• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.136-136
• /
• 2021

In this study, a deep convolutional neural network (DCNN) model is proposed for short-term precipitation forecasting using weather radar-based images. The DCNN model is a combination of convolutional neural networks, autoencoder neural networks, and U-net architecture. The weather radar-based image data used here are retrieved from competition for rainfall forecasting in Korea (AI Contest for Rainfall Prediction of Hydroelectric Dam Using Public Data), organized by Dacon under the sponsorship of the Korean Water Resources Association in October 2020. This data is collected from rainy events during the rainy season (April - October) from 2010 to 2017. These images have undergone a preprocessing step to convert from weather radar data to grayscale image data before they are exploited for the competition. Accordingly, each of these gray images covers a spatial dimension of 120×120 pixels and has a corresponding temporal resolution of 10 minutes. Here, each pixel corresponds to a grid of size 4km×4km. The DCNN model is designed in this study to provide 10-minute predictive images in advance. Then, precipitation information can be obtained from these forecast images through empirical conversion formulas. Model performance is assessed by comparing the Score index, which is defined based on the ratio of MAE (mean absolute error) to CSI (critical success index) values. The competition results have demonstrated the impressive performance of the DCNN model, where the Score value is 0.530 compared to the best value from the competition of 0.500, ranking 16^th out of 463 participating teams. This study's findings exhibit the potential of applying the DCNN model to short-term rainfall prediction using weather radar-based images. As a result, this model can be applied to other areas with different spatiotemporal resolutions.

• The Korean Journal of Franchise Management
• /
• v.6 no.2
• /
• pp.31-49
• /
• 2015

The purpose of this study was to propose a policy development plan for win-win growth between franchisor and franchisee by investigating success factors of win-win growth on the basis of the problems between franchisor and franchisee. There are many small scale franchise businesses in Korea that have not achieved an economy of scale compared to the developed countries. The conflicts between franchisor and franchisee have continued due to a lack of social trust which comes from an excessively high ratio of business failure and big firms' expansion into franchise business, then again, the perception of relations between the topdog and the underdog causes many problems. As franchise is the industry based on common people that helps service industry advance and competitiveness of the self-employed improve, it needs to be activated as the higher value-added business by promoting establishment of business and strengthening foundation of related industry. A matter of mutual cooperation and win-win growth between franchisor and franchisee is important not only for the sound development of franchise industry but also for the stable growth of nation's economy. Thus, this study suggested a policy development plan for win-win growth between franchisor and franchisee by analyzing success factor of win-win growth based on the problems between franchisor and franchisee. The results of the study provide the important strategic way towards mutual growth and maintaining cooperative relationship between franchisor and franchisee in Korean franchise industry.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.2D
• /
• pp.163-169
• /
• 2010

Construction monitoring and monitoring industry have been rapidly developed with advance of IT industry and telecommunication. However institutional, legal supports that need to settle the construction monitoring are practically inadequate. So development plans that are reflected enquete results about the present state of construction monitoring are considered. A way that consider establishment Korea construction monitoring association and society, deal with relevant law appointing monitoring industry, consider enactment and revision of construction monitoring design standard and specifications, appoint practical construction monitoring educational institution, appoint an efficiency test specialty institution of monitoring equipment, consider the term of guarantee of monitoring equipment consider enactment and revision of estimating cost of construction measurement, consider ratio of monitoring equipment loss for developing construction monitoring and monitoring industry are proposed.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.950-957
• /
• 2023

Purpose: The response technology is needed to prevent the spill of highly toxic oil contaminants in advance. Therefore, this paper described the results of an experimental study to predict the engineering properties of the developed reactive material. Method: Compaction tests and spectral information acquisition experiments were conducted on the reactive materials, and the results were evaluated. In addition, the correlation between spectral information and maximum dry unit weight was analyzed to evaluate the possibility of predicting the engineering properties for reactive materials. Result: The compaction test results showed that the maximum dry unit weight was in the range of approximately 9kN/m³ to 10kN/m³. The spectral information confirmed that the maximum reflectance decreased as the polynorbornene decreased. Conclusion: It was confirmed that the maximum dry unit weight of the reactive material for absorbing oil contaminants can be predicted using the maximum reflectance according to the component ratio of the reactive material.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.3
• /
• pp.101-108
• /
• 2024

A system with the ability to recognize potential key blocks during tunnel construction by analyzing the rock face was developed in this study. This system predicts the formation of key blocks in advance and evaluates their safety factors. A laser scanner was used to collect a three-dimensional point cloud of the rock face, which was then utilized to model the excavation surface and derive the joint surfaces. Because joint surfaces have specific strikes and dip angles, the key blocks formed by these surfaces are deduced through iterative calculations, and the safety factor of each key block can be calculated accordingly. The model experiments confirmed the accuracy of the system's output in terms of the joint surface characteristics. By inputting the joint surface information, the calculated safety factors were compared with those from the existing commercial software, demonstrating stable calculation results within a 1% error margin.

