• Journal of Navigation and Port Research
• /
• v.43 no.3
• /
• pp.209-218
• /
• 2019

Coastal cities suffer a great deal of storm and wind damage. The storm and wind characteristics vary between cities. Therefore, a storm and wind damage management system suited for specific characteristics is required for each coastal city. In this study, we analyze the current situation and establish the problem of storm and wind damage management system in regards to urban management, coastal management and disaster management. We also review the storm and wind damage management system for the USA and Japan. We consequently propose a plan to improve the storm and wind damage management system. As a result of the study, in terms of city management, we recommend the compulsory identification of disaster prevention districts, implementation of the integrated coastal city management plan, designation of natural disaster risk mitigation area as disaster prevention district, the division of disaster prevention district into wind damage prevention district, storm damage prevention district, erosion damage prevention district, the building of restrictions at the disaster prevention district by ordinance, etc. In regards to coastal management, we suggest the delegation of authority to delegate coastal erosion management area to the local government, the subdivision of coastal erosion management area into erosion serious area, erosion progress area, erosion concern area, the building restrictions at coastal erosion management area by ordinance, development of erosion prediction chart, etc. In relation to disaster management, we recommend the integration of "countermeasures against natural disasters act" and "disasters and safety management basic act", the local government-led disaster prevention system, the local disaster management network, and the customized local disaster prevention plan, etc.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.209-218
• /
• 2021

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.651-658
• /
• 2021

Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.55-63
• /
• 2022

In recent years, with the rapid development of large and medium-sized urban rail transit in China, the total operating mileage of high-speed railway and the total number of EMUs(Electric Multiple Units) are rising. The system complexity of high-speed EMU is constantly increasing, which puts forward higher requirements for the safety of equipment and the efficiency of maintenance.At present, the maintenance mode of high-speed EMU in China still adopts the post maintenance method based on planned maintenance and fault maintenance, which leads to insufficient or excessive maintenance, reduces the efficiency of equipment fault handling, and increases the maintenance cost. Based on the intelligent operation and maintenance technology of PHM(prognostics and health management). This thesis builds an integrated PHM platform of "vehicle system-communication system-ground system" by integrating multi-source heterogeneous data of different scenarios of high-speed EMU, and combines the equipment fault mechanism with artificial intelligence algorithms to build a fault prediction model for traction motors of high-speed EMU.Reliable fault prediction and accurate maintenance shall be carried out in advance to ensure safe and efficient operation of high-speed EMU.

• Korean Journal of Acupuncture
• /
• v.37 no.4
• /
• pp.209-230
• /
• 2020

Objectives : Practice-Based Research Networks (PBRNs), collaborations of practitioners and academic researchers, have provided platforms for conducting research to address clinical questions generated from daily routine care. This review aimed to critically analyse articles from PBRNs that are related to complementary and integrative medicine (CIM) and to suggest future directions for a PBRN which is appropriate for Korean Medicine (KM). Methods : PubMed, PBRN registries in Agency for Healthcare Research and Quality and relevant PBRN websites were searched up to November 2019 for research articles from PBRNs that focused on CIM regardless of study design. Methodological quality of the included studies was assessed. The included studies were read in full, classified and summarised according to their topics. Results : A total of 51 articles published from 1998 through 2020 were included in this review. They were categorised into three principal themes based on research questions and findings: health services research (embracing researches examining characteristics of patients and CIM practitioners/practices, and communication between patients and practitioners); effectiveness and safety of CIM practices/interventions; and feasibility studies of instruments and interventions in PBRN settings. The study designs varied including surveys (n=30), prospective observational studies (n=6), 2ndary analyses of existing studies (n=7), protocols (n=7), retrospective chart review (n=1) and qualitative study (n=1). Quality of the included studies greatly varied. Conclusions : PBRNs can serve as a feasible platform for conducting practice-relevant research on KM and CIM. Considering growing demands on evidence-base for routine practice of KM amid various stakeholders, a PBRN in KM community and further researches nested within PBRN designs are warranted.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1167-1181
• /
• 2021

In relation to the algae bloom, four types of blue-green algae that emit toxic substances are designated and managed as harmful Cyanobacteria, and prediction information using a physical model is being also published. However, as algae are living organisms, it is difficult to predict according to physical dynamics, and not easy to consider the effects of numerous factors such as weather, hydraulic, hydrology, and water quality. Therefore, a lot of researches on algal bloom prediction using machine learning have been recently conducted. In this study, the characteristic importance of water quality factors affecting the occurrence of Cyanobacteria harmful algal blooms (CyanoHABs) were analyzed using the random forest (RF) model for Bohyeonsan Dam and Yeongcheon Dam located in Yeongcheon-si, Gyeongsangbuk-do and also predicted the occurrence of harmful blue-green algae using the machine learning and deep learning models and evaluated their accuracy. The water temperature and total nitrogen (T-N) were found to be high in common, and the occurrence prediction of CyanoHABs using artificial neural network (ANN) also predicted the actual values closely, confirming that it can be used for the reservoirs that require the prediction of harmful cyanobacteria for algal management in the future.

