• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.155-175
• /
• 2017

As social data become into the spotlight, mainstream web search engines provide data indicate how many people searched specific keyword: Web Search Traffic data. Web search traffic information is collection of each crowd that search for specific keyword. In a various area, web search traffic can be used as one of useful variables that represent the attention of common users on specific interests. A lot of studies uses web search traffic data to nowcast or forecast social phenomenon such as epidemic prediction, consumer pattern analysis, product life cycle, financial invest modeling and so on. Also web search traffic data have begun to be applied to predict tourist inbound. Proper demand prediction is needed because tourism is high value-added industry as increasing employment and foreign exchange. Among those tourists, especially Chinese tourists: Youke is continuously growing nowadays, Youke has been largest tourist inbound of Korea tourism for many years and tourism profits per one Youke as well. It is important that research into proper demand prediction approaches of Youke in both public and private sector. Accurate tourism demands prediction is important to efficient decision making in a limited resource. This study suggests improved model that reflects latest issue of society by presented the attention from group of individual. Trip abroad is generally high-involvement activity so that potential tourists likely deep into searching for information about their own trip. Web search traffic data presents tourists' attention in the process of preparation their journey instantaneous and dynamic way. So that this study attempted select key words that potential Chinese tourists likely searched out internet. Baidu-Chinese biggest web search engine that share over 80%- provides users with accessing to web search traffic data. Qualitative interview with potential tourists helps us to understand the information search behavior before a trip and identify the keywords for this study. Selected key words of web search traffic are categorized by how much directly related to "Korean Tourism" in a three levels. Classifying categories helps to find out which keyword can explain Youke inbound demands from close one to far one as distance of category. Web search traffic data of each key words gathered by web crawler developed to crawling web search data onto Baidu Index. Using automatically gathered variable data, linear model is designed by multiple regression analysis for suitable for operational application of decision and policy making because of easiness to explanation about variables' effective relationship. After regression linear models have composed, comparing with model composed traditional variables and model additional input web search traffic data variables to traditional model has conducted by significance and R squared. after comparing performance of models, final model is composed. Final regression model has improved explanation and advantage of real-time immediacy and convenience than traditional model. Furthermore, this study demonstrates system intuitively visualized to general use -Youke Mining solution has several functions of tourist decision making including embed final regression model. Youke Mining solution has algorithm based on data science and well-designed simple interface. In the end this research suggests three significant meanings on theoretical, practical and political aspects. Theoretically, Youke Mining system and the model in this research are the first step on the Youke inbound prediction using interactive and instant variable: web search traffic information represents tourists' attention while prepare their trip. Baidu web search traffic data has more than 80% of web search engine market. Practically, Baidu data could represent attention of the potential tourists who prepare their own tour as real-time. Finally, in political way, designed Chinese tourist demands prediction model based on web search traffic can be used to tourism decision making for efficient managing of resource and optimizing opportunity for successful policy.

• Clinical and Experimental Pediatrics
• /
• v.50 no.1
• /
• pp.33-39
• /
• 2007

Purpose : In spite of medical advances, empyema is a serious complication of pneumonia in children. Vaccination practices and antibiotic prescribing practices promote the change of clinical manifestations of empyema and causative organisms. So we made a nationwide clinical observation of 122 cases of empyema in children from 32 hospitals during the 5 year period from September 1999 to August 2004. Methods : Demographic data, and clinical information on the course and management of empyema patients were collected retrospectively from medical records in secondary and tertiary hospitals in Korea. Results : One hundred twenty two patients were enrolled from 35 hospitals. The most frequent age group was 1-3 years, accounting for 48 percent of all cases. The male to female sex ratio was 1.2:1. The main symptoms were cough, fever, respiratory difficulty, lethargy and chest pain in order of frequency. Hematologic findings on admission revealed decreased hemoglobin levels ($10.4{\pm}1.6g/dL$) and increased leukocyte counts ($16,234.3{\pm}10,601.8/{\mu}L$). Pleural fluid obtained from patients showed high leukocyte counts ($30,365.8{\pm}64,073.0/{\mu}L$), high protein levels ($522.3{\pm}1582.3g/dL$), and low glucose levels ($88.1{\pm}523.5mg/dL$). Findings from pleural fluid cultures were positive in 80 cases(65.6 percent). The most common causative agent was Streptococcus pneumoniae. The majority of patients were treated with antibiotics and closed drainage. Some patients needed open drainage (16.4 percent) or decortication (3.3 percent). The mean duration of hospitalization was $28.6{\pm}15.3days$. Conclusion : We analyzed childhood empyema patients during a period of 5 years in Korean children. The most frequent age group was 1-3 years and the most common causative agent was Streptococcus pneumoniaeiae. The majority of patients were treated with antibiotics and close drainage.

