• Journal of Korean Society of Disaster and Security
• /
• v.13 no.4
• /
• pp.75-92
• /
• 2020

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.1
• /
• pp.98-105
• /
• 2022

It is essential for vertical smart farms that artificially grow crops in an enclosed space to properly utilize air environment facilities to create an appropriate growth environment. However, domestic vertical smart farm companies are creating a growing environment by relying on empirical data rather than systematic methods. Using IoT to create a growing environment based on systematic and precise monitoring can increase crop production yield and maximize profitability. This study aims to construct a monitoring system using IoT and to analyze the cause by demonstrating the imbalance of temperature environment, which is a significant factor in crop cultivation. 1) The horizontal temperature distribution of the multi-layer shelf was measured with different operating methods of LED and air conditioner. As a result, there was a temperature difference of "up to 1.7℃" between the sensors. 2) As a result of measuring the vertical temperature distribution, the temperature difference was "up to 6.3℃". In order to reduce this temperature gap, a strategy for proper arrangement and operation of air conditioning equipment is required.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.391-401
• /
• 2022

As deep learning-based object detection and recognition research have been developed recently, the scope of application to industry and real life is expanding. But deep learning-based systems in the construction system are still much less studied. Calculating materials in the construction system is still manual, so it is a reality that transactions of wrong volumn calculation are generated due to a lot of time required and difficulty in accurate accumulation. A fast and accurate automatic drawing recognition system is required to solve this problem. Therefore, we propose an AI-based automatic drawing recognition accumulation system that detects and recognizes steel materials in construction drawings. To accurately detect steel materials in construction drawings, we propose data augmentation techniques and spatial attention modules for improving small object detection performance based on YOLOv4. The detected steel material area is recognized by text, and the number of steel materials is integrated based on the predicted characters. Experimental results show that the proposed method increases the accuracy and precision by 1.8% and 16%, respectively, compared with the conventional YOLOv4. As for the proposed method, Precision performance was 0.938. The recall was 1. Average Precision AP_0.5 was 99.4% and AP_0.5:0.95 was 67%. Accuracy for character recognition obtained 99.9.% by configuring and learning a suitable dataset that contains fonts used in construction drawings compared to the 75.6% using the existing dataset. The average time required per image was 0.013 seconds in the detection, 0.65 seconds in character recognition, and 0.16 seconds in the accumulation, resulting in 0.84 seconds.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.11
• /
• pp.119-135
• /
• 2022

This paper used dynamic centrifuge tests to examine the seismic response for a deep temporary retaining wall with four input motions of 100, 1,000, and 2,400 years of return periods. The centrifuge model was designed based on an actual deep excavation design with a 50 m maximum excavation depth. The model backfill was prepared with dry silica sand at a relative density of 55%, and the retaining wall was modeled as a 24.8 m height diaphragm wall supported by struts. Acceleration response was amplified at the backfill surface, top of the wall, and near bedrock. However, in the middle of the model, input motion was de-amplified. The member forces of the wall and strut induced by the seismic load, which excited, were compared with the member force at rest condition. The wall's maximum negative and positive moments were increased to 36% and 10% compared to the maximum moment at rest. The maximum axial force increases to 70% of the at rest axial force on the bottom strut. The equivalent static analysis using Mononobe-Okabe (M-O) and Seed-Whitman (S-W) seismic earth pressures were compared to the centrifuge results. Considering the bending moment, the analysis results with the M-O theory underestimates but that with the S-W theory overestimates.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.105-118
• /
• 2022

The demand for information related to 3D spatial objects model in metaverse, smart cities, digital twins, autonomous vehicles, urban air mobility will be increased. 3D model construction for spatial objects is possible with various equipments such as satellite-, aerial-, ground platforms and technologies such as modeling, artificial intelligence, image matching. However, it is not easy to quickly detect and convert spatial objects that need updating. In this study, based on spatial information (features) and attributes, using matching elements such as address code, number of floors, building name, and area, the converged building DB and the detected building DB are constructed. Both to support above and to verify the suitability of object selection that needs to be updated, one system prototype was developed. When constructing the converged building DB, the convergence of spatial information and attributes was impossible or failed in some buildings, and the matching rate was low at about 80%. It is believed that this is due to omitting of attributes about many building objects, especially in the pilot test area. This system prototype will support the establishment of an efficient drone shooting plan for the rapid update of 3D spatial objects, thereby preventing duplication and unnecessary construction of spatial objects, thereby greatly contributing to object improvement and cost reduction.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.303-312
• /
• 2022

