• Tuberculosis and Respiratory Diseases
• /
• v.43 no.3
• /
• pp.367-376
• /
• 1996

Background : The diagnosis of emphysema during life is based on a combination of clinical, functional, and radiographic findings, but this combination is relatively insensitive and nonspecific. The development of rapid, high-resolution third and fourth generation CT scanners has enabled us to resolve pulmonary parenchymal abnormalities with great precision. We compared the chest HRCT findings to the pulmonary function test and arterial blood gas analysis in pulmonary emphysema patients to test the ability of HRCT to quantify the degree of pulmonary emphysema. Methods : From october 1994 to october 1995, the study group consisted of 20 subjects in whom HRCT of the thorax and pulmonary function studies had been obtained at St. Mary's hospital. The analysis was from scans at preselected anatomic levels and incorporated both lungs. On each HRCT slice the lung parenchyma was assessed for two aspects of emphysema: severity and extent. The five levels were graded and scored separately for the left and right lung giving a total of 10 lung fields. A combination of severity and extent gave the degree of emphysema. We compared the HRCT quantitation of emphysema, pulmonary function tests, ABGA, CBC, and patients characteristics(age, sex, height, weight, smoking amounts etc.) in 20 patients. Results : 1) There was a significant inverse correlation between HRCT scores for emphysema and percentage predicted values of DLco(r = -0.68, p < 0.05), DLco/VA(r = -0.49, p < 0.05), FEV1(r = -0.53, p < 0.05), and FVC(r = -0.47, p < 0.05). 2) There was a significant correlation between the HRCT scores and percentage predicted values of TLC(r = 0.50, p < 0.05), RV(r = 0.64, p < 0.05). 3) There was a significant inverse correlation between the HRCT scores and PaO2(r = -0.48, p < 0.05) and significant correlation with D(A-a)O2(r = -0.48, p < 0.05) but no significant correlation between the HRCT scores and PaCO2. 4) There was no significant correlation between the HRCT scores and age, sex, height, weight, smoking amounts in patients, hemoglobin, hematocrit, and wbc counts. Conclusion : High-Resolution CT provides a useful method for early detection and quantitating emphysema in life and correlates significantly with pulmonary function tests and arterial blood gas analysis.

• Journal of Korean Home Economics Education Association
• /
• v.19 no.4
• /
• pp.37-56
• /
• 2007

The purpose of this study is to provide basic resources to the first-grade Home Economics Regular Teacher Qualification Program (FGHERTQP) in order to improve its operation plans. For the study, the three methods were carried out: an analysis on the curricula of FGHERTQP over six years since 2000, a questionnaire asking their satisfaction degrees and needs on the programs which was answered by the home economics teachers who were the participants of FGHERTQP, and several statistical analyses such as a descriptive-test, a $X^2$-test, a t-test, and one way ANOVA by using SPSS Win ver 10.0. The results of the study were as follows; Firstly, FGHERTQP has been operated ten times by five training centers during resent six years. Subject matters ($1{\sim}7$), whole numbers of lectures ($11{\sim}29$), and their allotted working hours ($111{\sim}136$) vary with individual training centers and operation years. Secondly, when using 5 point likert scales, Contents and Methods of evaluation marked 3.08 which were the lowest scores, and Qualification Training in General marked 3.72 which was the highest score among five fields of Qualification Training in General, Contents, Organizations, Methods and Evaluation. The overall scores were low. Thirdly, in needs analysis on offering subject matters, the participants wanted to study the field of home economics education more than that of subject contents. Looking about the highest needs classified by domains, Food Principles & Meal Management showed the highest in Foods. And Consumer Issues in Clothing & Textiles in Textiles, Upcoming Housing Cultures in Housing, Family Relationship in Child Development & Family Relationship, Juveniles and their daily life as a consumer in Family & Consumer Resources Management. Fourthly, training centers' lectures available had a significant influence on the satisfaction degrees according to general characteristic variations of the participants. That is, as a training center offers more lectures in the field of subject education than those of subject contents, the participants showed higher satisfaction degrees (p<.05).