• Journal of Korean Academy of Nursing Administration
• /
• v.3 no.1
• /
• pp.51-64
• /
• 1997

The purpose of the study was to introduce an integrated approach of new Casuistry and specified principlism in resolving ethical problems and studying nursing ethics. In studying clinical ethics and nursing ethics, there is no systematic research method. While nurses often experience ethical dilemmas in practice, much of previous research on nursing ethics has focused merely on describing the existing problems. In addition, ethists presented theoretical analysis and critics rather than providing the specific problems solving strategies. There is a need in clinical situations for an integrated method which can provide the objective description for existing problem situations as well as specific problem solving methods. We inherit two distinct ways of discussing ethical issues. One of these frames these issues in terms of principles, rules, and other general ideas; the other focuses on the specific features of particular kinds of moral cases. In the first way general ethical rules relate to specific moral cases in a theoretical manner, with universal rules serving as "axioms" from which particular moral judgments are deduced as theorems. In the seconds, this relation is frankly practical. with general moral rules serving as "maxims", which can be fully understood only in terms of the paradigmatic cases that define their meaning and force. Theoretical arguments are structured in ways that free them from any dependence on the circumstances of their presentation and ensure them a validity of a kind that is not affected by the practical context of use. In formal arguments particular conclusions are deduced from("entailed by") the initial axioms or universal principles that are the apex of the argument. So the truth or certainty that attaches to those axioms flows downward to the specific instances to be "proved". In the language of formal logic, the axioms are major premises, the facts that specify the present instance are minor premises, and the conclusion to be "proved" is deduced (follows necessarily) from the initial presises. Practical arguments, by contrast, involve a wider range of factors than formal deductions and are read with an eye to their occasion of use. Instead of aiming at strict entailments, they draw on the outcomes of previous experience, carrying over the procedures used to resolve earlier problems and reapply them in new problmatic situations. Practical arguments depend for their power on how closely the present circumstances resemble those of the earlier precedent cases for which this particular type of argument was originally devised. So. in practical arguments, the truths and certitudes established in the precedent cases pass sideways, so as to provide "resolutions" of later problems. In the language of rational analysis, the facts of the present case define the gounds on which any resolution must be based; the general considerations that carried wight in similar situations provide warrants that help settle future cases. So the resolution of any problem holds good presumptively; its strengh depends on the similarities between the present case and the prededents; and its soundness can be challenged (or rebutted) in situations that are recognized ans exceptional. Jonsen & Toulmin (1988), and Jonsen (1991) introduce New Casuistry as a practical method. The oxford English Dictionary defines casuistry quite accurately as "that part of ethics which resolves cases of conscience, applying the general rules of religion and morality to particular instances in which circumstances alter cases or in which there appears to be a conflict of duties." They modified the casuistry of the medieval ages to use in clinical situations which is characterized by "the typology of cases and the analogy as an inference method". A case is the unit of analysis. The structure of case was made with interaction of situation and moral rules. The situation is what surrounds or stands around. The moral rule is the essence of case. The analogy can be objective because "the grounds, the warrants, the theoretical backing, the modal qualifiers" are identified in the cases. The specified principlism was the method that Degrazia (1992) integrated the principlism and the specification introduced by Richardson (1990). In this method, the principle is specified by adding information about limitations of the scope and restricting the range of the principle. This should be substantive qualifications. The integrated method is an combination of the New Casuistry and the specified principlism. For example, the study was "Ethical problems experienced by nurses in the care of terminally ill patients"(Um, 1994). A semi-structured in-depth interview was conducted for fifteen nurses who mainly took care of terminally ill patients. The first stage, twenty one cases were identified as relevant to the topic, and then were classified to four types of problems. For instance, one of these types was the patient's refusal of care. The second stage, the ethical problems in the case were defined, and then the case was analyzed. This was to analyze the reasons, the ethical values, and the related ethical principles in the cases. Then the interpretation was synthetically done by integration of the result of analysis and the situation. The third stage was the ordering phase of the cases, which was done according to the result of the interpretation and the common principles in the cases. The first two stages describe the methodology of new casuistry, and the final stage was for the methodology of the specified principlism. The common principles were the principle of autonomy and the principle of caring. The principle of autonomy was specified; when competent patients refused care, nurse should discontinue the care to respect for the patients' decision. The principle of caring was also specified; when the competent patients refused care, nurses should continue to provide the care in spite of the patients' refusal to preserve their life. These specification may lead the opposite behavior, which emphasizes the importance of nurse's will and intentions to make their decision in the clinical situations.

