• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.48 no.2
• /
• pp.97-104
• /
• 2022

In this study, the anti-inflammatory and anti-oxidant efficacy of camellia subcritical water extracts (SWE, 135 ~ 180 ℃, 70 bar) was compared with 70% ethanol and hot water extracts. Among these extracts, the yield (57.9%) of the subcritical water extract, which was extracted under the condition of 180 ℃ and 70 bar was the highest, which increased the extraction yield by more than two times compared to the hot water extract (28.1%). The results of the nitric oxide (NO) production inhibition activity experiment using RAW 264.7 macrophages stimulated with lipopolysaccharide (LPS) showed that subcritical water extracts had superior effects in inhibiting the production of NO without cytotoxicity than 70% ethanol and hot water extracts. In addition, DPPH and ABTS⁺ radical scavenging activity experiments showed that the radical scavenging activity of subcritical water extract was similar to that of 70% ethanol and hot water extract. Moreover, the content of gallic acid was determined by HPLC and the quantity was about 1.62 mg/g for the SWE (165 ℃, 70 bar), which was the highest among all of the extracts. Based on these results, it is concluded the SWE of C. japonica flowers could be potentially applicable as anti-inflammatory and anti-oxidative ingredients in cosmetic formulations.

• Composites Research
• /
• v.35 no.3
• /
• pp.147-152
• /
• 2022

Low-temperature characteristics according to internal temperature conditions during rotational molding of Type 4 pressure vessel liners were studied in this paper. Since rotational molding has a sensitive effect on the formability of the liner depending on the temperature conditions, the temperature conditions for the polyamide used should be accurately set. The structural changes of polyamide as the liner material was analyzed the surface by atomic force microscope (AFM), and the crystallinity measured with a differential scanning calorimeter (DSC) is used to evaluate the change of the mechanical strength value at low temperature. In addition, the formability of the liner was confirmed by observation of the yellow index inside the liner. As a result, as the melting range of the internal temperature becomes wider, the yellow index shows a lower value, and the elongation and impact characteristics at low temperatures are improved. It was also confirmed that the structure of the polyamide was uniform and the crystallinity was high by AFM and DSC. These experimental results contribute to the improvement of characteristics at low temperatures due to changes in temperature conditions during rotational molding.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.243-254
• /
• 2021

This study analyzed the abuse of authority among the types of power abuse in educational institutions in order to create an educational climate in which democracy and equality are respected and to create a better education and an equal society. First, we analyzed the concept and cause of power abuse through literature research, and then explored the cases of members of educational institutions according to the type of abuse of authority through qualitative research to derive implications. As a result, abuse of authority within educational institutions were found as follows: additional work without consultation, transfer of duties, coercive and unilateral instructions using status, instructions violating laws and guidelines, private instructions for personal convenience, specific institutions, personal rights, and privacy. Based on this analysis, a policy was proposed. First, an agreed standard for abuse of authority, an institutional mechanism to mediate conflicts and complaints over abuse of authority, mandatory installation and legislation of the best decision body, active and transparent disclosure of information, and a shift to open and listening administration are needed. Second, analyzing and seeking ways to reduce overuse of authority in educational institutions will be the cornerstone for leading education's democracy and equality by creating a culture of mutual respect and communication among members of the organization. Hope that follow-up studies will be carried out and that the Gap-jil in educational institutions will be reduced to create a better educational environment.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1109-1124
• /
• 2022

This study proposes a marine debris monitoring methods using satellite and drone multispectral images. A multi-layer perceptron (MLP) model was applied to detect marine debris using Sentinel-2 satellite image. And for the detection of marine debris using drone multispectral images, performance evaluation and comparison of U-Net, DeepLabv3+ (ResNet50) and DeepLabv3+ (Inceptionv3) among deep learning models were performed (mIoU 0.68). As a result of marine debris detection using satellite image, the F1-Score was 0.97. Marine debris detection using drone multispectral images was performed on vegetative debris and plastics. As a result of detection, when DeepLabv3+ (Inceptionv3) was used, the most model accuracy, mean intersection over union (mIoU), was 0.68. Vegetative debris showed an F1-Score of 0.93 and IoU of 0.86, while plastics showed low performance with an F1-Score of 0.5 and IoU of 0.33. However, the F1-Score of the spectral index applied to generate plastic mask images was 0.81, which was higher than the plastics detection performance of DeepLabv3+ (Inceptionv3), and it was confirmed that plastics monitoring using the spectral index was possible. The marine debris monitoring technique proposed in this study can be used to establish a plan for marine debris collection and treatment as well as to provide quantitative data on marine debris generation.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1871-1877
• /
• 2022