• Journal of Aerospace System Engineering
• /
• v.14 no.5
• /
• pp.122-129
• /
• 2020

Surion is required to install radios (U/VHF-AM, VHF-FM) capable of omni-directional communication. Therefore, this paper demonstrates the antenna performance test for the installation of the Surion communication antenna and the selection of optimal location. A simulation pattern analysis was performed employing the antenna, and a coupling test was performed by creating a new evaluation criterion. In addition, the results of the pattern flight test conducted at the previously suggested 1:20 turn and separation distance ratio were observed to be normal. However, the occurrence of voice cutoff was noted in the long-distance flight test. Therefore, in this paper, 1:300 (15 NM) is proposed as a new optimal ratio for predicting the long-distance flight test results in advance. Finally, the effectiveness of the proposed evaluation criteria was verified through long-distance flight tests. Consequently, it is expected to reduce the development schedule and cost by reducing the trial and error of the performance test for the Surion model. Also, the results of this study are expected to be used as standards for the installation of communication antenna and quality tests for other helicopters.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.158-161
• /
• 2004

In order for better management of a medical linear accelerator, the records of the operational failures of Varian CL2100C over ten years were analyzed. The failures were classified according to the involved functional subunits and each class was rated into three levels depending on operational conditions. The relationship between the failure rate and working ratio was investigated. Among the recorded failures ( total 587 failures), the most frequent failure, which was 20% of the total. was observed in the parts related to the collimation system including monitor chamber. Regrading to the operational conditions, the 2nd level of failures, that temporally interrupted treatments, was the most frequent. The 3rd level of failures, that interrupted treatment for more than several hours, was mostly caused by the accelerating subunit. The average life-time of a Klystron and Thyratron became shorter as the working ratio increased, which was 42 and 83% of the expected values, respectively. Recording equipment problems and failures in detail over a long period of time can provide a good knowledge of equipment function as well as the capability to forecast future failure. More rigorous equipment maintenance is required for old medical linear accelerator to avoid the serious failure in advance, and improve the patient treatment quality.

• Korean Security Journal
• /
• no.9
• /
• pp.27-68
• /
• 2005

Recently, because credit card crime using a personal credit information is increasing, professionalizing, and spreading the area, the loss occurring from credit card crime is enormous and is difficult to arrest and punish the criminals. At past, crime from forging and counterfeiting the credit card was originated by minority criminals, but at present, the types and appearance of credit card crime is very different to contrasting past crime. The numbers of people using credit card in the middle of 1990's was increasing and barometer of living conditions was evaluated by the number having credit card, therefore this bad phenomenon occurring from credit card crime was affected by abnormal consumption patterns. There is no need emphasizing the importance of personal credit card in this credit society. so, because credit card crime using personal credit card information has a bad effect, and brings the economic loss and harms to individuals, credit card company, and members joining credit card. Credit card crime using personal credit card information means the conduct using another people's credit card information(card number, expiring duration, secret number) that detected by unlawful means. And crime using dishonest means from another people's credit information is called a crime profiting money-making and a crime lending an illegal advance by making false documents. A findings on countermeasures of this study are as follows: Firstly, Diverting user's mind, improving the art of printing, and legitimating password from payment gateway was suggested. Secondly, Complementing input of password, disseminating the system of key-board protection, and promoting legitimations of immediate notification duty was suggested. Thirdly, Certificating the electronic certificates as a personal certificates, assuring the recognition by sense organ of organism, and lessening the ratio of crime occurrence, and restricting the ratio of the credit card crime was suggested.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.4
• /
• pp.589-598
• /
• 2000

A pilot-scale Spray Drying Sorber (SDS) system was set up to evaluate the effect of spray characteristics on the desulfurization yield. The size distribution and the Sauter Mean Diameters of slurry droplets were measured in advance using the optical size measurement system, Malvern 2600. The desulfurization yield of the drying chamber by size was measured for the conditions of inlet gas and spray injection. As a reagent, 10% limestone slurry of $Ca(OH)_2$ was treated with flue gas containing $SO_2$, and the combustion gas analyzer and gas detectors were attached to measure the $SO_2$ concentration. With a flow rate of 144 Nm3/h and a temperature range of $200{\sim}300^{\circ}C$, the experiments were performed for the Stoichiometric Ratio (SR) of 1.0 to 3.0 and droplet mean diameter of 6.5 to $34.3{\mu}m$. In case of smaller spray droplets, the desulfurization efficiency improved due to the increase of total droplet surface area, while the reduction in evaporation time reduced the contact time between the droplets and $SO_2$ gas. In some typical region of droplet diameter, this negative effect, reduction of contact time, became dominant and the desulfurization yield decreases the desulfurization yield in spite of the expansion in absorption area. These results revealed that there exists the optimal size of spray droplets for a given state, which is determined by the compromise between the total surface area of slurry droplets and the evaporation time of droplets. The measurements also indicated that the inlet temperature of flue gas changes the optimal injection condition by varying the driving force for evaporation. The results confirm that the effect of the evaporation time of slurry droplets should be considered in analyzing the desulfurization yield as well as the total surface area, for it is a significant aspect of the correlation with the capabilities of $SO_2$ absorption in wet droplets. In conclusion, the optimal condition of spray can be determined based on these results, which might be applied to design or scale-up of SDS system.

• Journal of the Korea Society for Simulation
• /
• v.17 no.2
• /
• pp.21-29
• /
• 2008

The High Level Architecture(HLA) specifies a framework for interoperation between heterogeneous simulators, and Run-Time Infrastructure(RTI) is a implementation of the HLA Interface Specification. The Data Distribution Management(DDM) services, one category of IEEE 1516 HLA/RTI management services, control filters for data transmission and reception of data volume among simulators. In this paper, we propose design concept of DDM and show its implementation for light-weighted RTI. The design concept of DDM is to minimize total amount of message that each federate and a federation process generate using the rate of RTI service execution. The design of our proposed DDM follows that a data transfer mechanism is differently applied as the rate of RTI service execution. A federate usually publishes or subscribes data when it starts. The federate constantly updates the data and modifies associated regions while it continues to advance its simulation time. Therefore, the proposed DDM design provides fast update or region modification in exchange of complex publish and subscribe services. We describe how to process the proposed DDM in IEEE 1516 HLA/RTI and experiment variable scenarios while modifying region, changing overlap ratio, and increasing data volume.