• Journal of Hospice and Palliative Care
• /
• v.9 no.2
• /
• pp.93-100
• /
• 2006

Purpose: This study was designed to understand the doctor's attitude toward hospice and palliative care for terminal cancer patients. Methods: Specialists who work at general hospital were surveyed with questionnaires about hospice and palliative care for terminal cancer patients. The questionnaires comprise 17 items. The data were statistically analyzed. Results: Eighty one doctors responded. Their median age was 35 years old. Thirty six doctors (44.4%) were from internal medicine. The median of specialist's experience was 4 years. Forty three respondents (53.2%) have rarely examined and treated cancer patients even a week. Thirty seven respondents (45.6%) knew the exact definition of hospice and palliative care. Eighty respondents (98.8%) felt that hospice and palliative care is necessary, and 91.2% of them responded the necessity of palliative medicine specialist. As to the question 'Do you positively referred terminal cancer patient to hospice and palliative care?', 55 respondents (67.9%) responded 'Yes' and 22 (27.2%) 'No'. Among the 'Yes' respondents 17 (30.9%) had an experience of hesitation for referring patients to hospice and palliative care; the most common reason was the disagreement of family members (6, 35.3%). As for the reasons of responding 'No', 6 doctors (27.2%) did so because of their 'feeling of abandoning the patients' and the other f for the 'lack of information on the referral procedure for hospice and palliative care'. Thirty seven specialists (45.7%) thought it is most desirable for the patients to have hospice and palliative care for 3 months before death. Fifty eight specialists (71.6%) responded that hospice and palliative care help controlling the patient's psychological symptoms before all. Conclusion: While most doctors recognize the need of hospice and palliative care for patients with terminal ranter, their attitude toward hospice and palliative care was rather reserved. We suggest that continuing education, information and promotion for hospice and palliative care should be provided for doctors.

• Korean Journal of Clinical Laboratory Science
• /
• v.37 no.2
• /
• pp.65-70
• /
• 2005

