• Korean Journal of Cognitive Science
• /
• v.3 no.1
• /
• pp.61-78
• /
• 1991

This paper descibes the study of application of a modified Neocognitron model with backward path for the recognition of Hangul(Korean) syllabic characters. In this original report, Fukushima demonstrated that Neocognitron can recognize hand written numerical characters of $19{\times}19$ size. This version accepts $61{\times}61$ images of handwritten Hangul syllabic characters or a part thereof with a mouse or with a scanner. It consists of an input layer and 3 pairs of Uc layers. The last Uc layer of this version, recognition layer, consists of 24 planes of $5{\times}5$ cells which tell us the identity of a grapheme receiving attention at one time and its relative position in the input layer respectively. It has been trained 10 simple vowel graphemes and 14 simple consonant graphemes and their spatial features. Some patterns which are not easily trained have been trained more extrensively. The trained nerwork which can classify indivisual graphemes with possible deformation, noise, size variance, transformation or retation wre then used to recongnize Korean syllabic characters using its selective attention mechanism for image segmentation task within a syllabic characters. On initial sample tests on input characters our model could recognize correctly up to 79%of the various test patterns of handwritten Korean syllabic charactes. The results of this study indeed show Neocognitron as a powerful model to reconginze deformed handwritten charavters with big size characters set via segmenting its input images as recognizable parts. The same approach may be applied to the recogition of chinese characters, which are much complex both in its structures and its graphemes. But processing time appears to be the bottleneck before it can be implemented. Special hardware such as neural chip appear to be an essestial prerquisite for the practical use of the model. Further work is required before enabling the model to recognize Korean syllabic characters consisting of complex vowels and complex consonants. Correct recognition of the neighboring area between two simple graphemes would become more critical for this task.

• Radiation Oncology Journal
• /
• v.17 no.1
• /
• pp.84-88
• /
• 1999

Purpose :To develop a method for verifying a treatment setup in stereotactic radiotherapy by ma- tching portal images to DRRs. Materials and Methods : Four pairs of orthogonal portal images of one patient immobilized by a thermoplastic mask frame for fractionated stereotactic radiotherapy were compared with DRRs. Portal images are obtained in AP (anteriorfposterior) and lateral directions with a target localizer box containing fiducial markers attached to a stereotactic frame. DRRs superimposed over a planned iso-center and fiducial markers are printed out on transparent films. And then, they were overlaid over onhogonal penal images by matching anatomical structures. From three different kind of objects (isgcenter, fiducial markers, anatomical structure) on DRRs and portal images, the displacement error between anatomical structure and isocenters (overall setup error), the displacement error between anatomical structure and fiducial markers (irnrnobiliBation error), and the displacement error between fiducial markers and isocenters (localization error) were measured. Results : Localization error were 1.5$\pm$0.3 mm (AP), 0.9$\pm$0.3 mm (lateral), and immobilization errors were 1.9$\pm$0.5 mm (AP), 1.9$\pm$0.4 mm (lateral). In addition, overall setup errors were 1.0$\pm$0.9 mm (AP), 1.3$\pm$0.4 mm (lateral). From these orthogonal displacement errors, maximum 3D displacement errors($\sqrt{(\DeltaAP)^{2}+(\DeltaLat)^{2}$)) were found to be 1.7$\pm$0.4 mm for localization, 2.0$\pm$0.6 mm for immobilization, and 2.3$\pm$0.7 mm for overall treatment setup. Conclusion : By comparing orthogonal portal images with DRRs, we find out that it is possible to verify treatment setup directly in stereotactic radiotherapy.

