOCI-II products such as remote sensing reflectance, chlorophyll-a concentration, suspended particulate matter, and colored dissolved organic matter, using the in-situ measurements collected from ship-based field campaign. Secondly, this study also presents preliminary analysis on the use of drone images for product validation. Multispectral images were acquired from a MicaSense RedEdge camera onboard a UAV to compensate for the significant scale difference between the ship-based measurements and the satellite data. Variation of water radiance in terms of camera altitude was analyzed for future application of drone images for validation. Validation conducted with a limited number of samples showed that GOCI-II remote sensing reflectance at 555 nm is overestimated more than 30%, and chlorophyll-a and colored dissolved organic matter products exhibited little correlation with in-situ measurements. Suspended particulate matter showed moderate correlation with in-situ measurements (R²~0.6), with approximately 20% uncertainty.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.13 no.2
• /
• pp.69-78
• /
• 2011

Rice is one of the world's staple foods. Paddy rice fields have unique biophysical characteristics that the rice is grown on flooded soils unlike other crops. Information on the spatial distribution of paddy fields and the timing of irrigation are of importance to determine hydrological balance and efficiency of water resource management. In this paper, we detected the timing of irrigation and spatial distribution of paddy fields using the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor onboard the NASA EOS Aqua satellite. The timing of irrigation was detected by the combined use of MODIS-based vegetation index and Land Surface Water Index (LSWI). The detected timing of irrigation showed good agreement with field observations from two flux sites in Korea and Japan. Based on the irrigation detection, a land cover map of paddy fields was generated with subsidiary information on seasonal patterns of MODIS enhanced vegetation index (EVI). When the MODISbased paddy field map was compared with a land cover map from the Ministry of Environment, Korea, it overestimated the regions with large paddies but underestimated those with small and fragmented paddies. Potential reasons for such spatial discrepancies may be attributed to coarse pixel resolution (500 m) of MODIS images, uncertainty in parameterization of threshold values for discarding forest and water pixels, and the application of LSWI threshold value developed for paddy fields in China. Nevertheless, this study showed that an improved utilization of seasonal patterns of MODIS vegetation and water-related indices could be applied in water resource management and enhanced estimation of evapotranspiration from paddy fields.

• 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..

• Progress in Medical Physics
• /
• v.26 no.3
• /
• pp.168-177
• /
• 2015

For evaluating the treatment planning accurately, the quality assurance for treatment planning is recommended when patients were treated with IMRT which is complex and delicate. To realize this purpose, treatment plan quality assurance software can be used to verify the delivered dose accurately before and after of treatment. The purpose of this study is to evaluate the accuracy of treatment plan quality assurance software for each IMRT plan according to MLC DLG (dosimetric leaf gap). Novalis Tx with a built-in HD120 MLC was used in this study to acquire the MLC dynalog file be imported in MobiusFx. To establish IMRT plan, Eclipse RTP system was used and target and organ structures (multi-target, mock prostate, mock head/neck, C-shape case) were contoured in I'mRT phantom. To verify the difference of dose distribution according to DLG, MLC dynalog files were imported to MobiusFx software and changed the DLG (0.5, 0.7, 1.0, 1.3, 1.6 mm) values in MobiusFx. For evaluation dose, dose distribution was evaluated by using 3D gamma index for the gamma criteria 3% and distance to agreement 3 mm, and the point dose was acquired by using the CC13 ionization chamber in isocenter of I'mRT phantom. In the result for point dose, the mock head/neck and multi-target had difference about 4% and 3% in DLG 0.5 and 0.7 mm respectively, and the other DLGs had difference less than 3%. The gamma index passing-rate of mock head/neck were below 81% for PTV and cord, and multi-target were below 30% for center and superior target in DLGs 0.5, 0.7 mm, however, inferior target of multi-target case and parotid of mock head/neck case had 100.0% passing rate in all DLGs. The point dose of mock prostate showed difference below 3.0% in all DLGs, however, the passing rate of PTV were below 95% in 0.5, 0.7 mm DLGs, and the other DLGs were above 98%. The rectum and bladder had 100.0% passing rate in all DLGs. As the difference of point dose in C-shape were 3~9% except for 1.3 mm DLG, the passing rate of PTV in 1.0 1.3 mm were 96.7, 93.0% respectively. However, passing rate of the other DLGs were below 86% and core was 100.0% passing rate in all DLGs. In this study, we verified that the accuracy of treatment planning QA system can be affected by DLG values. For precise quality assurance for treatment technique using the MLC motion like IMRT and VMAT, we should use appropriate DLG value in linear accelerator and RTP system.

• Tuberculosis and Respiratory Diseases
• /
• v.40 no.4
• /
• pp.357-366
• /
• 1993

Background: Lung clearance of inhaled $^{99m}Tc$-DTPA reflects alveolar epithelial permeability and it had been reported as more sensitive than conventional pulmonary function tests in detecting lung epithelial damage. However, measuring lung clearance of inhaled $^{99m}Tc$-DTPA by gamma camera may not always reflect alveolar epithelial permeability exactly because it is influenced by mucociliary clearance depending on the site of particle deposition. Moreover, this method takes much time and patient's effort because he has to sit or lie still in front of the camera for a prolonged period. Most of the absorbed DTPA is excreted in urine within 24 hours and the amount of excreted DTPA in urine during the first few hours after inhalation is influenced by absorption rate which is correlated with the alveolar-epithelial permeability suggesting that the urinary excretion, especially in first few hours, may be an alternate index for lung clearance. The purpose of this study was to evaluate the usefulness of ratio of excreted $^{99m}Tc$-DTPA in 2 hour and 24 hour urine as an index of alveolar-epithelial damage. Methods: Pulmonary function tests including diffusing capacity and lung clearance of $^{99m}Tc$-DTPA measured by gama camera ($T_{1/2}$) and 2hr/24hr urine excretion ratio (Ratio) of inhaled $^{99m}Tc$-DTPA in 8 normal subjects and 14 patients with diffuse interstitial lung disease were compared. Results: 1) In the normal control, there was significant negative correlation between the $T_{1/2}$ and the Ratio (r=-0.77, p<0.05). In patients with diffuse interstitial lung disease, there also was significant negative correlation between $T_{1/2}$ and Ratio(r=-0.63, p<0.05). 2) In diffuse interstitial lung disease patients, the $T_{1/2}$ was $38.65{\pm}11.63$ min which was significantly lower than that of normal control, $55.53{\pm}11.15$ min and the Ratio was $52.15{\pm}10.07%$ also signifantly higher than that of the normal control, $40.43{\pm}5.53%$ (p<0.05). 3) There was no significant correlations between $T_{1/2}$ or Ratio and diffusing capactiy of lung in both patients and controls (p>0.05). Conclusion: These results suggests that 2hr/24hr urine excretion ratio of inhaled $^{99m}Tc$-DTPA is a useful simple bedside test in assessing alveolar epithelial permeability and that it may be used as an additive follow-up test in patients with diffuse interstitial lung disease complementing conventional pulmonary function tests.