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.79-96
• /
• 2012

As the pace of competition dramatically accelerates and the complexity of change grows, a variety of research have been conducted to improve firms' short-term performance and to enhance firms' long-term survival. In particular, researchers and practitioners have paid their attention to identify promising technologies that lead competitive advantage to a firm. Discovery of promising technology depends on how a firm evaluates the value of technologies, thus many evaluating methods have been proposed. Experts' opinion based approaches have been widely accepted to predict the value of technologies. Whereas this approach provides in-depth analysis and ensures validity of analysis results, it is usually cost-and time-ineffective and is limited to qualitative evaluation. Considerable studies attempt to forecast the value of technology by using patent information to overcome the limitation of experts' opinion based approach. Patent based technology evaluation has served as a valuable assessment approach of the technological forecasting because it contains a full and practical description of technology with uniform structure. Furthermore, it provides information that is not divulged in any other sources. Although patent information based approach has contributed to our understanding of prediction of promising technologies, it has some limitations because prediction has been made based on the past patent information, and the interpretations of patent analyses are not consistent. In order to fill this gap, this study proposes a technology forecasting methodology by integrating patent information approach and artificial intelligence method. The methodology consists of three modules : evaluation of technologies promising, implementation of technologies value prediction model, and recommendation of promising technologies. In the first module, technologies promising is evaluated from three different and complementary dimensions; impact, fusion, and diffusion perspectives. The impact of technologies refers to their influence on future technologies development and improvement, and is also clearly associated with their monetary value. The fusion of technologies denotes the extent to which a technology fuses different technologies, and represents the breadth of search underlying the technology. The fusion of technologies can be calculated based on technology or patent, thus this study measures two types of fusion index; fusion index per technology and fusion index per patent. Finally, the diffusion of technologies denotes their degree of applicability across scientific and technological fields. In the same vein, diffusion index per technology and diffusion index per patent are considered respectively. In the second module, technologies value prediction model is implemented using artificial intelligence method. This studies use the values of five indexes (i.e., impact index, fusion index per technology, fusion index per patent, diffusion index per technology and diffusion index per patent) at different time (e.g., t-n, t-n-1, t-n-2, ${\cdots}$) as input variables. The out variables are values of five indexes at time t, which is used for learning. The learning method adopted in this study is backpropagation algorithm. In the third module, this study recommends final promising technologies based on analytic hierarchy process. AHP provides relative importance of each index, leading to final promising index for technology. Applicability of the proposed methodology is tested by using U.S. patents in international patent class G06F (i.e., electronic digital data processing) from 2000 to 2008. The results show that mean absolute error value for prediction produced by the proposed methodology is lower than the value produced by multiple regression analysis in cases of fusion indexes. However, mean absolute error value of the proposed methodology is slightly higher than the value of multiple regression analysis. These unexpected results may be explained, in part, by small number of patents. Since this study only uses patent data in class G06F, number of sample patent data is relatively small, leading to incomplete learning to satisfy complex artificial intelligence structure. In addition, fusion index per technology and impact index are found to be important criteria to predict promising technology. This study attempts to extend the existing knowledge by proposing a new methodology for prediction technology value by integrating patent information analysis and artificial intelligence network. It helps managers who want to technology develop planning and policy maker who want to implement technology policy by providing quantitative prediction methodology. In addition, this study could help other researchers by proving a deeper understanding of the complex technological forecasting field.