• Economic and Environmental Geology
• /
• v.49 no.2
• /
• pp.121-134
• /
• 2016

We characterize the spatial distribution of Cobalt-rich ferromanganese crusts covering the summit and slopes of a seamount in the western Pacific, using acoustic backscatter from multibeam echo sounders (MBES) and seafloor video observation. Based on multibeam bathymetric data, we identify that ~70% of the summit area of this flattopped seamount has slope gradients less than $5^{\circ}$. The histogram of the backscatter intensity data shows a bi-modal distribution, indicating significant variations in seabed hardness. On the one hand, visual inspection of the seafloor using deep-sea camera data exhibits that the steep slope areas with high backscatter are mainly covered by manganese crusts. On the other hand, the visual analyses for the summit reveal that the summit areas with relatively low backscatter are covered by sediments. The other summit areas, however, exhibit high acoustic reflectivity due to coexistence of manganese crusts and sediments. Comparison between seafloor video images and acoustic backscatter intensity suggests that the central summit has relatively flat topography and low backscatter intensity resulting from unconsolidated sediments. In addition, the rim of the summit and the slopes are of high acoustic reflectivity because of manganese crusts and/or bedrock outcrops with little sediments. Therefore, we find a strong correlation between the acoustic backscatter data acquired from sea-surface multibeam survey and the spatial distribution of sediments and manganese crusts. We propose that analyzing acoustic backscatter can be one of practical methods to select optimal minable areas of the ferromanganese crusts from seamounts for future mining.

• The Korean Journal of Nuclear Medicine
• /
• v.32 no.3
• /
• pp.238-249
• /
• 1998

Purpose: To localize and compare the neural basis of verbal and visual human working memory, we performed functional activation study using $H_2^{15}O$ PET. Materials and Methods: Repeated $H_2^{15}O$ PET scans with one control and three different activation tasks were performed on six right-handed normal volunteers. Each activation task was composed of 13 match-ing trials. On each trial, four targets, a fixation dot and a probe were presented sequentially and subject's task was to press a response button to indicate whether or not the probe was one of the previous targets. Short meaningful Korean words, simple drawings and monochromic pictures of human faces were used as matching objects for verbal or visual memory. All the images were spatially normalized and the differences between control and activation states were statistically analyzed using SPM96. Results: Statistical analysis of verbal memory activation with short words showed activation in the left Broca's area, promoter cortex, cerebellum and right cingulate gyrus. In verbal memory with simple drawings, activation was shown in the larger regions including where activated with short words and left superior temporal cortex, basal ganglia, thalamus, prefrontal cortex, anterior portion of right superior temporal gyrus and right infero-lateral frontal cortex. On the other hand, the visual memory task activated predominantly right-sided structures, especially inferior frontal cortex, supplementary motor cortex and superior parietal cortex. Conclusion: The results are consistent with the hypothesis of the laterality and dissociation of the verbal and visual working memory from the invasive electrophysiological studies and emphasize the pivotal role of frontal cortex and cingulate gyrus in working memory system.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1657-1667
• /
• 2021

Anthropogenic activities and natural processes have been causes of land subsidence which is sudden sinking or gradual settlement of the earth's solid surface. Mexico City, the capital of Mexico, is one of the most severe land subsidence areas which are resulted from excessive groundwater extraction. Because groundwater is the primary water resource occupies almost 70% of total water usage in the city. Traditional terrestrial observations like the Global Navigation Satellite System (GNSS) or leveling survey have been preferred to measure land subsidence accurately. Although the GNSS observations have highly accurate information of the surfaces' displacement with a very high temporal resolution, it has often been limited due to its sparse spatial resolution and highly time-consuming and high cost. However, space-based synthetic aperture radar (SAR) interferometry has been widely used as a powerful tool to monitor surfaces' displacement with high spatial resolution and high accuracy from mm to cm-scale, regardless of day-or-night and weather conditions. In this paper, advanced interferometric approaches have been applied to get a time-series of land subsidence of Mexico City using four-year-long twenty ALOS PALSAR L-band observations acquired from Feb-11, 2007 to Feb-22, 2011. We utilized persistent scatterer interferometry (PSI) and small baseline subset (SBAS) techniques to suppress atmospheric artifacts and topography errors. The results show that the maximum subsidence rates of the PSI and SBAS method were -29.5 cm/year and -27.0 cm/year, respectively. In addition, we discuss the different subsidence rates where the study area is discriminated into three districts according to distinctive geotechnical characteristics. The significant subsidence rate occurred in the lacustrine sediments with higher compressibility than harder bedrock.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.23 no.1
• /
• pp.75-79
• /
• 2019

