• 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.

• (The)Study of the Eastern Classic
• /
• no.63
• /
• pp.9-41
• /
• 2016

This paper focuses on 'clean(cheong: 淸)' kinds of style terminologies among various style terminologies appearing in Heo Gyun's Seongsushihwa("惺?詩話") and tries to analyze the distinctive points which 'clean(cheong: 淸)' kinds of style terminologies include. In Heo Gyun's Seongsushihwa, 11 of 'clean' kinds of style terminologies, such as "cheonggyeong(淸勁), cheonghryang(淸亮), cheongryeo(淸麗), cheongseom(淸贍), cheongso(淸?), cheongweol(淸越), cheongjang(淸壯), cheongjeol(淸絶), cheongjeol(淸切), cheongchang(淸?), cheongcho(淸楚)," were used. This paper focuses and analyzes 'cheonggyeong(淸勁)', 'cheongjeol(淸切)', 'cheongcho(淸楚)', and 'cheongweol(淸越)' that he suggested through applying to real literary pieces. The result of analysis indicates that 'clean' kinds of style terminologies 'cheonggyeong', 'cheongjeol', 'cheongcho', and 'cheongweol' share the same 1st character 'clean(淸)', yet have distinctive qualities by the 2nd characters. These 4 style terminologies all share 'cheong(淸)' image which means clear and clean, yet each one has the attribute of the 2nd character that indicates each one's individual characteristic. It is apparent that 'Cheonggyeong(淸勁)' reflects the 'gyeong(勁)' image meaning upright and solid and implies poems of poets' steadfast spirit within clear boundary; 'cheongjeol(淸切)' reflects the 'jeol(切)' image meaning either desperation and imminence or pitifulness and sorrow and implies poems of poets' urgent and pitiful emotions within clear and clean boundary; 'cheongcho(淸楚)' reflects the 'cho(楚)' image meaning either delicacy and fineness or slenderness and tenderness and implies poems of poets' beautiful but not luxurious, delicate and tender emotions within clear and clean boundary; and 'cheongweol(淸越)' reflects the image of 'weol(越)' meaning unworldliness and excellency and implies poems, within clear and clean boundary, of excellent appearance and mentality surpassing mundane world. Compared with the 1st character's attributes of the style terminologies which Heo Gyun used, the 2nd characters's attributes do not appear that vivid. Especially, in the case that the 2nd characters have similar meanings, it is not easy to clarify the categories. Indeed, in order to grasp clear and distinctive qualities of style terminologies, the kinds of them need to be initially categorized by the 1st characters, and then sorted by the 2nd characters. In this case, the contents which the 2nd characters of style terminologies indicate should be considered. It is because style terminologies explain both literary pieces' aesthetic qualities and writers' personalities, and because explanations about literary pieces' aesthetic qualities includes not only the conclusive poetic or semantic boundaries which literary pieces' created but also literary pieces' creation processes and expression techniques. Through the style terminologies with Heo Gyun used in Seongsushihwa, it can be aware that he evaluated poems focussing more on the conclusive semantic boundaries that poets' spirits and poems created than expression techniques or creation methods. The overall aspects Heo Gyun's such style criticism has will be checked out in more detail through further studies by examining more materials.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.73-95
• /
• 2021

