• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.118-127
• /
• 2010

Resistivity logging instruments are designed to measure the electrical resistivity of a formation, and this can be directly interpreted to provide a water-saturation profile. However, resistivity logs are sensitive to borehole and shoulder-bed effects, which often result in misinterpretation of the results. These effects are emphasised more in the presence of tool eccentricity. For precise interpretation of short- and long-normal logging measurements in the presence of tool eccentricity, we simulate and analyse eccentricity effects by combining the use of a Fourier series expansion in a new system of coordinates with a 2D goal-oriented high-order self-adaptive hp finite-element refinement strategy, where h denotes the element size and p the polynomial order of approximation within each element. The algorithm automatically performs local mesh refinement to construct an optimal grid for the problem under consideration. In addition, the proper combination of h and p refinements produces highly accurate simulations even in the presence of high electrical resistivity contrasts. Numerical results demonstrate that our algorithm provides highly accurate and reliable simulation results. Eccentricity effects are more noticeable when the borehole is large or resistive, or when the formation is highly conductive.

• Spatial Information Research
• /
• v.20 no.2
• /
• pp.13-24
• /
• 2012

To prevent the damage to human health by climate change, vulnerability assessment should be conducted for establishment of adaptation strategies. In this study, vulnerability assessment was conducted to provide information about vulnerable area for making adaptation policy. vulnerability assessment for human health was divided into three categories; extreme heat, ozone, and epidemic disease. To assess vulnerability, suitable indicators were selected by three criteria; sensitivity, adaptive capacity, and exposure, spatial data of indicators were prepared and processed using GIS technique. As a result, high vulnerability to extreme heat was shown in the low land regions of southern part. And vulnerability to harmful ozone was high in the surrounding area of Dae-gu basin and metropolitan area with a number of automobiles. Vulnerability of malaria and tsutsugamushi disease have a region-specific property. They were high in the vicinity of the Dimilitarized zone and south-western plain, respectively. In general, vulnerability of human health was increased in the future time. Vulnerable area was extended from south to central regions and from plain to low mountainous regions. For assessing vulnerability with high accuracy, it is necessary to prepare more related indicators and consider weight of indicators and use climate prediction data based on the newly released scenario when assessing vulnerability.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.496-500
• /
• 2009

소하천은 하천 네트워크의 최상류에 넓게 소재하는 하천이다. 본 연구의 목적은 올바른 소하천 수생태계 관리방안을 도출하기 위하여 소하천의 건강성을 분석하고 현행 소하천 관리제도의 개선점을 모색하는 것이었다. 본 연구에서는 다음과 같은 분석방법을 이용하였다. 첫째, 2007년 한강수계 소하천 28개 지점에서의 부착조류($DAI_{PO}$, TDI), 저서성 대형무척추동물(KSI), 어류(IBI), 서식환경, 수변환경 등 6개 항목에 대한 수생태 건강성 조사결과를 토대로 공간적 분포와 수질현황을 조사하여 소하천에 대한 종합적인 건강성 평가를 실시하였다. 둘째, 분석대상지역을 각각 소하천 구간스케일(28개 지점)과 유역스케일(팔당호, 안성천 유역)로 선정, 하천차수도(1:25,000)를 활용하여 해당 구간과 유역의 소하천도를 작성하였다. 셋째, 작성된 소하천도 는ArcGIS(ver. 9.3)에서 30, 60, 90, 120, 150-m Buffering을 하였다. 다음으로 소하천 구간은 중분류(23개 항목, $2000{\sim}2006$ 또는 2007년) 토지피복도를, 팔당호 및 안성천 유역의 소하천은 대분류(8개 항목, $1975{\sim}2000$년) 토지피복도를 적용하여 분류항목별 면적변화비율을 산정하였다. 끝으로 소하천 정비에 대한 제도적 문제점을 분석하여 소하천 관리의 개선점을 연구하였다. 그 연구 결과, 첫째 연구대상 소하천(28개)의 건강성은 도심 소하천에서 가장 낮게 조사되었고, 일부 소하천은 비록 상류에 위치함에도 불구하고 부착조류의 유기물, 영양염류 평가가 낮게 평가되었다. 둘째, 소하천 구간 스케일의 수변토지피복변화 분석결과 소하천 수생태 건강성은 거시적으로 산림, 도시화, 밭 등의 피복변화에 민감한 것으로 나타났으며 도시화 피복변화의 영향은 수변 30m에서 60m보다 3배 정도 큰 것으로 나타났다. 유역 스케일 분석에서는 상대적으로 도시화가 많이 진행된 안성천 유역의 소하천이 팔당호 유역보다 낮은 건강성일 것으로 예측되었다. 결론적으로 적절한 소하천 수변관리는 지역 하천의 건강성을 온전히 회복시키고 개선 유지하기 위한 중요한 수단들 중에 하나이며 수변토지피복의 변화율은 (소)하천 건강성 또는 유역관리의 지표로 활용될 수가 있는 것으로 조사되었다. 이와 더불어 본 연구를 통해 소하천 복원 및 관리는 소하천 특성을 고려한 장기적인 계획과 관리대상의 우선순위를 바탕으로 점진적인 대안마련이 필요할 것으로 사료된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.294-302
• /
• 2020