Purpose Cadmium-zinc-telluride (CZT) camera with semiconductor detector is capable of dynamic myocardial perfusion SPECT for coronary flow reserve (CFR). Image acquisition with the heart positioned within 2 cm in the center of the quality field of view (QFOV) is recommended because the CZT detector based on focused multi-pinhole collimators and is stationary gantry without rotation. The aim of this study was to investigate the optimal method for measuring position of the heart within the center of the QFOV when performing dynamic myocardial perfusion SPECT with the Discovery NM 530c camera. Materials and Methods From June to September 2018, 45 patients were subject to dynamic myocardial perfusion SPECT with D530c. For accurate heart positioning, the patient's heart was scanned with a mobile ultrasound and marked at the top of the probe where the mitral valve (MV) was visible in the parasternal long-axis view (PLAX). And, the marked point on the patient's body matched with the reference point indicated CZT detector in dynamic stress. The heart was positioned to be in the center of the QFOV in rest. The coordinates of dynamic stress and rest were compared statistically. Results The coordinates of the dynamic stress using mobile ultrasound and those taken of the rest were recorded for comparative analysis with regard to the position of the couch and analyzed. There were no statistically significant differences in the coordinates of Table in & out, Table up & down, and Detector in & out (P > 0.05). The difference in distance between the 2 groups was measured at $0.25{\pm}1.00$, $0.24{\pm}0.96$ and $0.25{\pm}0.82cm$ respectively, with no difference greater than 2 cm in all categories. Conclusion The position of the heart taken using mobile ultrasound did not differ significantly from that of the center of the QFOV. Therefore, The use of mobile ultrasound in dynamic stress will help to select the correct position of the heart, which will be effective in clinical diagnosis by minimizing the image quality improvement and the patient's exposure to radiation.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.419-430
• /
• 2021

Remote sensing techniques using drone-based multispectral image were studied for fast and two-dimensional monitoring of algal blooms in the river. Drone is anticipated to be useful for algal bloom monitoring because of easy access to the field, high spatial resolution, and lowering atmospheric light scattering. In addition, application of multispectral sensors could make image processing and analysis procedures simple, fast, and standardized. Spectral indices derived from the active spectrum of photosynthetic pigments in terrestrial plants and phytoplankton were tested for estimating chlorophyll-a concentrations (Chl-a conc.) from drone-based multispectral image. Spectral indices containing the red-edge band showed high relationships with Chl-a conc. and especially, 3-band model (3BM) and normalized difference chlorophyll index (NDCI) were performed well (R²=0.86, RMSE=7.5). NDCI uses just two spectral bands, red and red-edge, and provides normalized values, so that data processing becomes simple and rapid. The 3BM which was tuned for accurate prediction of Chl-a conc. in productive water bodies adopts originally two spectral bands in the red-edge range, 720 and 760 nm, but here, the near-infrared band replaced the longer red-edge band because the multispectral sensor in this study had only one shorter red-edge band. This index is expected to predict more accurately Chl-a conc. using the sensor specialized with the red-edge range.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.515-530
• /
• 2021

