• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1663-1676
• /
• 2022

Recently, a number of deep-learning based land cover segmentation studies have been introduced. Some studies denoted that the performance of land cover segmentation deteriorated due to insufficient training data. In this study, we verified the improvement of land cover segmentation performance through data augmentation. U-Net was implemented for the segmentation model. And 2020 satellite-derived landcover dataset was utilized for the study data. The pixel accuracies were 0.905 and 0.923 for U-Net trained by original and augmented data respectively. And the mean F1 scores of those models were 0.720 and 0.775 respectively, indicating the better performance of data augmentation. In addition, F1 scores for building, road, paddy field, upland field, forest, and unclassified area class were 0.770, 0.568, 0.433, 0.455, 0.964, and 0.830 for the U-Net trained by original data. It is verified that data augmentation is effective in that the F1 scores of every class were improved to 0.838, 0.660, 0.791, 0.530, 0.969, and 0.860 respectively. Although, we applied data augmentation without considering class balances, we find that data augmentation can mitigate biased segmentation performance caused by data imbalance problems from the comparisons between the performances of two models. It is expected that this study would help to prove the importance and effectiveness of data augmentation in various image processing fields.

• The Korean Society of Law and Medicine
• /
• v.23 no.3
• /
• pp.117-137
• /
• 2022

Today, the medical system is changing into a comprehensive health care system in which collaborative relationships between medical professionals and non-medical personnels in neighboring occupational areas. The current medical act brands such "collaboration" as unlicensed medical practice, and punishes non-medical personnel who acted in the risk management of doctors as well as doctors collaborated with non-medical personnel as unlicensed medical practice. In order to narrow the gap between the legal system that regulates unlicensed medical practices and the medical reality, it is necessary to overcome the structural limitations of dualistic, nationalistic, and identity-oriented regulation of unlicensed medical practices. The legal interests of unlicensed medical practice have a dual nature as a personal legal interest of "human life and body" as well as a national legal interest of "maintenance and protection of the nation's medical license system", and it should be noted that the criteria for judging the legal interests protected by the regulations of criminal punishment should be found in "personal legal interest theory." In addition, when determining which behavior is a medical practice and evaluating its risk, the dimension of behavior and measures should be considered in a fair manner without being biased against the subject (identity) of the action. In other words, judging unlicensed medical practice should depend on whether the risk of side effects that may result from the act is reasonably managed. Considering the prospect of therapeutic dialogue between medical professionals and patients, it would be desirable for medical law policies to move in a way that does not fundamentally block the possibility of collaboration among pluralistic medical personalities.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.257-274
• /
• 2021

Although image segmentation is a critical part of object-based analysis of high resolution imagery, there has been lack of studies to evaluate the quality of image segmentation. In this study, we aimed to find practical and effective methods to obtain optimal parameters for image segmentation. Evaluations of image segmentation are divided into unsupervised, supervised, and qualitative visual interpretation methods. Using the multispectral UAV images, sampled from urban and forest over the Incheon Metropolitan City Park, three evaluation methods were compared. In overall, three methods showed very similar results regardless of the computational costs and applicability, although the optimal parameters determined by the evaluations were different between the urban and forest images. There is no single measure that outperforms in the unsupervised evaluation. Any combinations of intra-segment measures (V, COV, WV) and inter-segment measures (MI, BSH, DTNP) provided almost the same results. Although supervised method may be biased by subjective selection of reference data, it can be easily applied to detect object of interest. The qualitative visual interpretation on the segmentation results corresponded with the unsupervised and supervised evaluations.