Those specifications of the CLIA analytical tolerance limits are consistent with the performance goals in Six Sigma Quality Management. Six sigma analysis determines performance quality from bias and precision statistics. It also shows if the method meets the criteria for the six sigma performance. Performance standards calculates allowable total error from several different criteria. Six sigma means six standard deviations from the target value or mean value and about 3.4 failures per million opportunities for failure. Sigma Quality Level is an indicator of process centering and process variation total error allowable. Tolerance specification is replaced by a Total Error specification, which is a common form of a quality specification for a laboratory test. The CLIA criteria for acceptable performance in proficiency testing events are given in the form of an allowable total error, TEa. Thus there is a published list of TEa specifications for regulated analytes. In terms of TEa, Six Sigma Quality Management sets a precision goal of TEa/6 and an accuracy goal of 1.5 (TEa/6). This concept is based on the proficiency testing specification of target value +/-3s, TEa from reference intervals, biological variation, and peer group median mean surveys. We have found rules to calculate as a fraction of a reference interval and peer group median mean surveys. We studied to develop total error allowable from peer group survey results and CLIA 88 rules in US on 19 items TP, ALB, T.B, ALP, AST, ALT, CL, LD, K, Na, CRE, BUN, T.C, GLU, GGT, CA, phosphorus, UA, TG tests in chematology were follows. Sigma level versus TEa from peer group median mean CV of each item by group mean were assessed by process performance, fitting within six sigma tolerance limits were TP ($6.1{\delta}$/9.3%), ALB ($6.9{\delta}$/11.3%), T.B ($3.4{\delta}$/25.6%), ALP ($6.8{\delta}$/31.5%), AST ($4.5{\delta}$/16.8%), ALT ($1.6{\delta}$/19.3%), CL ($4.6{\delta}$/8.4%), LD ($11.5{\delta}$/20.07%), K ($2.5{\delta}$/0.39mmol/L), Na ($3.6{\delta}$/6.87mmol/L), CRE ($9.9{\delta}$/21.8%), BUN ($4.3{\delta}$/13.3%), UA ($5.9{\delta}$/11.5%), T.C ($2.2{\delta}$/10.7%), GLU ($4.8{\delta}$/10.2%), GGT ($7.5{\delta}$/27.3%), CA ($5.5{\delta}$/0.87mmol/L), IP ($8.5{\delta}$/13.17%), TG ($9.6{\delta}$/17.7%). Peer group survey median CV in Korean External Assessment greater than CLIA criteria were CL (8.45%/5%), BUN (13.3%/9%), CRE (21.8%/15%), T.B (25.6%/20%), and Na (6.87mmol/L/4mmol/L). Peer group survey median CV less than it were as TP (9.3%/10%), AST (16.8%/20%), ALT (19.3%/20%), K (0.39mmol/L/0.5mmol/L), UA (11.5%/17%), Ca (0.87mg/dL1mg/L), TG (17.7%/25%). TEa in 17 items were same one in 14 items with 82.35%. We found out the truth on increasing sigma level due to increased total error allowable, and were sure that the goal of setting total error allowable would affect the evaluation of sigma metrics in the process, if sustaining the same process.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.4
• /
• pp.95-104
• /
• 2006

The DMZ is a 248km long thin green line which has various landscapes of fields, hills and mountains. This study focused on western part of DMZ and vicinity which consist of abandoned rice paddy, wetlands and fields. The main purpose of this study is to detect the vegetation vitality from the western part of MDL to DMZ vicinity and identify and quantify ecological buffer(ecotone) width adopting logistic function derived from 'Vegetation Index-distance curve' using an Landsat ETM+ image acquired on June of 2002. Green leaf vegetation was quantified to identify the ecotone buffer in western DMZ and vicinity(civilian control area: CCA) using Transformed Vegetation Index(TVI) which is one of common measurement among various indices. Vegetation measurement from Military Demarcation Line(MDL) to vicinity area was investigated at 500m intervals to 10kms of southern and northern part of western DMZ and vicinity. The Logistic function models the sigmoid curve of growth with three stages of growth of initial competition and maturity. In the TVI-distance logistic curve, the maturity is high vegetation vitality, the competition is vitality changing, and the initial is low vitality. In the TVI-distance curve, maturity area of high TVI value is core area for ecological conservation, and the competition area between inflection points can be an ecotone(ecological buffer). In case of southern part, maximum TVI value is 221.92 and minimum is 207.16, and maximum TVI of northen part is 215.32 and minimum is 188.35. That means forest devastation of north Korean part of DMZ and vicinity is severer than that of south Korea. The width of core area for ecological conservation is 2,311m, and ecotone in the southern part is 5,339m, so minimum width from MDL for ecological conservation can be computed as 7,651m. In case of Northern part, the width of core area is 1,841m, and ecotone buffer is 5,014m, so ecological conservation width can be estimated as 6,855m. In case of northen part, width of estimated core area is less than that of DMZ width, which means ecological disturbance is very severe in northern part of western DMZ.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.1-17
• /
• 2017

The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

• Korean journal of communication and information
• /
• v.67
• /
• pp.177-208
• /
• 2014