This study is to estimate soil moisture (SM) using Sentinel-1A/B C-band SAR (synthetic aperture radar) images and Multiple Linear Regression Model(MLRM) in the Yongdam-Dam watershed of South Korea. Both the Sentinel-1A and -1B images (6 days interval and 10 m resolution) were collected for 5 years from 2015 to 2019. The geometric, radiometric, and noise corrections were performed using the SNAP (SentiNel Application Platform) software and converted to backscattering coefficient of VV and VH polarization. The in-situ SM data measured at 6 locations using TDR were used to validate the estimated SM results. The 5 days antecedent precipitation data were also collected to overcome the estimation difficulty for the vegetated area not reaching the ground. The MLRM modeling was performed using yearly data and seasonal data set, and correlation analysis was performed according to the number of the independent variable. The estimated SM was verified with observed SM using the coefficient of determination (R²) and the root mean square error (RMSE). As a result of SM modeling using only BSC in the grass area, R² was 0.13 and RMSE was 4.83%. When 5 days of antecedent precipitation data was used, R² was 0.37 and RMSE was 4.11%. With the use of dry days and seasonal regression equation to reflect the decrease pattern and seasonal variability of SM, the correlation increased significantly with R² of 0.69 and RMSE of 2.88%.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.4
• /
• pp.100-118
• /
• 2015

This study established a land-cover classification method on objects using satellite images, and figured out distributional patterns of land cover according to categories through spatial statistics techniques. Object-based classification generated each land cover classification map by spectral information, texture information, and the combination of the two. Through assessment of accuracy, we selected optimum land cover classification map. Also, to figure out spatial distribution pattern of land cover according to categories, we analyzed hot spots and quantified them. Optimal weight for an object-based classification has been selected as the Scale 52, Shape 0.4, Color 0.6, Compactness 0.5, Smoothness 0.5. In case of using the combination of spectral information and texture information, the land cover classification map showed the best overall classification accuracy. Particularly in case of dry fields, protected cultivation, and bare lands, the accuracy has increased about 12 percent more than when we used only spectral information. Forest, paddy fields, transportation facilities, grasslands, dry fields, bare lands, buildings, water and protected cultivation in order of the higher area ratio of DMZ according to categories. Particularly, dry field sand transportation facilities in Yanggu occurred mainly in north areas of the civilian control line. dry fields in Cheorwon, forest and transportation facilities in Inje fulfilled actively in south areas of the civilian control line. In case of distributional patterns according to categories, hot spot of paddy fields, dry fields and protected cultivation, which is related to agriculture, was distributed intensively in plains of Yanggu and in basin areas of Cheorwon. Hot spot areas of bare lands, waters, buildings and roads have similar distribution patterns with hot spot areas related to agriculture, while hot spot areas of bare lands, water, buildings and roads have different distributional patterns with hot spot areas of forest and grasslands.

• Journal of radiological science and technology
• /
• v.30 no.2
• /
• pp.129-138
• /
• 2007

The Purpose of this study is to suggest the basic data for making good quality image and maintaining equipment homeostasis by accepting image quality evaluation and radiation dose evaluation in Multi-detector CT. In this study we surveyed 14 CT equipments in Seoul. The results obtained were as follows ; CT number was $0.56{\pm}0.70\;HU$. Noise was $0.39{\pm}0.09\;HU$. Uniformity was $1.08{\pm}0.52\;HU$. High contrast resolution was $0.48{\pm}0.05\;mm$ and low contrast resolution was $3.65{\pm}1.16\;mm$. For CTDI, the central part and the peripheral part of head phantom were $43.2{\pm}15.4\;mGy$ and $45.6{\pm}17.5\;mGy$, respectively. For body phantom, the central part and the peripheral part of head phantom were $13.5{\pm}4.5$ and $29.2{\pm}10.2\;mGy$, respectively. CTDIw was $44.8{\pm}16.8\;mGy$ and CTDIw/100 mAs was $18.8{\pm}5.3\;mGy$ using head phantom. CTDIW was $24.0{\pm}8.3\;mGy$ and CTDIw/100 mAs was $10.1{\pm}2.5\;mGy$ using body phantom. Therefore, CT number, noise, high contrast resolution, low contrast resolution, CTDI, CTDIw and CTDIw/100 mAs of MDCT were showed excellently in all equipments.