• The Journal of Natural Sciences
• /
• v.7
• /
• pp.103-114
• /
• 1995

These experiments were conducted for decrease of injury by continuous cropping in the peanut fields of Chonbuk Wangkungarea. The continuous cropping field for four years was used in this experiment. Italian ryegrass and rye were cultivated andlime materials were distributed for improvement of soil fertility. The results were as follows; 1. Forage crops were cultivatedand lime materials were distributed on the continuous cropping field of peanut. The organic matter content of the expermentalplot cultivating Italian ryegrass was only 1.25%. The organic matter content of soil cultivated Italian ryegrass after distributedmagnesium lime was 1.37% and that of soil cultivated Italian ryegrass after distributed gypsum was 1.30%. It was highcontent comparing to that of soil distributed lime materials only. The organic matter content of soil cultivated rye after distributed gypsum was 1.77%. 2. The phosphate content of soil cutivated Italian ryegrass was 332ppm. The phosphate content ofsoil cultivated Italian ryegrass after distributed magnesium lime was 34Oppm and that of soil cultivated Italian ryegrass afterdistributed gypsum was 31 2ppm. The phosphate content of soil cultivated rye only was 386ppm. The phosphate content ofsoil cultivated rye after distributed gypsum was 41 8ppm. This phosphate content was lower than that of soil distributed limematerials only. 3. The phytotoxin content of soil cultivated Italian ryegrass after distributed magnesium lime was decreased to17.7% and that of soil cultivated Italian ryegrass after distributed gypsum was decreased to 25.3%. The phytotoxin content ofsoil cultivated rye after distributed magnesium lime was decreased to 12.0% and that of soil cultivated rye after distributedgypsum was decreased to 12.8% comparing to the phytotoxin content of soil distributed lime materials only. Italian ryegrasswas effective to decrease phytotoxin among the forage crops and gypsum was effective among the lime materials. 4. Abacterial wilt and a late spot of peanut which were known as, main reason of continuous cropping failure were surveyed.lnccidence of a bacterial wilt was 3.4% in the plot cultivated Italian ryegrass only and that was 2.9% in the plot cultivated ryeonly. lnccidence of a bacterial wilt was 2.5% in the plot cultivated Italian ryegrass after distributed magnesium lime and thatwas 2.3% in the plot cultivated rye after distributed gypsum. Inccidence plot cultivated forage crops was lower than that of plotdistributed lime materials. 5. Inccidence of a late spot was high in the plot cultivated forage crops ony, but it was low in the plotcultivated forage crops after distributed lime materials comparing to that of the control plot. 6. The growth and yield of peanutwere bad in the plot cultivated forage crops only comparing to the control plot distributed lime materials only. These resultswere same in the plot cultivated rye after distributed lime materials, but the growth and yield were grown up in the plotcultured Italian ryegrass after distributed lime materials.

• Journal of agricultural medicine and community health
• /
• v.26 no.1
• /
• pp.19-35
• /
• 2001

This study was conducted to investigate the internal changes and the countermeasure for performance improvement by Separation of Prescribing and Dispensing Practice (SPDP) in Health Center. Data were collected from two sources: Performance report before and after SPDP of 25 Health Centers in Kyongsangbuk-do and 6 Health Centers in Daegu-City and self-administerd questionnaire survey of 221 officials at health center. The results of this study were summarized as follows: Twenty-four health centers(77.4%) of 31 health centers took convenience measures for medical treatment of citizens and convenience measures were getting map of pharmacy, improvement of health center interior, introduction of order communication system in order. After the SPDP in health centers, 19.4% of health centers increased doctors and 25.8% decreased pharmacists. 58.1% of health centers showed that number of medical treatments were decreased. 96.4%, 80.6% 80.6% 96.7% of health centers showed that number of prescriptions, total medical treatment expenses, amounts paid by the insureds and the expenses to purchase drugs, respectively, were decreased. More than fifty percent(54.2%) of health centers responded that the relative importance of health works increased compared to medical treatments after the SPDP, and number of patients decreased compared to those in before the SPDP. And there was a drastic reduction in number of prescriptions, total medical treatment expenses, amounts paid by insureds, the expenses to purchase drugs after the SPDP. Above fifty percent(57.6%) of officers at health center responded that the function of medical treatment should be reduced after the SPDP. Fields requested improvement in health centers were 'development of heath works contents'(62.4%), 'rearrangement of health center personnel'(51.6%), 'priority setting for health works'(48.4%), 'restructuring the organization'(36.2%), 'quality impro­vement for medical services'(32.1%), 'replaning the budgets'(23.1%) in order. And to better the image of health centers, health center officers replied that 'health information management'(60.7%), 'public relations for health center'(15.8%), 'kindness of health center officers'(15.3%) were necessary in order. Health center officers suggested that 'vaccination program', 'health promotion', 'maternal and children health', 'communicable disease management', 'community health planning' were relatively important works, in order, performed by health center after SPDP. In the future, medical services in health centers should be cut down with a momentum of the SPDP so that health centers might reestablish their functions and roles as public health organizations, but quality of medical services must be improved. Also health centers should pay attention to residents for improving health through 'vaccination program', 'health promotion', 'mother-children health', 'acute and chronic communicable disease management', 'community health planning', 'oral health', 'chronic degenerative disease management', etc. And there should be a differentiation of relative importance between health promotion services and medical treatment services by character of areas(metropolitan, city, county).

