• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• 제27권2호
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• Journal of Korea Water Resources Association
• /
• 제57권9호
• /
• pp.615-626
• /
• 2024

To accurately and efficiently monitor soil moisture (SM) across South Korea, this study developed a SM estimation model that integrates the cloud computing platform Google Earth Engine (GEE) and Automated Machine Learning (AutoML). Various spatial information was utilized based on Terra MODIS (Moderate Resolution Imaging Spectroradiometer) and the global precipitation observation satellite GPM (Global Precipitation Measurement) to test optimal input data combinations. The results indicated that GPM-based accumulated dry-days, 5-day antecedent average precipitation, NDVI (Normalized Difference Vegetation Index), the sum of LST (Land Surface Temperature) acquired during nighttime and daytime, soil properties (sand and clay content, bulk density), terrain data (elevation and slope), and seasonal classification had high feature importance. After setting the objective function (Determination of coefficient, R² ; Root Mean Square Error, RMSE; Mean Absolute Percent Error, MAPE) using AutoML for the combination of the aforementioned data, a comparative evaluation of machine learning techniques was conducted. The results revealed that tree-based models exhibited high performance, with Random Forest demonstrating the best performance (R² : 0.72, RMSE: 2.70 vol%, MAPE: 0.14).

• Journal of Intelligence and Information Systems
• /
• 제20권4호
• /
• pp.43-58
• /
• 2014

As the use of trading systems has increased rapidly, many researchers have become interested in developing effective stock market prediction models using artificial intelligence techniques. Stock market prediction involves multifaceted interactions between market-controlling factors and unknown random processes. A successful stock prediction model achieves the most accurate result from minimum input data with the least complex model. In this research, we develop a combination model of ${\pi}$-fuzzy logic and support vector machine (SVM) models, using a genetic algorithm to optimize the parameters of the SVM and ${\pi}$-fuzzy functions, as well as feature subset selection to improve the performance of stock market prediction. To evaluate the performance of our proposed model, we compare the performance of our model to other comparative models, including the logistic regression, multiple discriminant analysis, classification and regression tree, artificial neural network, SVM, and fuzzy SVM models, with the same data. The results show that our model outperforms all other comparative models in prediction accuracy as well as return on investment.

• The Journal of the Korea Contents Association
• /
• 제8권3호
• /
• pp.86-96
• /
• 2008

General development basis of letter system is recognized by formative value in terms of its function and structure. principle of clustered writing is the most significant feature of Hangeul typography as considered that it is based on function and formativeness. Thus, not only by changes with its form but also by its characteristic syllable combination, space structure is made as consonants and vowels are combined in single letter, then the combination develop into word, sentence, paragraph to make second, third space structure character. This character has significant impact on readability that is core function of typography. With this property, space structure character is regarded as very important component of Hangeul typography. First, space structure character of Hangeul typography is reviewed by relating it to visual perception of gestalt psychology and compared square-framed letter and framed latter By applying square-framed letter and framed latter in same sentence, legibility and readability were studied. Researcher has found that space structure character of Hangeul typography has significant impact on its function, and in terms of future design, it is very critical not only for design but also for communication environment as space structure formativeness of Hangeul typography interact with communication that is basic concept.

• Journal of Intelligence and Information Systems
• /
• 제18권3호
• /
• pp.1-12
• /
• 2012

There are many trees in a roadside, parks or facilities for landscape. Although we are easily seeing a tree in around, it would be difficult to classify it and to get some information about it, such as its name, species and surroundings of the tree. To find them, you have to find the illustrated books for plants or search for them on internet. The important components of a tree are leaf, flower, bark, and so on. Generally we can classify the tree by its leaves. A leaf has the inherited features of the shape, vein, and so on. The shape is important role to decide what the tree is. And texture included in vein is also efficient feature to classify them. This paper evaluates the performance of a leaf classification system using both shape and texture features. We use Fourier descriptors for shape features, and both gray-level co-occurrence matrices and wavelets for texture features, and used combinations of such features for evaluation of images from the Flavia dataset. We compared the recognition rates and the precision-recall performances of these features. Various experiments showed that a combination of shape and texture gave better results for performance. The best came from the case of a combination of features of shape and texture with a flipped contour for a Fourier descriptor.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제16권5호
• /
• pp.3315-3322
• /
• 2015

Staphylococcus aureus is the major causative organism of nasocomial infection being the important pathogen in the clinic. Appearance of staphylococcus aureus resistant to methicillin (MRSA) is becoming a big problem in clinics and dynamics all over the world acquiring antibiotic resistance with virulence factors as its feature differentiated from other pathogenic bacteria fast. This research intended to compare and analyze the correlation of antibiotics resistance between strains with toxin genes and distribution of toxin genes of MRSA 101 strains acquired from clinical specimen in one general hospital (enterotoxin(se), toxic shock syndrome toxin-1(tst), exfoliative toxin(et), Panton Valentine leukocidin(pvl)). seg gene, isolated the most among toxin genes, was detected in 59 strains (58.4%) and more than two toxin genes were detected in 70 strains (69.3%). As a combination possessing toxin genes, it was detected in 19 strains (18.8%) as seb, sec, seg, sei, tst and the second frequent combination was sec, seg, sei shown in 11 strains (10.9%). 19 strains (18.8%) with combinations of toxin genes same with seb, sec, seg, sei, tst had 100% resistance Ampicillin, Benzylpenicillin, Ciprofloxacin, Clindamycin, Gentamicin, Erythromycin, Telithromycin, Tetracycline antibiotics. Strains with many toxin genes showed high correlation of antibiotic resistance. Afterwards, effective therapy and thorough infection management should be preceded not to spread the resistance of MRSA strain.