This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.227-252
• /
• 2018

The evolution of instant communication has mirrored the development of the Internet and messenger applications are among the most representative manifestations of instant communication technologies. In messenger applications, senders use emoticons to supplement the emotions conveyed in the text of their messages. The fact that communication via messenger applications is not face-to-face makes it difficult for senders to communicate their emotions to message recipients. Emoticons have long been used as symbols that indicate the moods of speakers. However, at present, emoticon-use is evolving into a means of conveying the psychological states of consumers who want to express individual characteristics and personality quirks while communicating their emotions to others. The fact that companies like KakaoTalk, Line, Apple, etc. have begun conducting emoticon business and sales of related content are expected to gradually increase testifies to the significance of this phenomenon. Nevertheless, despite the development of emoticons themselves and the growth of the emoticon market, no suitable emoticon recommendation system has yet been developed. Even KakaoTalk, a messenger application that commands more than 90% of domestic market share in South Korea, just grouped in to popularity, most recent, or brief category. This means consumers face the inconvenience of constantly scrolling around to locate the emoticons they want. The creation of an emoticon recommendation system would improve consumer convenience and satisfaction and increase the sales revenue of companies the sell emoticons. To recommend appropriate emoticons, it is necessary to quantify the emotions that the consumer sees and emotions. Such quantification will enable us to analyze the characteristics and emotions felt by consumers who used similar emoticons, which, in turn, will facilitate our emoticon recommendations for consumers. One way to quantify emoticons use is metadata-ization. Metadata-ization is a means of structuring or organizing unstructured and semi-structured data to extract meaning. By structuring unstructured emoticon data through metadata-ization, we can easily classify emoticons based on the emotions consumers want to express. To determine emoticons' precise emotions, we had to consider sub-detail expressions-not only the seven common emotional adjectives but also the metaphorical expressions that appear only in South Korean proved by previous studies related to emotion focusing on the emoticon's characteristics. We therefore collected the sub-detail expressions of emotion based on the "Shape", "Color" and "Adumbration". Moreover, to design a highly accurate recommendation system, we considered both emotion-technical indexes and emoticon-emotional indexes. We then identified 14 features of emoticon-technical indexes and selected 36 emotional adjectives. The 36 emotional adjectives consisted of contrasting adjectives, which we reduced to 18, and we measured the 18 emotional adjectives using 40 emoticon sets randomly selected from the top-ranked emoticons in the KakaoTalk shop. We surveyed 277 consumers in their mid-twenties who had experience purchasing emoticons; we recruited them online and asked them to evaluate five different emoticon sets. After data acquisition, we conducted a factor analysis of emoticon-emotional factors. We extracted four factors that we named "Comic", Softness", "Modernity" and "Transparency". We analyzed both the relationship between indexes and consumer attitude and the relationship between emoticon-technical indexes and emoticon-emotional factors. Through this process, we confirmed that the emoticon-technical indexes did not directly affect consumer attitudes but had a mediating effect on consumer attitudes through emoticon-emotional factors. The results of the analysis revealed the mechanism consumers use to evaluate emoticons; the results also showed that consumers' emoticon-technical indexes affected emoticon-emotional factors and that the emoticon-emotional factors affected consumer satisfaction. We therefore designed the emoticon recommendation system using only four emoticon-emotional factors; we created a recommendation method to calculate the Euclidean distance from each factors' emotion. In an attempt to increase the accuracy of the emoticon recommendation system, we compared the emotional patterns of selected emoticons with the recommended emoticons. The emotional patterns corresponded in principle. We verified the emoticon recommendation system by testing prediction accuracy; the predictions were 81.02% accurate in the first result, 76.64% accurate in the second, and 81.63% accurate in the third. This study developed a methodology that can be used in various fields academically and practically. We expect that the novel emoticon recommendation system we designed will increase emoticon sales for companies who conduct business in this domain and make consumer experiences more convenient. In addition, this study served as an important first step in the development of an intelligent emoticon recommendation system. The emotional factors proposed in this study could be collected in an emotional library that could serve as an emotion index for evaluation when new emoticons are released. Moreover, by combining the accumulated emotional library with company sales data, sales information, and consumer data, companies could develop hybrid recommendation systems that would bolster convenience for consumers and serve as intellectual assets that companies could strategically deploy.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.3
• /
• pp.351-360
• /
• 1995

