• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.206-216
• /
• 2020

As the number of aging railway bridges in Korea increases, maintenance costs due to aging are increasing and continuous management is becoming more important. However, while the number of old facilities to be managed increases, there is a shortage of professional personnel capable of inspecting and diagnosing these old facilities. To solve these problems, this study presents an improved model that can detect Local damage to structures using machine learning techniques of AI technology. To construct a damage detection machine learning model, an analysis model of the bridge was set by referring to the design drawing of a non-ballasted plate-girder railroad bridge. Static strain data according to the damage scenario was extracted with the analysis model, and the Local damage index based on the reliability of the bridge was presented using statistical techniques. Damage was performed in a three-step process of identifying the damage existence, the damage location, and the damage severity. In the estimation of the damage severity, a linear regression model was additionally considered to detect random damage. Finally, the random damage location was estimated and verified using a machine learning-based damage detection classification learning model and a regression model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.80-91
• /
• 2021

The purpose of this study is to present the applicability to the effective survey into the actual condition of lands such as analysis of occupied location of government owned lands based on orthoimages created from aerial photographs taken by UAV. The boundary point coordinates and areas of the parcels were observed respectively by VRS-GNSS surveying and orthoimages for each land use of two categories of land, i.e. building site and farmland. As a result of comparing boundary point coordinates and areas extracted from UAV orthoimages with VRS-GNSS surveying data which were used as reference data, the RMS error of the coordinates for the boundary points was ±0.074m for both X and Y in the building site, and ±0.150m and ±0.127m for the X and Y respectively in the farmland. The positional error of the boundary point was 1.7~ 2 times higher in the farmland than in the building site where the boundary points were relatively clear. The RMS error of ±8.964㎡ of areas in the farmland was 4.7 times higher than that of ±1.898㎡ of areas in the building site. The area errors of all 22 parcels measured from the orthoimage were found to be within the allowed error range, indicating that it is feasible to apply the orthoimage generated by UAV to survey of government owned lands in terms of accuracy.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.171-179
• /
• 2020

In this study, a local corrosion environment monitoring was conducted using steel box specimen fabricated to be the same as actual steel bridge members. The steel box specimen that obtained the same corrosion environment as a steel bridge was classified into the upper plate, bottom plate and web plate. Atmospheric corrosion monitoring sensors(ACM sensors) were installed in each corrosion monitoring member of a steel box specimen to measure the corrosion current and examine time of wetness for each monitoring member. The time of wetness and accumulated corrosion current of each monitoring member were calculated from the measured corrosion current using ACM sensors. The corrosion environment that appeared for each of the steel box members was evaluated from monitoring corrosion environment data as the corrosion current, time of wetness, mean corrosion depth of each monitoring member. Additionally, the atmospheric corrosion environment monitoring was also conducted to compare with the local corrosion environment of steel box members. From these local corrosion environment monitoring for the steel box specimen, the relationship between the relative corrosion environment and mean corrosion depth of each steel box member was examined.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.1
• /
• pp.11-19
• /
• 2021

The aim of the research is providing a fundamental data on quality and constructability of direct tile setting method depending on various cement to sand ratio for tiling dry cement mortar. A large number of tile setting failures reported is related with the cement mortar and its construction for tiling. Because of different materials of tiles, the properties of tiling dry cement mortar, an adhesive for tiling, can influence on quality and constructability of tiling differently. Practically, the easiest way of controlling the properties of the tiling dry cement mortar is to control the proportion of cement and sand. Hence, in this research, sand to cement ratio (S/C) was controlled. Since there is no standarized method on evaluating performance of dry cement mortar for tiling, a several sensory evaluation methods were suggested and executed. According to the experiments conducted in this research, the adhesive performance of cement mortar for tiles can be different depending on the sides such as tile and substrate. Additionally, depending on S/C, finishability, initial adhesive performance, and tile shifting resistance can be changed for ceramic tile. Therefore, under the conditions of this research, about 5 of S/C can be recommended for appropriate performace of tiling dry cement mortar.

• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.18-27
• /
• 2020

This study presents flow assurance analysis in subsea pipeline considering system availability of topside in LNG-FPSO. A hydrate management strategy was established, which consisted of PVCap experiments, system availability analysis of LNG-FPSO topside, hydrate risk analysis in the pipeline, and calculation of PVCap injection concentration. The experimental data required for the determination of PVCap injection concentration were obtained by measuring the hydrate induction time of PVCap at the subcooling temperatures of 6.1, 9.2, and 12.1℃. The availability of LNG-FPSO topside system for 20 years was 89.3%, and the longest downtime of 50 hours occurred 2.9 times per year. The subsea pipeline model for multiphase flow simulation was created using field geometry data. As a result of risk analysis of hydrate plugging using subsea pipeline model, hydrate was formed at the end of flowline in 23.2 hours under the condition of 50 hours shutdown. The injection concentration of PVCap was determined based on the PVCap experiment results. The hydrate plugging in subsea pipeline of LNG-FPSO can be completely prevented by injecting PVCap 0.25 wt% 2.9 times per year.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.8
• /
• pp.65-73
• /
• 2021

This study investigated differences in learning styles and learning strategies according to learning factors: major fields, achievements, and grades and differences in learning strategies according to learning styles for college students. Unlike previous studies that analyzed differences focused on the dominant learning style, the learning style was subdivided into a balanced and dominant learning style. In the analysis of the 179 participants in M colleges, it was found that the difference between the learning style and the learning strategy according to the learning factors was not significant. But, there was a significant difference in the use of cognitive strategies according to the learning style in the dimension of information input, and in the use of all strategies according to the information processing style. It was analyzed that active learners had a high level of using cognitive strategies, visual learners had a high level of using external strategies, and balanced learners had a high level of using internal strategies. Based on the results, the training strategies to understand the learning style and to improve the level of use of the learning strategy in the learning competency improvement program was proposed.

• Journal of Life Science
• /
• v.31 no.6
• /
• pp.595-602
• /
• 2021

Human intestinal microbiota play an important role in the regulation of the host's metabolism. There is a close pathological and physiological interaction between dysbiosis of the intestinal microflora and obesity and metabolic syndrome. Akkermansia muciniphila, which was recently isolated from human feces, accounts for about 1-4% of the intestinal microbiota population. The use of A. muciniphila- derived external membrane protein Amuc_1100 and extracellular vesicles (EVs) could be a new strategy for the treatment of obesity. A. muciniphila is considered a next-generation probiotic (NGP) for the treatment of metabolic disorders, such as obesity. Faecalibacterium prausnitzii accounts for about 5% of the intestinal microbiota population in healthy adults and is an indicator of gut health. F. prausnitzii is a butyrate-producing bacterium, with anti-inflammatory effects, and is considered an NGP for the treatment of immune diseases and diabetes. Postbiotics are complex mixtures of metabolites contained in the cell supernatant secreted by probiotics. Parabiotics are microbial cells in which probiotics are inactivated. Paraprobiotics and postbiotics have many advantages over probiotics, such as clear chemical structures, safe dose parameters, and a long shelf life. Thus, they have the potential to replace probiotics. The most natural strategy to restore the imbalance of the intestinal ecosystem normally is to use NGPs among commensal bacteria in the gut. Therefore, it is necessary to develop new foods or drugs such as parabiotics and postbiotics using NGPs.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.391-404
• /
• 2021

This study developed a long-term prediction model for the potential yield of garlic based on a genetic algorithm (GA) by utilizing global climate reanalysis data. The GA is used for digging the inherent signals from global climate reanalysis data which are both directly and indirectly connected with the garlic yield potential. Our results indicate that both deterministic and probabilistic forecasts reasonably capture the inter-annual variability of crop yields with temporal correlation coefficients significant at 99% confidence level and superior categorical forecast skill with a hit rate of 93.3% for 2 × 2 and 73.3% for 3 × 3 contingency tables. Furthermore, the GA method, which considers linear and non-linear relationships between predictors and predictands, shows superiority of forecast skill in terms of both stability and skill scores compared with linear method. Since our result can predict the potential yield before the start of farming, it is expected to help establish a long-term plan to stabilize the demand and price of agricultural products and prepare countermeasures for possible problems in advance.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.14-25
• /
• 2021

With the spread of COVID-19 and the government policy of social distancing, the demand for subways and buses is decreasing, whereas the demand for public bicycles and personal transportation is increasing. Hence, research is needed to understand the characteristics of this phenomenon and to prove the statistical reliability of the correlation between the subway and shared bicycle demands. In this study, the correlation between the number of confirmed COVID-19 cases and the replacement rate of subway and public bicycle demands was examined, but the statistical significance was not significant. However, during the period of September to December 2020, in which the number of confirmed COVID-19 cases in Seoul started to increase rapidly, there was a correlation between the number of confirmed COVID-19 cases and the replacement ratio. If the number of confirmed COVID-19 cases increases by more than a certain number, public bicycles are expected to play a significant role as alternates to the subways. It is expected that the role of public bicycles will increase, and that it is possible to suggest the direction of transportation operation and policy establishment for the continuation of COVID-19 countermeasures in field demonstration after elementary technology development. It is also expected that this study will suggest a direction for future development and policymaking.