• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Journal of Korean Society of Forest Science
• /
• v.113 no.2
• /
• pp.222-238
• /
• 2024

Coniferous species in subalpine ecosystems are known to be highly sensitive to climate change. Therefore, it is becoming increasingly important to monitor community and population dynamics. This study monitored 37 plots within the distribution area of Abies koreana on Mt. Jirisan for a period of eight years. We analyzed the importance value, density of living stems, mortality rate, recruitment rate, basal area, DBH (diameter of breast height) class distribution, and tree health status. Our results showed changes in the importance value based on the tree stratum, with A. koreana decreasing by 3.6% and Tripterygium regelii increasing by 2.5% in the tree layer. Between 2015 and 2023, there were 149 dead trees/ha (17.99% mortality rate) and 12 living trees/ha (1.02% recruitment rate) of A. koreana. The decrease in basal area was attributed to a decrease in the number of living trees. Tree mortality occurred in all DBH classes, with a particularly high decline in the <10 cm class (65 trees/ha reduced). In terms of changes in tree health status, the population of alive standing (AS) type trees, initially consisting of 539 trees/ha, has been transformed into alive standing (AS), alive lean (AL), and death standing (DS), accounting for 69.7%, 0.5%, and 13.8%, respectively. Meanwhile, DS-type trees have transitioned into dead broken (DB) and dead fallen (DF) types. This phenomenon is believed to be caused by strong winds in the subalpine region that pull up the rootlets from the soil. Further research on this finding is recommended.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.387-396
• /
• 2024

Most very high-resolution (VHR) satellite images provide rational polynomial coefficients (RPC) data to facilitate the transformation between ground coordinates and image coordinates. However, initial RPC often contains geometric errors, necessitating correction through matching with ground control points (GCPs). A GCP chip is a small image patch extracted from an orthorectified image together with height information of the center point, which can be directly used for geometric correction. Many studies have focused on area-based matching methods to accurately align GCP chips with VHR satellite images. In cases with seasonal differences or changed areas, edge-based algorithms are often used for matching due to the difficulty of relying solely on pixel values. However, traditional edge extraction algorithms,such as canny edge detectors, require appropriate threshold settings tailored to the spectral characteristics of satellite images. Therefore, this study utilizes deep learning-based edge information that is insensitive to the regional characteristics of satellite images for matching. Specifically,we use a pretrained pixel difference network (PiDiNet) to generate the edge maps for both satellite images and GCP chips. These edge maps are then used as input for normalized cross-correlation (NCC) and relative edge cross-correlation (RECC) to identify the peak points with the highest correlation between the two edge maps. To remove mismatched pairs and thus obtain the bias-compensated RPC, we iteratively apply the data snooping. Finally, we compare the results qualitatively and quantitatively with those obtained from traditional NCC and RECC methods. The PiDiNet network approach achieved high matching accuracy with root mean square error (RMSE) values ranging from 0.3 to 0.9 pixels. However, the PiDiNet-generated edges were thicker compared to those from the canny method, leading to slightly lower registration accuracy in some images. Nevertheless, PiDiNet consistently produced characteristic edge information, allowing for successful matching even in challenging regions. This study demonstrates that improving the robustness of edge-based registration methods can facilitate effective registration across diverse regions.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.67-84
• /
• 2010

In terms of business, forecasting is a work of what is expected to happen in the future to make managerial decisions and plans. Therefore, the accurate forecasting is very important for major managerial decision making and is the basis for making various strategies of business. But it is very difficult to make an unbiased and consistent estimate because of uncertainty and complexity in the future business environment. That is why we should use scientific forecasting model to support business decision making, and make an effort to minimize the model's forecasting error which is difference between observation and estimator. Nevertheless, minimizing the error is not an easy task. Case-based reasoning is a problem solving method that utilizes the past similar case to solve the current problem. To build the successful case-based reasoning models, retrieving the case not only the most similar case but also the most relevant case is very important. To retrieve the similar and relevant case from past cases, the measurement of similarities between cases is an important key factor. Especially, if the cases contain symbolic data, it is more difficult to measure the distances. The purpose of this study is to improve the forecasting accuracy of case-based reasoning approach using fuzzy relation and composition. Especially, two methods are adopted to measure the similarity between cases containing symbolic data. One is to deduct the similarity matrix following binary logic(the judgment of sameness between two symbolic data), the other is to deduct the similarity matrix following fuzzy relation and composition. This study is conducted in the following order; data gathering and preprocessing, model building and analysis, validation analysis, conclusion. First, in the progress of data gathering and preprocessing we collect data set including categorical dependent variables. Also, the data set gathered is cross-section data and independent variables of the data set include several qualitative variables expressed symbolic data. The research data consists of many financial ratios and the corresponding bond ratings of Korean companies. The ratings we employ in this study cover all bonds rated by one of the bond rating agencies in Korea. Our total sample includes 1,816 companies whose commercial papers have been rated in the period 1997~2000. Credit grades are defined as outputs and classified into 5 rating categories(A1, A2, A3, B, C) according to credit levels. Second, in the progress of model building and analysis we deduct the similarity matrix following binary logic and fuzzy composition to measure the similarity between cases containing symbolic data. In this process, the used types of fuzzy composition are max-min, max-product, max-average. And then, the analysis is carried out by case-based reasoning approach with the deducted similarity matrix. Third, in the progress of validation analysis we verify the validation of model through McNemar test based on hit ratio. Finally, we draw a conclusion from the study. As a result, the similarity measuring method using fuzzy relation and composition shows good forecasting performance compared to the similarity measuring method using binary logic for similarity measurement between two symbolic data. But the results of the analysis are not statistically significant in forecasting performance among the types of fuzzy composition. The contributions of this study are as follows. We propose another methodology that fuzzy relation and fuzzy composition could be applied for the similarity measurement between two symbolic data. That is the most important factor to build case-based reasoning model.