Bridges across waterways act as interference factors, that reduce the navigable water area from the perspective of navigation safety. To analyze the safety navigational width of ships navigating bridges across waterways, the optimal traffic distribution based on AIS data was investigated, and ships were classified according to size through k-means clustering. As a result of the goodness-of-fit analysis of the clustered data, the lognormal distribution was found to be close to the optimal distribution for Incheon Bridge and Busan Harbor Bridge. Also, the normal distributions for Mokpo Bridge and Machang Bridge were analyzed. Based on the lognormal and normal distribution, the analysis results assumed that the safe passage range of the vessel was 95% of the confidence interval, As a result, regarding the Incheon Bridge, the difference between the normal distribution and the lognormal distribution was the largest, at 64m to 98m. The minimum difference was 10m, which was revealed for Machang Bridge. Accordingly, regarding Incheon Bridge, it was analyzed that it is more appropriate to present a safety width of traffic by assuming a lognormal distribution, rather than suggesting a safety navigation width by assuming a normal distribution. Regarding other bridges, it was analyzed that similar results could be obtained using any of the two distributions, because of the similarity in width between the normal and lognormal distributions. Based on the above results, it is judged that if a safe navigational range is presented, it will contribute to the safe operation of ships as well as the prevention of accidents.

• Journal of Wetlands Research
• /
• v.24 no.1
• /
• pp.1-24
• /
• 2022

This study was conducted to perform efficient conservation and management by classifying the types of wetlands distributed in forests of Korea and assigning grades according to the evaluation system from 2015 until 2019. From 2005 to 2014, 1,264 sites derived from the first national forest wetland survey and 16 additional excavated sites were classified and also evaluated 455 out of a total of 1,280 forest wetlands. Forest wetlands are divided into four types: natural type, abandoned paddy field type, man-made type, and modified type, and by reclassifying them in detail, a total of 11 detailed wetland types could be distinguished. Based on this, evaluation was performed according to various items such as plants and ecology, hydrology and hydrology, humanities and society, and the degree of disturbance was graded. As a result, the forest wetland value was sorted at 30 A- grade sites, high-value B-grade 201 sites, moderate C-grade 184 sites, and low-value D-grade 40 sites. Forest Genetic Resource Reserve (FGRR) and other effective area -based conservation measures (OECMs) were designated for 231 sites that received a high grade of A or B, and a long-term monitoring system should be established to systematically conserve forest biodiversity hotspot. It is judged that wetlands need to be managed more effectively and at the national level.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of Wetlands Research
• /
• v.24 no.2
• /
• pp.115-122
• /
• 2022

As the impermeable area of soil increases due to urbanization, the water circulation system of the city is deteriorating. The existing guidelines for low impact development (LID) facilities installed to solve these water problems or in previous studies, engineering aspects are more prominent than landscaping aspects. This study attempted to present an engineering and landscaping model for reducing pollutants by identifying the effects of vegetation on rainfall outflows and pollutant reduction in bioretention and the economic aspects of planting. Based on the results of artificial rainfall monitoring at Jeonju Seogok Park and the literature on vegetation rainfall runoff and pollutant reduction performance, the best vegetation for reducing pollution compared to cost was Lythrum salicaria L and Salix gracilistyla Miq. was the best vegetation for carbon storage. If you insist to design plants with only these two plantation, there is no choice but to take risks such as biodiversity. Herbaceous plants such as Lythrum salicaria L can be replaced by death of the plants or pests if considered planting various plants. The initial planting cost could expensive, but it is also necessary to mix and plant Salix gracilistyla Miq, which are woody plants that are advantageous in terms of maintenance, according to the surrounding environment and conditions. Based on the conclusions drawn in this study, it can be a reference material when considering the reduction of pollution by species and carbon storage of vegetation in LID facilities.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.279-284
• /
• 2022

As a study of the blended learning method on design education through the blended learning method, I would like to propose that more advanced learner-led customized design education is possible. Understanding in face-to-face classes and advantages in non-face-to-face classes can be supplemented in an appropriate way in remote classes. Advanced artificial intelligence and big data technology can provide personalized and subdivided learning materials and effective learning methods tailored to learners' levels and interests based on quantified data in design classes. In this paper, it was proposed to maximize the efficiency of the class by applying a method that exceeds the limitations of time and space through the proposal of the A La Carte model (A La Carte). It is a remote class that can be heard anytime, anywhere, and it is also possible to bridge the educational quality and educational gap provided to students living in underprivileged areas. As the goal of fostering creative convergence-type future talents, it is changing with a rapid technological development speed. It is necessary to adapt to the change in learning methods in line with this. An analysis of the infographic virtual space design and construction process through the A La Carte model (A La Carte) proposal was presented. Rather than simply acquiring knowledge, it is expected that knowledge can be sorted, distinguished, learned, and easily reborn with its own knowledge.