In a genetic algorithm, computer simulations are performed based on the natural evolution process of life, such as selection, crossover, and mutation. The genetic algorithm searches the approximate optimal solution by the parallel arrangement of Schema, which has a short definition length, low order, and high adaptability. This study examined the possibility of improving the efficiency of the optimal solution by considering the characteristics of the building block hypothesis, which are one of the key operating principles of a genetic algorithm. This study evaluated the efficiency of the optimization results according to the gene sequence for the implementation in solving problems. The optimal design problem of the water pipe was selected, and the genetic arrangement order reflected the engineering specificity by dividing into the existing, the network topology-based, and the flowrate-based arrangement. The optimization results with a flowrate-based arrangement were, on average, approximately 2-3% better than the other batches. This means that to increase the efficiency of the actual engineering optimization problem, a methodology that utilizes clear prior knowledge (such as hydraulic properties) to prevent such excellent solution characteristics from disappearing is essential. The proposed method will be considered as a tool to improve the efficiency of large-scale water supply network optimization in the future.

• Journal of the Korean association of regional geographers
• /
• v.16 no.2
• /
• pp.85-99
• /
• 2010

This study analyzes the geomorphic environments of river channels and properties of sediments in the Naeseong-River basin, a branch of Nakdong-River. While the area at NU1 located in the uppermost reaches indicates the landscapes with the gravel riverbeds, the sand riverbeds can be seen in the downstream of NU2 whose basin consists mostly of the granite regolith. The downstream of NU2 has the braided channels in the beds and this may be due to the large quantities of sand particles supply to the bed under the favorable geologic and geomorphic conditions, properties of river flowing within the floodplains less resistant to the erosion and great fluctuations of discharges. Whereas the river at NU2 may seem that sand particles are actively eroded during the high water-level periods, the particles may be actively deposited during the periods at NM2 and NL2. Moreover, in the reaches of NU2 to NM1 and NL1 to NL2, the mean grain sizes of sediments increase downstream suggesting the other supplies of coarse sediments from the lower order streams running the steep slopes because the river flows in the areas consisting of the metamorphic rocks rather than the granites and shows the properties of incised meander.

• Korean Chemical Engineering Research
• /
• v.48 no.1
• /
• pp.80-87
• /
• 2010

Lignite of low rank coal and petroleum coke of high sulfur content can be high potential energy sources for coal gasification process because of their plentiful supply. The kinetic study of steam gasification has been performed in an atmospheric thermobalance with wood chip, lignite, bituminous, anthracite, pet-coke. The effects of gasification temperature($600{\sim}850^{\circ}C$) and partial pressure of steam(30~90 kPa) on the gasification rate have been investigated. The modified volumetric reaction model was applied to the experimental data to describe the behavior of carbon conversion and to evaluate the needed kinetic parameters. Lignite and wood chip with high volatile content showed high average gasification rates comparing to other fuel and thus they might be proper fuel for gasification processes. The activation energies for wood chip, lignite, bituminous, anthracite, and pet-coke through Arrhenius plot were found to be 260.3, 167.9, 134.6, 82.2, 168.9 kJ/mol, respectively. The expression of apparent reaction rates for steam gasification of various chars have been proposed as basic information for the design of coal gasification processes.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.1
• /
• pp.49-60
• /
• 2017