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.101-123
• /
• 2013

Recently due to the advancements of science and information technology, the socio-economic business areas are changing from the industrial economy to a knowledge economy. Furthermore, companies need to do creation of new value through continuous innovation, development of core competencies and technologies, and technological convergence. Therefore, the identification of major trends in technology research and the interdisciplinary knowledge-based prediction of integrated technologies and promising techniques are required for firms to gain and sustain competitive advantage and future growth engines. The aim of this paper is to understand the recent research trend in management of technology (MOT) and to foresee promising technologies with deep knowledge for both technology and business. Furthermore, this study intends to give a clear way to find new technical value for constant innovation and to capture core technology and technology convergence. Bibliometrics is a metrical analysis to understand literature's characteristics. Traditional bibliometrics has its limitation not to understand relationship between trend in technology management and technology itself, since it focuses on quantitative indices such as quotation frequency. To overcome this issue, the network focused bibliometrics has been used instead of traditional one. The network focused bibliometrics mainly uses "Co-citation" and "Co-word" analysis. In this study, a keywords network analysis, one of social network analysis, is performed to analyze recent research trend in MOT. For the analysis, we collected keywords from research papers published in international journals related MOT between 2002 and 2011, constructed a keyword network, and then conducted the keywords network analysis. Over the past 40 years, the studies in social network have attempted to understand the social interactions through the network structure represented by connection patterns. In other words, social network analysis has been used to explain the structures and behaviors of various social formations such as teams, organizations, and industries. In general, the social network analysis uses data as a form of matrix. In our context, the matrix depicts the relations between rows as papers and columns as keywords, where the relations are represented as binary. Even though there are no direct relations between papers who have been published, the relations between papers can be derived artificially as in the paper-keyword matrix, in which each cell has 1 for including or 0 for not including. For example, a keywords network can be configured in a way to connect the papers which have included one or more same keywords. After constructing a keywords network, we analyzed frequency of keywords, structural characteristics of keywords network, preferential attachment and growth of new keywords, component, and centrality. The results of this study are as follows. First, a paper has 4.574 keywords on the average. 90% of keywords were used three or less times for past 10 years and about 75% of keywords appeared only one time. Second, the keyword network in MOT is a small world network and a scale free network in which a small number of keywords have a tendency to become a monopoly. Third, the gap between the rich (with more edges) and the poor (with fewer edges) in the network is getting bigger as time goes on. Fourth, most of newly entering keywords become poor nodes within about 2~3 years. Finally, keywords with high degree centrality, betweenness centrality, and closeness centrality are "Innovation," "R&D," "Patent," "Forecast," "Technology transfer," "Technology," and "SME". The results of analysis will help researchers identify major trends in MOT research and then seek a new research topic. We hope that the result of the analysis will help researchers of MOT identify major trends in technology research, and utilize as useful reference information when they seek consilience with other fields of study and select a new research topic.

• Korean Journal of Heritage: History & Science
• /
• v.50 no.4
• /
• pp.4-19
• /
• 2017

