• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.446-452
• /
• 2021

As a higher standard for food consumption is required, the consumption of chicken meat that can satisfy the subdivided food preferences is increasing. In March 2003, the quality criteria for chicken carcasses notified by the Livestock Quality Assessment Service suggested quality grades according to fecal contamination and the size and weight of blood and bruises. On the other hand, it is too difficult for human inspection to qualify mass products, which is key to maintaining consistency for grading thousands of chicken carcasses. This paper proposed the computer vision algorithm as a non-destructive inspection, which can identify chicken carcass parts according to the detailed standards. To inspect the chicken carcasses conveyed at high speed, the image calibration was involved in providing robustness to the side effect of external lighting interference. The separation between chicken and background was achieved by a series of image processing, such as binarization based on Expectation Maximization, Erosion, and Labeling. In terms of shape analysis of chicken carcasses, the features are presented to reveal geometric information. After applying the algorithm to 78 chicken carcass samples, the algorithm was effective in segmenting chicken carcass against a background and analyzing its geometric features.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.4
• /
• pp.33-45
• /
• 2022

A series of model tests were performed in this study to demonstrate the clogging mechanism created during the installation of a compaction pile to improve soft ground. The application of an air-jet to extrude sand or aggregates from a casing during the installation of a compaction pile imposes a remarkably high-pressure difference between the composite soil layers of clay and sand (or aggregates), resulting in severe clogging. Therefore, a one-dimensional testing system was developed to simulate composite soil layers consisting of clay and sand (or aggregates) and to apply a high-pressure differential at both boundaries, thus replicating the extrusion process used in compaction pile installation. Herein, the performance of two construction materials for compaction piles of crushed stone and grading-controlled aggregates was compared. A series of one-dimensional model tests were performed under multiple pressure settings, with clogging depth and permeability measured in each case. Results indicate that, blinding clogging mechanisms and blocking defined by previous studies were observed for crushed stone, and a new mechanism of "infiltration" was revealed and defined. Whereas, the controlled aggregates performed excellently against clogging because only blinding was observed.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.5
• /
• pp.144-155
• /
• 2022

The Korea Coast Guard evaluates the risk of major coastal activity places to prevent coastal accidents, and patrols and manages them based on that, but it is not responding properly to the continuously increasing number of coastal accidents. The reason for this is that, despite the gradual expansion of coastal activity places, there is a lack of manpower to manage and supervise them, resulting in blind spots in coastal accident safety management. Therefore, in order to solve this problem, it is necessary to prepare more efficient and effective measures that check and supplement the current coastal safety management system. Coastal accidents show different characteristics of accident causes and places due to differences in the activity characteristics of users according to time. As a result of analyzing coastal accident data (2017~2021), the frequency of daytime accidents is high in the case of sea rock, beach, and offshore, where family leisure activities are frequent. In the case of wharf, tidal flat and bridge, where accidents due to drinking, disorientation, and suicide mainly occur, the frequency of accidents at night is high. In addition, there were more accidents on weekends when the number of users increased compared to weekdays. This trend indicates that the user's temporal activity characteristics must be reflected in the risk assessment of coastal activity places. Therefore, in this study, based on the case of coastal accidents, the characteristics of accidents at coastal activity places according to time were identified, and the criteria were presented for risk evaluation by grading them. It is expected that it will be possible to lay the foundation for reducing coastal accidents by efficiently managing and supervising coastal activity places over time using the presented evaluation criteria.

• Ecology and Resilient Infrastructure
• /
• v.8 no.2
• /
• pp.112-119
• /
• 2021

In 2012, the National Park Service conducted an ecological health assessment to efficiently preserve and manage the ecosystem. The need for improving pre-existing management indicators was recognized from the revised Natural Park Act because, while the indicators of the existing evaluation system focused on endangered species, ecosystem disturbance, diversity, water quality (BOD, DO), and habitat fragmentation, they did not reflect the lack of indicators for marine ecological assessment, policy changes, and the time demands. The evaluation results comprised a five-point grading system, which made the analysis of immediate changes, difficult. Therefore, the benthic pollution index (BPI) and habitat restoration indicators were added to improve the evaluation system. The National Park was assessed using 10 classifications, however, only four classifications were evaluated. The ratings were divided into five states, and ten classes were presented as pictograms. The assessment results showed a similar trend as the indicators were improved, increasing from level 3 to level 5. However, the results of the Wolaksan National Park after improvement in the indicators were lower than that before the improvement, whereas, for the Juwangsan National Park, it was higher. This study aims at contributing to the scientific and systematic management of the national park ecosystem by improving the ecological health assessment system.