This study inquires how human interest news on society section of newspapers had been modulated as multi-layered political narratives that would consistently have Koreans consider, realize and question on colonial situation as well as ethnic identity. Under totalitarian censorship of the colonial government, newspapers could not publish reports on political issues and current affairs, so society page of human interest such as crime, accident, conflict, disaster, and many kinds of sufferings of peoples to death would take great public attention and consequently be considered as a substitute of political section. Society page had enjoyed its influence on formation of public opinion of the colonized ethnic society and had maintained cultural-nationalist position ever since the founding of newspaper in mother-tongue in 1920. In colonial context, there is nothing non-political to the lives of the colonized, social facts would be necessary and happen to be modulated into a narrative that could trigger nationalist sentiment. For this end, news reporting of society section usually concentrated on aspects of 'Les Mis${\acute{e}}$rqbles', dramatic quality, and psychological factors in detail. Narrative style of news reporting got used to modulate factual informations with a proper taste of exaggeration, emotional expression, and commercial touch of exciting words. Even in a case of death by drug abuse, news was written to indicate what made him/her drive to miserable death on street, that is, what is de facto reason of all of social problems like as migration, hunger, leaving home, crime, suicide, violence, gambling, love affairs to death, adultery, and even opium habit. Those social problems and personal sufferings appeared up on newspaper 3rd page at daily base. Readers could acknowledge and identify what the real matter that should be resolved and then blame colonialism, capitalism, and militarism for those social problems. Journalists put values on inciting the colonized to realize the national and ethnic situation and feel sympathy for their people tied up by a common destiny. In this terms, news on society section of newspaper under Colonial Occupation were encoded as narratives of politically layered text and then decoded as intriguing sentiments against colonial dominance. I argue that society page of newspaper of colonial period engaged in a sort of cultural politics of sentiment and emotion which is a private area outside of imperial sight.

• Journal of the Korean Geographical Society
• /
• v.30 no.3
• /
• pp.296-310
• /
• 1995

Classification of spatial units into meaningful sets is an important procedure in spatial analysis. It is crucial in characterizing and identifying spatial structures. But traditional classification methods such as cluster analysis require an exact database and impose a clear-cut boundary between classes. Scrutiny of realistic classification problems, however, reveals that available infermation may be vague and that the boundary may be ambiguous. The weakness of conventional methods is that they fail to capture the fuzzy data and the transition between classes. Fuzzy subsets theory is useful for solving these problems. This paper aims to come to the understanding of theoretical foundations of fuzzy spatial analysis, and to find the characteristics of fuzzy classification methods. It attempts to do so through the literature review and the case study of urban classification of the Cities and Eups of Kyung-Nam Province. The main findings are summarized as follows: 1. Following Dubois and Prade, fuzzy information has an imprecise and/or uncertain evaluation. In geography, fuzzy informations about spatial organization, geographical space perception and human behavior are frequent. But the researcher limits his work to numerical data processing and he does not consider spatial fringe. Fuzzy spatial analysis makes it possible to include the interface of groups in classification. 2. Fuzzy numerical taxonomic method is settled by Deloche, Tranquis, Ponsard and Leung. Depending on the data and the method employed, groups derived may be mutually exclusive or they may overlap to a certain degree. Classification pattern can be derived for each degree of similarity/distance $\alpha$. By takina the values of $\alpha$ in ascending or descending order, the hierarchical classification is obtained. 3. Kyung-Nam Cities and Eups were classified by fuzzy discrete classification, fuzzy conjoint classification and cluster analysis according to the ratio of number of persons employed in industries. As a result, they were divided into several groups which had homogeneous characteristies. Fuzzy discrete classification and cluste-analysis give clear-cut boundary, but fuzzy conjoint classification delimit the edges and cores of urban classification. 4. The results of different methods are varied. But each method contributes to the revealing the transparence of spatial structure. Through the result of three kinds of classification, Chung-mu city which has special characteristics and the group of Industrial cities composed by Changwon, Ulsan, Masan, Chinhai, Kimhai, Yangsan, Ungsang, Changsungpo and Shinhyun are evident in common. Even though the appraisal of the fuzzy classification methods, this framework appears to be more realistic and flexible in preserving information pertinent to urban classification.