Kim Jeong-gi (pen-name: Changsan, Mar. 31, 1930 - Aug. 26, 2015) made a major breakthrough in the history of cultural property excavation in Korea: In 1959, he began to develop an interest in cultural heritage after starting work as an employee of the National Museum of Korea. For about thirty years until he retired from the National Research Institute of Cultural Heritage in 1987, he devoted his life to the excavation of our country's historical relics and artifacts and compiled countless data about them. He continued striving to identify the unique value and meaning of our cultural heritage in universities and excavation organizations until he passed away in 2015. Changsan spearheaded all of Korea's monumental archeological excavations and research. He is widely known at home and abroad as a scholar of Korean archeology, particularly in the early years of its existence as an academic discipline. As such, he has had a considerable influence on the development of Korean archeology. Although his multiple activities and roles are meaningful in terms of the country's archaeological history, there are limits to his contributions nevertheless. The Deoksugung Palace period (1955-1972), when the National Museum of Korea was situated in Deoksugung Palace, is considered to be a time of great significance for Korean archeology, as relics with diverse characteristics were researched during this period. Changsan actively participated in archeological surveys of prehistoric shell mounds and dwellings, conducted surveys of historical relics, measured many historical sites, and took charge of photographing and drawing such relics. He put to good use all the excavation techniques that he had learned in Japan, while his countrywide archaeological surveys are highly regarded in terms of academic history as well. What particularly sets his perspectives apart in archaeological terms is the fact that he raised the possibility of underwater tombs in ancient times, and also coined the term "Haemi Culture" as part of a theory of local culture aimed at furthering understanding of Bronze Age cultures in Korea. His input was simply breathtaking. In 1969, the National Research Institute of Cultural Heritage (NRICH) was founded and Changsan was appointed as its head. Despite the many difficulties he faced in running the institute with limited financial and human resources, he gave everything he had to research and field studies of the brilliant cultural heritages that Korea has preserved for so long. Changsan succeeded in restoring Bulguksa Temple, and followed this up with the successful excavation of the Cheonmachong Tomb and the Hwangnamdaechong Tomb in Gyeongju. He then explored the Hwangnyongsa Temple site, Bunhwangsa Temple, and the Mireuksa Temple site in order to systematically evaluate the Buddhist culture and structures of the Three Kingdoms Period. We can safely say that the large excavation projects that he organized and carried out at that time not only laid the foundations for Korean archeology but also made significant contributions to studies in related fields. Above all, in terms of the developmental process of Korean archeology, the achievements he generated with his exceptional passion during the period are almost too numerous to mention, but they include his systematization of various excavation methods, cultivation of archaeologists, popularization of archeological excavations, formalization of survey records, and promotion of data disclosure. On the other hand, although this "Excavation King" devoted himself to excavations, kept precise records, and paid keen attention to every detail, he failed to overcome the limitations of his era in the process of defining the nature of cultural remains and interpreting historical sites and structures. Despite his many roles in Korean archeology, the fact that he left behind a controversy over the identity of the occupant of the Hwangnamdaechong Tomb remains a sore spot in his otherwise perfect reputation.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.179-196
• /
• 2019

Recently, the "Smart Consumer" has been emerging. He or she is increasingly inclined to search for and purchase products by taking into account personal judgment or expert reviews rather than by relying on information delivered through manufacturers' advertising. This is especially true when purchasing cosmetics. Because cosmetics act directly on the skin, consumers respond seriously to dangerous chemical elements they contain or to skin problems they may cause. Above all, cosmetics should fit well with the purchaser's skin type. In addition, changes in global cosmetics consumer trends make it necessary to study this field. The desire to find one's own individualized cosmetics is being revealed to consumers around the world and is known as "Finding the Holy Grail." Many consumers show a deep interest in customized cosmetics with the cultural boom known as "K-Beauty" (an aspect of "Han-Ryu"), the growth of personal grooming, and the emergence of "self-culture" that includes "self-beauty" and "self-interior." These trends have led to the explosive popularity of cosmetics made in Korea in the Chinese and Southeast Asian markets. In order to meet the customized cosmetics needs of consumers, cosmetics manufacturers and related companies are responding by concentrating on delivering premium services through the convergence of ICT(Information, Communication and Technology). Despite the evolution of companies' responses regarding market trends toward customized cosmetics, there is no "Intelligent Data Platform" that deals holistically with consumers' skin condition experience and thus attaches emotions to products and services. To find the Holy Grail of customized cosmetics, it is important to acquire and analyze consumer data on what they want in order to address their experiences and emotions. The emotions consumers are addressing when purchasing cosmetics varies by their age, sex, skin type, and specific skin issues and influences what price is considered reasonable. Therefore, it is necessary to classify emotions regarding cosmetics by individual consumer. Because of its importance, consumer emotion analysis has been used for both services and products. Given the trends identified above, we judge that consumer emotion analysis can be used in our study. Therefore, we collected and indexed data on consumers' emotions regarding their cosmetics experiences focusing on consumers' language. We crawled the cosmetics emotion data from SNS (blog and Twitter) according to sales ranking ($1^{st}$ to $99^{th}$), focusing on the ample/serum category. A total of 357 emotional adjectives were collected, and we combined and abstracted similar or duplicate emotional adjectives. We conducted a "Consumer Sentiment Journey" workshop to build a "Consumer Sentiment Dictionary," and this resulted in a total of 76 emotional adjectives regarding cosmetics consumer experience. Using these 76 emotional adjectives, we performed clustering with the Self-Organizing Map (SOM) method. As a result of the analysis, we derived eight final clusters of cosmetics consumer sentiments. Using the vector values of each node for each cluster, the characteristics of each cluster were derived based on the top ten most frequently appearing consumer sentiments. Different characteristics were found in consumer sentiments in each cluster. We also developed a cosmetics experience pattern map. The study results confirmed that recommendation and classification systems that consider consumer emotions and sentiments are needed because each consumer differs in what he or she pursues and prefers. Furthermore, this study reaffirms that the application of emotion and sentiment analysis can be extended to various fields other than cosmetics, and it implies that consumer insights can be derived using these methods. They can be used not only to build a specialized sentiment dictionary using scientific processes and "Design Thinking Methodology," but we also expect that these methods can help us to understand consumers' psychological reactions and cognitive behaviors. If this study is further developed, we believe that it will be able to provide solutions based on consumer experience, and therefore that it can be developed as an aspect of marketing intelligence.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.5 no.3
• /
• pp.195-207
• /
• 2000