• Journal of the Korean Wood Science and Technology
• /
• v.32 no.2
• /
• pp.90-95
• /
• 2004

Pitch pine (Pinus rigida) has been planted in Korean forests for several decades, primarily for erosion control and use as a fuel supply. To enhance its value, and especially potential use as lamina for structural glued laminated timber (glulam), log quality and lumber yield of pitch pine were evaluated in this study. Trees from pure pitch pine stands with an average diameter at breast height of 32 cm were felled and bucked into 3.6m long 15 cm minimum butt-end diameter logs. Over 80% of the logs were classified to No.2 or No.3 visual grade group. Upon sawing total lumber yield was 55.2%, 39.9% for structural glulam lamina, 7.2% for louver, and 8.1% for miscellaneous use. The final lumber yield for manufacturing structural glulam, after cross-cutting to eliminate knots and finger jointing, was only 15.3%. To enhance this manufacturing yield requires that the rate of knot-included lumber used as lamina be raised. However arrangement of the knot-included lamina, whose mechanical properties need to be accurately evaluated, must be optimized to minimize any reduction to the structural glulam strength. The log quality and lumber yield of pitch pine evaluated in this study are expected to facilitate proper planning for wood product manufacture in the Korean lumbering and glulam industrial field, which has not previously dealt with this species.

• Journal of Korea Water Resources Association
• /
• v.55 no.8
• /
• pp.589-601
• /
• 2022

Although drought is a natural phenomenon, its damage occurs in combination with regional physical and social factors. Especially, related to the supply and demand of various waters, drought causes great socio-economic damage. Even meteorological droughts occur with similar severity, its impact varies depending on the regional characteristics and water supply system. Therefore, this study assessed regional drought risk considering regional socio-economic factors and water supply system. Drought hazard was assessed by grading the joint drought management index (JDMI) which represents water shortage. Drought vulnerability was assessed by weighted averaging 10 socio-economic factors using Entropy, Principal Component Analysis (PCA), and Gaussian Mixture Model (GMM). Drought response capacity that represents regional water supply factors was assessed by employing Bayesian networks. Drought risk was determined by multiplying a cubic root of the hazard, vulnerability, and response capacity. For the drought hazard meaning the possibility of failure to supply water, Goesan-gun was the highest at 0.81. For the drought vulnerability, Daejeon was most vulnerable at 0.61. Considering the regional water supply system, Sejong had the lowest drought response capacity. Finally, the drought risk was the highest in Cheongju-si. This study identified the regional drought risk and vulnerable causes of drought, which is useful in preparing drought mitigation policy considering the regional characteristics in the future.

• 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 Science Education
• /
• v.46 no.1
• /
• pp.1-16
• /
• 2022

The purpose of this study is to explore learning progressions for global warming at middle school level. For this purpose, we conducted a construct modeling approach that specifies constructs, item designs, outcome spaces, and measurement model steps from April to October, 2021. In order to develop student assessment items, we analyzed the 2015 revised curriculum and textbooks of middle school and categorized a concept hierarchy for each construct to create a construct map. The assessment items were developed into multiple-choice, short answer, and essay questions according to the selected constructs to strengthen the linkage between the constructs and the items. Based on the three-step grading criteria for each item, an online assessment of 21 minor items developed for middle school students show that many students met 'high' level, but none met 'low' level. In this manner, the initial set lower anchor was reset to level 0, the original set upper anchor was lowered from level 4 to level 3, and the hypothetical learning progression for global warming was presented in the following order: phenomenal, conceptual, and mechanical understandings. The results of the research have raised implications for reorganizing the next science curriculum and improving the assessment system.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.7
• /
• pp.271-280
• /
• 2021

The purpose of this study was to conduct a subjective and objective evaluation to verify the improvements in acne skin conditions followed by the use of foam cleanser, skin toner, and a facial pack that contains bamboo vinegar. The research targets are 20 male and female high school students in Gwangju and Jeolla regions with acne skin of grade II and above based on the Korean Acne Grading System (KAGS). For the experiment, the subjects were classified between an experimental group with 10 subjects who used bamboo vinegar foam cleanser, skin toner, and facial pack and a control group with 10 subjects who used foam cleanser, skin toner, and facial pack without bamboo vinegar, and the subjects had to use the foam cleanser, skin toner, and facial pack for 12 weeks. In the case of skin improvement effects founded upon the objective measurement values, the experimental group showed a greater improvement for reducing the pores in the forehead, nose ridge, and left cheek (p<.001) compared to the control group, and the experiment group had higher satisfaction overall even for the skin improvement effects based on the subjective evaluation tool (p<.05, p<.001). The overall values of the satisfaction of the cosmetics showed that the experiment group had higher values (p<.01, p<.001) compared to the control group for the foam cleanser, skin toner, and facial pack, and there were statistically significant differences for usability in details (p<.01, p<.001). In conclusion, it was proven that bamboo vinegar is an effective natural cosmetic product material to improve acne skin conditions.