In the past, satellite development required enormous budget and time, so only some developed countries possessed satellites. However, with the recent emergence of low-budget satellites such as micro-satellites, many countries around the world are participating in satellite development. Low-orbit and geostationary-orbit satellites are used in various fields such as environment and weather monitoring, precise change detection, and disasters. Recently, it has been actively used for monitoring through deep learning-based object-of-interest detection. Until now, Korea has developed satellites for national demand according to the space development plan, and the satellite image obtained through this is used for various purpose in the public and private sectors. Interest in satellite image is continuously increasing in Korea, and various contests are being held to discover ideas for satellite image application and promote technology development. In this special issue, we would like to introduce the topics that participated in the recently held 2022 Satellite Information Application Contest and research on the processing and utilization of KOMPSAT image data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.1
• /
• pp.79-94
• /
• 2022

The demand for tunnel construction is increasing as part of underground space development due to urban saturation. The shield TBM method minimizes vibration and noise and minimizes ground deformation that occurs simultaneously with excavation, and shield TBM is generally applied to tunnel construction in urban areas. The importance of urban ground settlement prediction is increasing day by day, and in the case of shield TBM construction, ground deformation is minimized, but ground settlement due to tunnel excavation inevitably occurs. Therefore, in this study, the correlation between shield TBM, which is highly applicable to urban areas, and ground settlement is analyzed to suggest the shield TBM construction factors that have a major effect on ground settlement. Correlation analysis was performed between the shield TBM construction data and ground settlement measurement data collected at the actual site, and the degree of correlation was expressed as a correlation coefficient "r". As a result, the main construction factors of shield TBM affecting ground settlement were thrust force, torque, chamber pressure, backfill pressure and muck discharge. Based on the results of this study, it is expected to contribute to the presentation of judgment criteria for major construction data so that the ground settlement can be predicted and controlled in advance when operating the shield TBM in the future.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.54 no.6
• /
• pp.880-889
• /
• 2021

The home meal replacement (HMR) market has attracted significant attention due to COVID-19 pandemic and products that utilize the combination of different processed ingredients are now being developed. In this study, Broughton's ribbed ark Scapharca broughtonii was soaked in seasoned soy sauce with the incorporation of mustard leaf Brassica juncea (M-BRA), which is known to have a unique texture as well as excellent functional properties such as antioxidation, to develop a regional specialty product. The optimal conditions for manufacturing M-BRA from the seasoned soy sauce (the sauce to be added [X₁] and the soaking time [X₂]), were examined using response surface methodology (RSM) to analyze the significance of the salinity (Y₁), amino-N content (Y₂), and overall acceptance (Y₃). The coefficient of determination (R²) between X₁-X₂ and Y₁-Y₃ were close to 1, thereby confirming the suitability of the RSM model. The optimal conditions were seasoned soy sauce addition of 140% and soaking time of 156 min. The M-BRA manufactured under these conditions exhibited superior overall acceptance compared to seasoned commercial soy sauce, which was used as a control. We expect that the market for M-BRA manufactured by combining marine and agricultural materials will expand owing to superior overall acceptance compared with commercial products.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.54 no.6
• /
• pp.869-879
• /
• 2021

Methods for the development of home meal replacement seafood tailored to consumer needs for the advanced use of Broughton's ribbed ark Scapharca broughtonii (BRA) in Korea are required. In this study, we developed a cheese-topped, semi-dried, and seasoned Broughton's ribbed ark (S-BRA) tailored for the younger generation with an improved texture and fish odor. The optimization of conditions to improve the texture and fish odor was performed using RSM. The design of the model was appropriate because there was no significant difference (P>0.05) between the predicted and actual values of moisture content, hardness, and overall acceptance, and the optimal preparation conditions were a vinegar content of 2.68%, a soaking time of 62 min, a drying temperature of 60℃, and a time of 162 min. The S-BRA manufactured under these optimal conditions exhibited a lower odor intensity compared to the unsoaked and undried control, suggesting that the fish odor of S-BRA has been improved. The moisture content related to the texture of the S-BRA was lower than that of the control, and the hardness was higher. Therefore, the S-BRA developed in this study will appeal to people of all ages, especially the younger generation; their consumption is expected to increase.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.595-602
• /
• 2022

This study tried to suggest the most efficient learning rate for accurate and efficient automatic diagnosis of medical images for chest X-ray pneumonia images using deep learning. After setting the learning rates to 0.1, 0.01, 0.001, and 0.0001 in the Inception V3 deep learning model, respectively, deep learning modeling was performed three times. And the average accuracy and loss function value of verification modeling, and the metric of test modeling were set as performance evaluation indicators, and the performance was compared and evaluated with the average value of three times of the results obtained as a result of performing deep learning modeling. As a result of performance evaluation for deep learning verification modeling performance evaluation and test modeling metric, modeling with a learning rate of 0.001 showed the highest accuracy and excellent performance. For this reason, in this paper, it is recommended to apply a learning rate of 0.001 when classifying the presence or absence of pneumonia on chest X-ray images using a deep learning model. In addition, it was judged that when deep learning modeling through the application of the learning rate presented in this paper could play an auxiliary role in the classification of the presence or absence of pneumonia on chest X-ray images. In the future, if the study of classification for diagnosis and classification of pneumonia using deep learning continues, the contents of this thesis research can be used as basic data, and furthermore, it is expected that it will be helpful in selecting an efficient learning rate in classifying medical images using artificial intelligence.