• Cross-Cultural Studies
• /
• 제42권
• /
• pp.205-240
• /
• 2016

The combination of animals has been developed in each of the cultural spheres as a method of metaphor and symbolism of the cultural code. However, its symbolism is not a fixed constant, but a variable and relative constant. This work focused on its features in comparison with East Asian cultural spheres comedic stories and proverbs. Consequently, several features were identified. First, the combinations of animals in similar comedic stories and proverbs among Korea, Japan and China show a difference in point of view. Korean focuses on the difference of the two animals, but Chinese and Japanese focus on the differences in value and level. Second, the method of anthropomorphization is relatively more developed in China and Japan than Korea. The combinations of animals of Chinese comedic stories and proverbs particularly in the field of anthropomorphization, are most focused on age and sex of the animal. The animal's age or sex remains mostly undetermined in Korean animal's proverbs, unlike Chinese proverbs. On the other hand, two animals in Japanese comedic stories and proverbs are usually of the male and female gender from. Third, the combinations of animals of Chinese and Japanese focus on the animal's body and its characteristics of action. Chinese and Japanese combine the characteristics of the two animal's bodies and actions. This feature apparently caused the resultant combinations of the animal's body parts, for example, the Dragon. Understanding of the combinations of two animals is a good portal into the features of East Asian culture sphere.

• Journal of Sericultural and Entomological Science
• /
• 제21권2호
• /
• pp.11-19
• /
• 1979

This has been carried out how the sericin insoluble fixations of raw silk should be with potassium alum. This is learned from the leather tanning technique which the process works with collagen, a kind of proteins. Former reports had shown such works, however, they did not consider the moisture absorbability after their process reports by using chromium alum, formalin or vinyl acetate grafting. This report, however, paid attention to protect such absorbability as well as sericin fixation, so far it may be useful for plactical use of silk. In order to clear how the sericin is fixed with such chemicals, fundermental mechanism of weding process and chemical reaction against proteins were also discussed. The obtained results of the report are as followings. 1. Alum should not be treated for raw silk with high temperature bath like other reports because such treat induces raw silk to be stiffly after the treat. 2. It is recommended that raw silk should be treated with alum solution at room temperature for more than three hours. Even in this case, the use of only alum with raw silk could to fix sericin some how, but it increased the water proofness of the silk. 3. 1% of alum solution was found to be able to fix the sericin of raw silk. 4. In case we consider only sericin fixations, a combination treat of 1% alum for three hours and 0.5% NaOH for ten minutes method showed the best result. 5. In case we consider sericin insoluble fixation and moisture absorbility, the reversive combination of the above process was found to be the best results. 6. Sericin fixing evidence was shown with drying feature curves of wed each treated silk where we could to analyze how the chemical nature is changed after each treat. 7. Deguming ratio may be obtained up to 4.3% after the alum combination treat with regular raw silk. Such ratio was considered to be good enough for the purpose when the textile is washed with warm soap water. 8. Moisture absorbability of the combination treat of alum and NaOH was found to be good enough as well as non treated silk. 9. The tenacity and elongation of the treated silk did not change even after three month. 10. Above all, this method is considered to be better process than other coloured fixing (tannin method. Cr-alum method) or smell fixing (formalin method. vinyl acetate method).

• The Research Journal of the Costume Culture
• /
• 제17권5호
• /
• pp.849-865
• /
• 2009

This research is a study of fashion design that applied formative features of formal beauty of architecture into clothing design; we focused on Gaudi's architectural style as well as Art Nouveau style that became popular from the end of the 19th century to the beginning of the 20th century. We noted that in general the simple and flat features of cloth impose a limitation on the expression of formal features in clothing design, but a unique diversity of designs can be achieved, evoking a sense of freshness by an ideal combination of flat patterns and draping. The aim of this research is to present a possibility of extending the sphere of design expression by creating three-dimensional clothes with pattern-cutting skills and applications of three-dimensional patterns as well as flat patterns found in Gaudi's works of architecture that are distinguished in curvaceousness and formal beauty. As for the research method, we reviewed previous studies by making a close review of books, papers, the pictures and web sites related to this topic. We made our clothes on the basis of this theoretical consideration. We found the following points. First, by presenting a work of fashion inspired by architectural designs, we realized that formal beauty in architect can become a motive for clothing design in a broad scale by noting the formal images, decoration details, and formative features of architectural works. Second, the characteristic lines of Gaudi's architecture are suitable to be adapted for expressing the detailed lines of decoration in clothes. Third, we can express formative beauty in clothes by highlighting the variation of shapes and lines through various attempts of change in background pattern, even though there is a limitation in the availability of cloth material because we must choose pieces of cloth with right texture and thickness that can be cut and sewn appropriately to express formative beauty. Fourth, we confirmed that it was possible to create unique formative designs by a creative application of both flat and three-dimensional cutting.