Organic and inorganic characteristics including bacterial cell number, enzyme activity, nutrients, and heavy metals have been monitored in twelve acrylic experimental tanks for two weeks to estimate and compare self-purification capacities in two Korean wet-land environments, tidal flat and rice field, which are possibly different with the environments in other countries because of their own climatic conditions. FW tanks, filled with rice field soils and fresh water, consist of FW1&2 (with paddy), FW3&4 (without paddy), and FW5&6 (newly reclaimed, without paddy). SW tanks, filled with tidal flat sediments and salt water, are SW1&2 (with anoxic silty mud), SW3&4 (anoxic mud), and SW5&6 (suboxic mud). Contaminated solution, which is formulated with the salts of Cu, Cd, As, Cr, Pb, Hg, and glucose+glutamic acid, was spiked into the supernatent waters in the tanks. Nitrate concentrations in supernatent waters as well as bacterial cell numbers and enzyme activities of soils in the FW tanks (except FW5&6) are clearly higher than those in the SW tanks. Phosphate concentrations in the SW1 tank increase highly with time compared to those in the other SW tanks. Removal rates of Cu, Cd, and As in supematent waters of the FW5&6 tanks are most slow in the FW tanks, while the rates in SW1&2 are most fast in the SW tanks. The rate for Pb in the SW1&2 tanks is most fast in the SW tanks, and the rate for Hg in the FW5&6 tanks is most slow in the FW tanks. Cr concentrations decrease generally with time in the FW tanks. In the SW tanks, however, the Cr concentrations decrease rapidly at first, then increase, and then remain nearly constant. These results imply that labile organic materials are depleted in the FW5&6 tanks compared to the FW1&2 and FW3&4 tanks. Removal of Cu, Cd, As from the supernatent waters as well as slow removal rates of the elements (including Hg) are likely due to the combining of the elements with organic ligands on the suspended particles and subsequent removal to the bottom sediments. Fast removal rates of the metal ions (Cu, Cd, As) and rapid increase of phosphate concentrations in the SW1&2 tanks are possibly due to the relatively porous anoxic sediments in the SW1&2 tanks compared to those in the SW3&4 tanks, efficient supply of phosphate and hydrogen sulfide ions in pore wates to the upper water body, complexing of the metal ions with the sulfide ions, and subsequent removal to the bottom sediments. Organic materials on the particles and sulfide ions from the pore waters are the major factors constraining the behaviors of organic/inorganic elements in the supernatent waters of the experimental tanks. This study needs more consideration on more diverse organic and inorganic elements and experimental conditions such as tidal action, temperature variation, activities of benthic animals, etc.