• Korean Journal of Clinical Pharmacy
• /
• v.32 no.3
• /
• pp.215-225
• /
• 2022

Background: Patients with hematologic cancers have a risk of drug-related problems (DRPs) from medications associated with chemotherapy and supportive care. Although the role of oncology pharmacists has been widely documented in the literature, few studies have reported its impact on cost reduction. This study aimed to describe the activities of oncology pharmacists with respect to hematologic diseases and evaluate the associated cost avoidance. Methods: From January to July 2021, patients admitted to the department of hemato-oncology at Seoul National University, Bundang Hospital were studied. The activities of oncology pharmacists were reported by DRP type following the Pharmaceutical Care Network version 9.1 guidelines, and the acceptance rate was calculated. The avoided cost was estimated based on the cost of the pharmacy intervention, pharmacist manpower, and prescriptions associated with the intervention. Results: Pharmacists intervened in 584 prescriptions from 208 patients during the study period. The most prevalent DRP was "adverse drug event (possibly) occurring" (32.4%), followed by "effect of drug treatment not optimal" (28.6%). "Drug selection" (42.5%) and "dose selection" (30.3%) were the most common causes of DRPs. The acceptance rate of the interventions was 97.1%. The total avoidance cost was KRW 149,468,321; the net profit of the avoidance cost, excluding labor costs, was KRW 121,051,690; and the estimated cost saving was KRW 37,223,748. Conclusion: Oncology pharmacists identified and resolved various types of DRPs from prescriptions for patients with hematologic disease, by reviewing the prescriptions. Their clinical service contributed to enhanced patient safety and the avoidance of associated costs.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.171-182
• /
• 2022

The safe use of a structure requires it to be maintained in an undamaged state. Thus, a typical factor that determines the safety of a structure is a crack in it. In addition, cracks are caused by various reasons, damage the structure in various ways, and exist in different shapes. Making matters worse, if these cracks are unattended, the risk of structural failure increases and proceeds to a catastrophe. Hence, recently, methods of checking structural damage using deep learning and computer vision technology have been introduced. These methods usually have the premise that there should be a large amount of training image data. However, the amount of training image data is always insufficient. Particularly, this insufficiency negatively affects the performance of deep learning crack detection algorithms. Hence, in this study, a method of augmenting crack image data based on the image translation technique was developed. In particular, this method obtained the crack image data for training a deep learning neural network model by transforming a specific case of a asphalt crack image into a concrete crack image or vice versa . Eventually, this method expected that a robust crack detection algorithm could be developed by increasing the diversity of its training data.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.9
• /
• pp.13-24
• /
• 2023

To investigate the stability of temporary retaining walls during excavation, it is essential to develop reverse analysis technologies capable of precisely evaluating the properties of the ground and a learning model that can assess stability by analyzing real-time data. In this study, we targeted excavation sites where the C.I.P method was applied. We developed a Deep Neural Network (DNN) model capable of evaluating the stability of the retaining wall, and estimated the physical properties of the ground being excavated using a Differential Evolution Algorithm. We performed reverse analysis on a model composed of a two-layer ground for the applicability analysis of the Differential Evolution Algorithm. The results from this analysis allowed us to predict the properties of the ground, such as the elastic modulus, cohesion, and internal friction angle, with an accuracy of 97%. We analyzed 30,000 cases to construct the training data for the DNN model. We proposed stability evaluation grades for each assessment factor, including anchor axial force, uneven subsidence, wall displacement, and structural stability of the wall, and trained the data based on these factors. The application analysis of the trained DNN model showed that the model could predict the stability of the retaining wall with an average accuracy of over 94%, considering factors such as the axial force of the anchor, uneven subsidence, displacement of the wall, and structural stability of the wall.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.1
• /
• pp.79-89
• /
• 2023

The inventory of many materials requires a large storage space, and the longer the storage period, the higher the potential maintenance cost. When materials are stored on a construction site, there are also concerns about safety due to the reduction of room for movement and working. On the other hand, construction sites that do not store materials have insufficient inventory, making it difficult to respond to demands such as sudden design changes. Ordering materials is then subject to delays and extra costs. Although securing an appropriate amount of inventory is important, in many cases, material management on a construction site depends on the experience of the site manager, so a reasonable material inventory management plan that reflects the construction conditions of a site is required. This study proposes an economical material management method by reflecting variables such as the status of the preceding and following activities, site size, material delivery cost, timing of an order, and quantity of orders. To this end, we set the appropriate inventory amount while adjusting related activities in the activity network, using float time for each activity, the size of the yard, and the order quantity as the main variables, and applied a genetic algorithm to this process to suggest the optimal order timing and order quantity. The material delivery cost derived from the results is set as a fitness index and the efficiency of inventory management was verified through a case application.