• Journal of the Korean Society of Radiology
• /
• v.15 no.7
• /
• pp.991-998
• /
• 2021

The purpose of this study is to investigate the image quality of the SE-EPI and SSH-TSE technique for MR DWI. Datum were analyzed for 35 PACS transmission datum(Normal part: 12 males, 13 females, Cerebral Infarction: 10(5males and 5females), and average age 68±7.32), randomly selected patients who underwent MRDWI tests. The equipment used was Ingenia CX 3.0T, SSH_TSE and SE-EPI pulse sequence and 32 Ch. head coil were used for data acquisition. Image evaluation was performed on the paired t-test and Wilcoxon tests, and was considered significant when the p value was 0.05 or less. As a result of quantitative analysis of SNR for DWI images, the mean and standard deviation values of 4 parts (WM, GM, BG, Cerebellum) in ADC (s/mm2), Diffusion b=0, 1000 images were higher in SE-EPI techniques(ADC: 120.50 ± 40, b=0: 54.50 ± 35.91, b=1000: 91.61 ± 36.63) than in SSH-TSE techniques(ADC: 99.69 ± 31.10, b=0: 43.52 ± 25.00 , b=1000: 60.74 ± 24.85)(p<0.05). The CNR values for GM-WM, BG-WM sites were also higher in SE-EPI technique (ADC: 116.08 ± 43.30, b=0:27.23 ± 09.10, b=1000: 78.50 ± 16.56) than in SSH-TSE(ADC: 101.08 ± 36.81, b=0: 23.96 ± 07.79 , b=1000: 74.30 ± 14.22). As a visual evaluation of observers, ghost artifact, magnetic susceptibility artifacts and overall image quality for SE-TSE and SSH-TSE all yielded high results from SSH-TSE techniques(ADC:3.6 ± 0.1, 2.8 ± 0.2, b=0: 4.3 ± 0.3, 3.4 ± 0.1 b=1000: 4.3 ± 0.2, 3.5 ± 0.2, p=0.000). In conclusion, the SE-EPI technique obtained an superiority in SNR and CNR measurements using SSH-TSE, SE-EPI. In the qualitative analysis, the SSH-TSE pulse sequence was obtained a high result according to the pulse sequence characteristics.

• Korean Journal of Clinical Laboratory Science
• /
• v.47 no.4
• /
• pp.216-224
• /
• 2015

This study aims to identify the prevalence of sleep related disease in those who experienced car accidents caused by drowsy driving. To this end, a survey of usual sleep habits, polysomnography, and multiple sleep latency tests were conducted in 34 persons who experienced an accident after normal sleep (Group 1), 22 persons who experienced an accident after abnormal sleep (Group 2), and 17 persons who was proven to be normal as a result of polysomnography and had no accident (Group 3). In all, 192 persons responded to the preliminary survey and the results were compared and analyzed. Crossover analysis was conducted to test the homogeneity of statistical characteristics, and the physical characteristics by age were analyzed. In the survey of sleeping habits, there was a significance between groups in how often they woke up while asleep (p<0.01), how difficult it was to go back to sleep again after waking up from sleep (p<0.05), how early they woke up in the morning (p<0.05), how difficult it was to get up in the morning (p<0.05), how sleepy they felt in the daytime (p<0.01), and how tired they felt in the daytime (p<0.01). Furthermore, among 56 subjects who had an accident during drowsy driving, 94.6% (53 persons) were found to have sleep related diseases. This suggests that car accidents during drowsy driving is not simply caused by temporary lack of sleep but by sleep related diseases even when sleep is adequate, leading to car accidents. Therefore, this study is significant identifying the association between car accidents during drowsy driving and sleep related disorders. Furthermore, the data would be considered basic to prepare social measures against drowsy driving related to such sleep related disorders.