• Journal of The Korean Association For Science Education
• /
• v.42 no.6
• /
• pp.597-610
• /
• 2022

In this study, we investigated actual cases of assessment science teachers conducted and the cases they preferred in a typical situation based on the curriculum in the context of 'Scientific Inquiries in the History' of Scientific Inquiry Experiment. A questionnaire composed of descriptive questions was developed and a survey was conducted with 70 science teachers with experience in teaching 'Scientific Inquiries in History'. Interviews were conducted with eight of them. The assessment cases were analyzed in terms of the assessment areas and assessment methods, and the results were compared. The analyses of the results revealed that 'scientific inquiry ability' accounted for the highest ratio of the assessment areas in the actual cases of assessment. There were few cases that assessed the core concepts presented in the curriculum, 'the nature of science' and 'scientists' inquiry methods'. The assessment methods were greatly biased toward the report method and various assessment methods were not used. In preferred cases of assessment, the ratio of cases that assessed the core concept increased slightly, however the frequencies remained at a low. As for the assessment methods in preferred cases of assessment, the measurement methods decreased, the performance methods increased, and the informal methods which were not shown in the actual cases appeared. However various assessment methods were still not used. The causes of the survey results were analyzed based on the opinions of the teachers who participated in the interviews. Based on above results, plans to actively conduct NOS assessments in Scientific Inquiry Experiment are discussed.

• Ecology and Resilient Infrastructure
• /
• v.10 no.1
• /
• pp.11-19
• /
• 2023

Alien species are known to threaten regional biodiversity globally, which has increased global interest regarding introduction of alien species. The Ministry of Environment of Korea designated species that have not yet been introduced into the country with potential threat as alert alien species to prevent damage to the ecosystem. In this study, potential habitats of Esox lucius and Maccullochella peelii, which are predatory and designated as alert alien fish, were predicted on a national basis. Habitat suitability was evaluated using EHSM (Ecological Habitat Suitability Model), and water temperature data were input to calculate Physiological Habitat Suitability (PHS). The prediction results have shown that PHS of the two fishes were mainly controlled by heat or cold stress, which resulted in biased habitat distribution. E. lucius was predicted to prefer the basins at high latitudes (Han and Geum River), while M. peelii preferred metropolitan areas. Through these differences, it was expected that the invasion pattern of each alien fish can be different due to thermal preference. Further studies are required to enhance the model's predictive power, and future predictions under climate change scenarios are required to aid establishing sustainable management plans.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.53-60
• /
• 2022

YouTube realistically shows fake news and biased content based on facts that have not been verified due to low entry barriers and ambiguity in video regulation standards. Therefore, this study aims to analyze the influence of the media and YouTube on individual behavior and their relationship. Data from YouTube and Twitter are randomly imported with selenium, beautiful soup, and Twitter APIs to classify the 31 most frequently mentioned keywords. Based on 31 keywords classified, data were collected from YouTube, Twitter, and Naver News, and positive, negative, and neutral emotions were classified and quantified with NLTK's Natural Language Toolkit (NLTK) Vader model and used as analysis data. As a result of analyzing the correlation of data, it was confirmed that the higher the negative value of news, the more positive content on YouTube, and the positive index of YouTube content is proportional to the positive and negative values on Twitter. As a result of this study, YouTube is not consistent with the emotion index shown in the news due to its secondary processing and affected characteristics. In other words, processed YouTube content intuitively affects Twitter's positive and negative figures, which are channels of communication. The results of this study analyzed that YouTube plays a role in assisting individual discrimination in the current situation where accurate judgment of information has become difficult due to the emergence of yellow media that stimulates people's interests and instincts.

• ALGAE
• /
• v.37 no.3
• /
• pp.227-237
• /
• 2022

Knowledge on the seaweeds of eastern Sorsogon in the Philippines is uneven. Not only is eastern Sorsogon among the areas of high seaweed diversity but locals there have interacted with seaweeds for ages. Despite seaweeds' assumed importance to Sorsoganon, ethnobotanical records are missing. In this study, we documented the traditional knowledge on seaweed use and determined the rate of knowledge transmission among the locals of eastern Sorsogon. Vernacular names and modes of preparation were given of the 12 identified species bearing culinary and medicinal importance. Ten species were eaten while three were used therapeutically. Based on ethnobotanical indices, Caulerpa chemnitzia ecad turbinata and Gelidiella acerosa were the most important seaweeds. The least cited was Caulerpa racemosa. Our study demonstrated that most of the seaweed resources in eastern Sorsogon remain largely untapped, as the identified ethnotaxa were only about 5% of the total seaweed species diversity reported for the area. The seaweed knowledge in eastern Sorsogon appeared to be homogenous across age groups with primary sources of knowledge biased towards female relatives (mothers and grandmothers) and to children as inheritors. Cessation of seaweed knowledge may come at a potential cost, as a significant fraction of the population did not transmit their knowledge to others. Our study furthered the interest in providing sophisticated resource management recommendations that consider the relationships of traditional and scientific knowledge of seaweed selection and use in eastern Sorsogon and beyond.