In this paper, we presented the result of the study on high-power handling capability of the X-band circular waveguide cavity filter configured at the output of high power amplifier(120 W) for geostationary satellites. The dual mode circular waveguide cavity filter with 6th order is selected and the physical model of the filter is designed after determination of the size of resonator from mode chart. Multipactor margin analysis is performed by the SEM method and the VMF method. The result shows that the VMF method predicts lower multipactor breakdown thresholds than the SEM method. Evaluating the multipactor margin obtained by the VMF method to ECSS criteria, we could decide to perform multipactor test. The multipactor test conducted in ESA facility shows that multipactor did not occur even until the RF power increased up to 540 W. In consequence, by both analysis and test, we could verify that the X-band circular waveguide cavity filter has the sufficient high-power handling capability to operate on orbit.

• Culinary science and hospitality research
• /
• v.22 no.7
• /
• pp.58-71
• /
• 2016

This study aimed to gauge the public awareness of the cultural value and superiority of Korean traditional sweets. Furthermore, it evaluated the obstacles that the Korean traditional sweet industry faces in the modern society, and a method to popularize it. It also analyzed the awareness of Korean traditional sweets. Both male and female study subjects showed the highest awareness of yakgwa and the lowest of chasugwa. Female respondents showed significantly (p<0.05~p<0.001) higher awareness of Osaekdasik, Hukimjadasik, Bellflower-junggwa, and Genseng-junggwa than male respondents. Maejakgwa, Osaekdasik, Rice-dasik, and Hukimjada- sik showed significant difference in awareness by the area survey respondents originated. Contrarily, Walnut-gangjung had significantly (p<0.001) higher awareness in rural areas than in more urban areas (e.g., large cities and small and medium-sized cities). Both male and female respondents answered (OR indicated) that the obstacles facing the Korean traditional sweet industry are uncommon products and expensive price. Both male and female respondents said that they had Korean traditional sweets less because it was harder to purchase than western sweets (due to limited access to these sweets), less delicious, and too expensive. Both male and female respondenst suggested that the urgent tasks to popularize the Korean traditional sweets were diversification in shape and ingredient, developing various new flavors, and cheaper products. Both male and female respondents responded that product diversification and strengthened marketing were urgent tasks to industrialize Korean traditional sweets. Therefore, it was believed that failure in generalization was the urgent problem of the Korean traditional sweet industry, and that Korean traditional sweets were harder to purchase because of lower accessibility than western sweets. To popularize Korean traditional sweets, it may be necessary to develop sweets in various shapes and ingredients, flavors suiTable to modern people, become cheaper in price, and have fancier (OR better) packaging.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.3B
• /
• pp.277-284
• /
• 2011

The limitations of existing Markov chain model for reproducing extreme rainfalls are a known problem, and the problems have increased the uncertainties in establishing water resources plans. Especially, it is very difficult to secure reliability of water resources structures because the design rainfall through the existing Markov chain model are significantly underestimated. In this regard, aims of this study were to develop a new daily rainfall simulation model which is able to reproduce both mean and high order moments such as variance and skewness using a piecewise Kernel-Pareto distribution. The proposed methods were applied to summer and fall season rainfall at three stations in Han river watershed in Korea. The proposed Kernel-Pareto distribution based Markov chain model has been shown to perform well at reproducing most of statistics such as mean, standard deviation and skewness while the existing Gamma distribution based Markov chain model generally fails to reproduce high order moments. It was also confirmed that the proposed model can more effectively reproduce low order moments such as mean and median as well as underlying distribution of daily rainfall series by modeling extreme rainfall separately.