Background: Pressure support(PS) is becomimg a widely accepted method of mechanical ventilation either for total unloading or for partial unloading of respiratory muscle. The aim of the study was to find out if PS exert different effects on respiratory mechanics in synchronized intermittent mandatory ventilation(SIMV) and continuous positive airway pressure (CPAP) modes. Methods: 5, 10 and 15 cm $H_2O$ of PS were sequentially applied in 14 patients($69{\pm}12$ yrs, M:F=9:5) and respiratory rate (RR), tidal volume($V_T$), work of breathing(WOB), pressure time product(PTP), $P_{0.1}$, and $T_1/T_{TOT}$ were measured using the CP-100 pulmonary monitor(Bicore, USA) in SIMV and CPAP modes respectively. Results: 1) Common effects of PS on respiratory mechanics in both CPAP and SIMV modes As the level of PS was increased(0, 5, 10, 15 cm $H_2O$), $V_T$ was increased in CPAP mode($0.28{\pm}0.09$, $0.29{\pm}0.09$, $0.31{\pm}0.11$, $0.34{\pm}0.12\;L$, respectively, p=0.001), and also in SIMV mode($0.31{\pm}0.15$, $0.32{\pm}0.09$, $0.34{\pm}0.16$, $0.36{\pm}0.15\;L$, respectively, p=0.0215). WOB was decreased in CPAP mode($1.40{\pm}1.02$, $1.01{\pm}0.80$, $0.80{\pm}0.85$, $0.68{\pm}0.76$ joule/L, respectively, p=0.0001), and in SIMV mode($0.97{\pm}0.77$, $0.76{\pm}0.64$, $0.57{\pm}0.55$, $0.49{\pm}0.49$ joule/L, respectively, p=0.0001). PTP was also decreased in CPAP mode($300{\pm}216$, $217{\pm}165$, $179{\pm}187$, $122{\pm}114cm$ $H_2O{\cdot}sec/min$, respectively, p=0.0001), and in SIMV mode($218{\pm}181$, $178{\pm}157$, $130{\pm}147$, $108{\pm}129cm$ $H_2O{\cdot}sec/min$, respectively, p=0.0017). 2) Different effects of PS on respiratory mechanics in CP AP and SIMV modes By application of PS (0, 5, 10, 15 cm $H_2O$), RR was not changed in CPAP mode($27.9{\pm}6.7$, $30.0{\pm}6.6$, $26.1{\pm}9.1$, $27.5{\pm}5.7/min$, respectively, p=0.505), but it was decreased in SIMV mode ($27.4{\pm}5.1$, $27.8{\pm}6.5$, $27.6{\pm}6.2$, $25.1{\pm}5.4/min$, respectively, p=0.0001). $P_{0.1}$ was reduced in CPAP mode($6.2{\pm}3.5$, $4.8{\pm}2.8$, $4.8{\pm}3.8$, $3.9{\pm}2.5\;cm$ $H_2O$, respectively, p=0.0061), but not in SIMV mode($4.3{\pm}2.1$, $4.0{\pm}1.8$, $3.5{\pm}1.6$, $3.5{\pm}1.9\;cm$ $H_2O$, respectively, p=0.054). $T_1/T_{TOT}$ was decreased in CPAP mode($0.40{\pm}0.05$, $0.39{\pm}0.04$, $0.37{\pm}0.04$, $0.35{\pm}0.04$, respectively, p=0.0004), but not in SIMV mode($0.40{\pm}0.08$, $0.35{\pm}0.07$, $0.38{\pm}0.10$, $0.37{\pm}0.10$, respectively, p=0.287). 3) Comparison of respiratory mechanics between CPAP+PS and SIMV alone at same tidal volume. The tidal volume in CPAP+PS 10 cm $H_2O$ was comparable to that of SIMV alone. Under this condition, the RR($26.1{\pm}9.1$, $27.4{\pm}5.1/min$, respectively, p=0.516), WOB($0.80{\pm}0.85$, 0.97+0.77 joule/L, respectively, p=0.485), $P_{0.1}$($3.9{\pm}2.5$, $4.3{\pm}2.1\;cm$ $H_2O$, respectively, p=0.481) were not different between the two methods, but PTP($179{\pm}187$, $218{\pm}181 cmH_2O{\cdot}sec/min$, respectively, p=0.042) and $T_1/T_{TOT}$($0.37{\pm}0.04$, $0.40{\pm}0.08$, respectively, p=0.026) were significantly lower in CPAP+PS than in SIMV alone. Conclusion: PS up to 15 cm $H_2O$ increased tidal volume, decreased work of breathing and pressure time product in both SIMV and CPAP modes. PS decreased respiration rate in SIMV mode but not in CPAP mode, while it reduced central respiratory drive($P_{0.1}$) and shortened duty cycle ($T_1/T_{TOT}$) in CPAP mode but not in SIMV mode. By 10 em $H_2O$ of PS in CPAP mode, same tidal volume was obtained as in SIMV mode, and both methods were comparable in respect to RR, WOB, $P_{0.1}$, but CPAP+PS was superior in respect to the efficiency of the respiratory muscle work (PTP) and duty cycle($T_1/T_{TOT}$).