• Journal of Mushroom
• /
• v.20 no.3
• /
• pp.107-112
• /
• 2022

This study was conducted to reduce the phenomenon of biased cultivation and to pursue the diversification of mushroom items. We focused on developing Sparassis latifolia varieties with a short cultivation period, stable pinheading, and a high yield. We have collected and determined the characteristics of genetic resources domestically and abroad since 2016. We bred the unique domestic variety, "Hanyeoul" and the results of this study are as follows. The optimal temperatures for mycelial growth and fruit body growth were 22~25℃ and 19~21℃, respectively. The color of the pileus was pale-yellowish white, which was similar to the color of the control variety, "Neoul". The number of days required for cultivation was 125 for bottle cultivation and 98~102 for bag cultivation, which was shorter than the number of days required for the control variety. Bottle cultivation took 39 days shorter for the new variety than the control variety. The fruiting body of the new variety was similar in size or larger than that of the control variety. The pinheading rate was more than 90% in bottle cultivation and bag cultivation, which was more stable than pinheading in the control variety. The yield was 79.1 g/bottle (1,100 cc) for bottle cultivation, which was 22.6% higher than the yield of the control variety, and 641.1~689.5 g/bag (2.6 kg) for bag cultivation, which 5.8~10.4% higher than yield of the control variety.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.39-48
• /
• 2022

Cyberattacks around the world continue to increase, and their damage extends beyond government facilities and affects civilians. These issues emphasized the importance of developing a system that can identify and detect cyber anomalies early. As above, in order to effectively identify cyber anomalies, several studies have been conducted to learn BGP (Border Gateway Protocol) data through a machine learning model and identify them as anomalies. However, BGP data is unbalanced data in which abnormal data is less than normal data. This causes the model to have a learning biased result, reducing the reliability of the result. In addition, there is a limit in that security personnel cannot recognize the cyber situation as a typical result of machine learning in an actual cyber situation. Therefore, in this paper, we investigate BGP (Border Gateway Protocol) that keeps network records around the world and solve the problem of unbalanced data by using SMOTE. After that, assuming a cyber range situation, an autoencoder classifies cyber anomalies and visualizes the classified data. By learning the pattern of normal data, the performance of classifying abnormal data with 92.4% accuracy was derived, and the auxiliary index also showed 90% performance, ensuring reliability of the results. In addition, it is expected to be able to effectively defend against cyber attacks because it is possible to effectively recognize the situation by visualizing the congested cyber space.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.693-702
• /
• 2022

The purpose of this study is to present the problems of urban ecosystem imbalance in Seoul and the need to restore housing functions through comparison with Manhattan, New York, which grew earlier than Seoul and has been striving to solve urban problems and restore urban ecosystems. The residential status in urban commercial use areas was investigated through analysis of the total amount of residential space, characteristics of each type of residential building, and distribution of residential buildings. Through this, it can be seen that most of the space in Seoul's historic city center is biased toward commercial roads, and there are significantly insufficient high- and high-density mixed-use buildings suitable for urban dwellings compared to Manhattan's. In addition, it can be seen that the complex building in the historical city center of Seoul is located adjacent to the outskirts of the target site. In conclusion, Seoul's historical city center does not provide an appropriate residential space for creating an urban ecosystem, and it is necessary to come up with measures to restore housing functions.