• Science of Emotion and Sensibility
• /
• v.9 no.spc3
• /
• pp.167-177
• /
• 2006

In this study, we developed a tool for measuring user's emotions expressed while using a product in the natural and accessible environment for the design field. Also, using emotional word logging software VideoTAME, we measured a user's emotions expressed while using a product. In the testing module of VideoTAME, participants evaluate their emotional changes through playing and watching the video clips of their performing tasks in the experiment room. In the analyzing module, the researchers replay the results created by participants during the experiment and analyze the results using Microsoft Excel. In this research, we have asked users to examine their emotional changes while watching the recorded video clip of them in the experiment room performing a series of tasks using a cellular phone. In this experiment, there were no big differences in the representative emotions expressed for each characteristics of task. The reason for this can be assumed it is because of the emotional changes occurred while facing specific situations when performing a task rather than the task itself. If more data is collected and concrete statistical analysis is done, it is expected that we can clarify what effect a product's usability has on user's emotions.

• International Commerce and Information Review
• /
• v.13 no.3
• /
• pp.403-431
• /
• 2011

The environmental issues including domestic measures to protect public life or health are generally easy to bring the tension between the WTO and its member countries. The standard of review, whether de novo review, total deference, or somewhere in between, is largely important in the WTO's adjudicating mechanism because it is closely related to the appropriate balance of power between sovereign nations and the WTO: The multilateral trading regime, through the proper standard of review, could harmoniously operated without interest conflicts among the member countries and at the same time between the WTO and the member countries. Irrespective the important function of the standard of review in the WTO judicial system, applicable standard of review has not been established in the current SPS Agreement. Furthermore, the nature of the SPS Agreement related in scientific factors, such as scientific experiment, data and assessment prevents the WTO's panel from applying consistent standard of review. Considering the judicial demand for the moderate treatment of the case under the SPS Agreement, this paper explores appropriate standard of review applicable the SPS-related environmental measures, particularly, by analysing the recent SPS-related dispute, US-Hormones Suspension.

• Analytical Science and Technology
• /
• v.6 no.5
• /
• pp.479-487
• /
• 1993

Potassium-Graphite Fiber Intercalation Compounds(K-GFIC) have been prepared from well oriented pitch-based Graphite fiber by the transformed two-bulbs method with variation of reaction temperatures of graphite($T_g$ : $450^{\circ}C$, $400^{\circ}C$, $350^{\circ}C$, $300^{\circ}C$, $250^{\circ}C$). The stage transition process of K-GFICs was studied by X-ray diffraction methods, and we have observed peaks with d-values of (001) diffraction of $5.40{\AA}$ and $8.78({\pm}0.01){\AA}$, which are charecteristic for the stage 1 and stage 2, respectively. The stage stability and energy states of K-GFICs were studied by UV/VIS spectrophotometer. As a results, We found that the minimum values of reflactance of K-GFICs with pure stage was moved to higher energy pristine Graphite fiber's. But because of mixtured stage, we could not observe minimum reflectance in the visible region at high reaction temperatures($400^{\circ}C$, $450^{\circ}C$). From X-ray diffraction and UV/VIS sepctrophotometry data, we can suggest that K-GFICs with lower stage has many charge carriers existed between C atoms of graphite Layers. And then, these results also provides information on the electrical and other physical properties of K-GFICs.

• Science of Emotion and Sensibility
• /
• v.21 no.2
• /
• pp.3-14
• /
• 2018

For satisfying consumer needs, commercial facilities require a variety of sale-related space expressions and eye-catching product arrangements; space composition can also be a direct marketing strategy. The human eye is the sensory organ that acquires the largest amount of information, and an analysis of visual information helps in understanding visual relations between . However, the existing studies are mostly focused on analysis of still frames in experimental images, and there is a lack of studies analyzing gaze information based on mobile images of commercial spaces. Therefore, this study analyzed emotional responses through gaze information of space users in reality using a video of a movement route through a commercial facility. The analysis targeted straight sections of the moving route; based on the data acquired, sectional characteristics of five gaze intensity ranges were examined. As a result, section A, the starting point of the route, had a low gaze intensity, while section B had the highest gaze intensity. This indicates that, starting in section B, the subjects explored the space in a stable way and needed time to adapt to the experimental video. In relation to space characteristics of the gaze-concentrated area, display formats of the right stores in 4 of 6 sections received greater attention. The gaze of consumers was mostly focused on props, and big gaze information was revealed in showcase display formats of the stores. In conclusion, this analysis method can provide highly useful direct design data about merchandise display and merchandise component arrangement based on consumer visual preference.