• Journal of Korean Society of Archives and Records Management
• /
• v.1 no.1
• /
• pp.201-230
• /
• 2001

Conserving the recored cultural inheritance is actually the duty of all of us. Above all, the management and conservation of archives and documents is up to archivists who have technical knowledge about archival science. Archivists have to not only conserve archives and documents but also carry out classifying and appraising them in order to define them as current historic ones. The fundamental education about archival science is made up of history and law. Because Archive is the organisation which manage archives and documents produced by legal and administrative actions. Although there are still arguments about technical knowledge and degree archivists have to acquire, most of them prefer the studies related with history and emphasize legal studies to be the general boundary of archivits' ideology and trust. The training course about conservation of archives is conducted in about 9 National Archives of Torino, Milano, Venezia, Genova, Bologna, Parma, Roma, Napoli, Palermo. The training course in 19th was mostly based on the lectures of Phaleography, Diplomatics. There were not the education about archival science yet. Toward the end of 19th and 20th, people stressed the most basic subject in the training course of National Archive was not Phaleography and Diplomatics but archival science. The goal of archival science is to study the institution and organisation transferring archives and documents to Archive. And also it help archivists not wander about with ignorance of organisational and original procedures and divisions but know exactly theirs works. Like this, the studies on institution and organisation have got in the saddle as a branch of archival science since a few ten years. While archival science didn't evoke sympathy among people and experienced the tedious and difficult path in italy and other countries, Archive was managed by experts of other branches. As a result, there were a lot of faults in Archival Science. Specializing training course for Italian archivists came into being under the backdrop of Social Science Institute of Roma National University in 1925. The archival course of universities accomplished by the studies of history, law and economy. And such as Eugenio Casanova and Giorgio Cencetti were devoted archival science was abled to settle down in national archive. The training course for experts of 'archival science, 'Phaleography and Diplomatics' in National Archive of Bologna(Archivio di Stato di Bologna) is one of courses conducted in 17 National Archives in italy. This course is gratuitous and made up of 8 subjects(Archivistica, Paleografia, Diplomatica, Storia dell' Archivio, Notariato e documenti privati, istituzione medievale, istituzione moderna, istituzione contemporanea) students have to complete for two years. Students can receive the degree through passing twice written exam and once oral test. After department of Culture and education finally puts the marks of students, the chief Nationa Archive of Bologna confer the degree of 'archival science Phaleography and Diplomatics' on students passing the exams. This degree authenticates trainees' qualification which enables him to work at the archive in province, district and administrative capital city and archive of comunity and so on. Italian training course naturally leads archivists to keep in contact with valuable cultural inheritance through training in Archive. And it shows the intention to strengthen the affinity with each documents in the spot of archival management before training archivists. Also this is appraised as one of positive policies to conserve the local cultual inheritante in connection with the original qualitity of national archive with testify the history of each region. Traning course for archivist in Italy shows us the way how we have to prepare and proceed it. First, from producing documents to conserving than forever there has introduced 'original order that is to say a general rule to respect the first order given at the time producing documents'. Management of administrative documents is related consistently with one of historical documents. Second, the traning course for archivist is managing around 17 national archives. because italian national archive lay stress not or rducation of theory bus on train for archivest working in the first time of archival science. Third, diplomatics and phaleography for studies about historical document support archives. Forth, the studies on history id proceeding by cooperation between archivist and historian around archive. How our duties is non continuinf disputer who has to conserve and manage document and archives, but traing experts who having ability, vision and flexible thought, responsibility about archivals.