• Tuberculosis and Respiratory Diseases
• /
• v.45 no.2
• /
• pp.290-300
• /
• 1998

Background: CYFRA 21-1 is a tumor marker which measures a fragment of cytokeratin 19 expressed by epithelial cells in bronchus. It is known that cytokeratin 19 is abundant in squamous epithelial cell cancer of the lung. However, if the incidence of elevated serum CYFRA 21-1 level in patients with benign lung diseases or pulmonary tuberculosis with severe parenchymal damage is high the specificity of CYFRA 21-1 could be decreased. The purpose of this study is to investigate the changes of serum CYFRA 21-1 according to the degree of parenchymal damage and the usefulness of CYFRA 21-1 for diagnosing possibly combined lung cancer in patients with pulmonary tuberculosis. Method: We studied the changes of serum CYFRA 21-1 according to the sputum AFB stain, radiologic manifestation and history of treatment in 81 patients with pulmonary tuberculosis, and 20 healthy persons, 25 patients with lung cancer, as a control group. CYFRA 21-1 concentration in serum was quantified by the immunoradiometry assay(Centocor$^{(R)}$). Result: The results were as follow; Serum CYFRA 21-1 level was significantly lower in patients with pulmonary tuberculosis($1.54{\pm}1.19ng/mL$, p<0.01) as compared to patients with lung cancer($12.25{\pm}15.97ng/mL$), and was slightly higher than the level in heathy persons($0.90{\pm}0.49ng/mL$) but there was no significant difference. Serum CYFRA 21-1 level was below the cut-off value of 3.3ng/mL in 95 percent of patients with pulmonary tuberculosis but it was above the cut-off value in 64 percent of patients with lung cancer. Serum CYFRA 21-1 level was significantly higher in the initial treatment group($1.91{\pm}1.55ng/mL$, p<0.05) as compared to the treatment. failure group ($0.92{\pm}0.30ng/mL$). According to the sputum AFB smear, serum CYFRA 21-1 level in patients with negative result was slightly higher than the level in patients with positive result but there was no significant difference. According to the radiologic manifestation, serum CYFRA 21-1 level was significantly higher in patients with infiltrative lesion ($2.15{\pm}1.63ng/mL$, p<0.01) as compared to patients with destructive lesion ($l.04{\pm}0.54ng/mL$). As the size of cavity or destructive lesion was larger, the level was significantly lower(p<0.05). Conclusion: As serum CYFRA 21-1 level was significantly higher in the initial treatment group and patients with infiltrative lesion, it suppose to be closely related with the degree of parenchymal damage of the lung of the pulmonary tuberculosis. However CYFRA 21-1 could be useful method for diagnosing lung cancer even in patients with pulmonary tuberculosis combined with lung cancer because of the fact that it was below the cutoff value of 3.3ng/mL in 95 percent of patients with pulmonary tuberculosis.

• The Journal of Korean Academy of Prosthodontics
• /
• v.47 no.2
• /
• pp.156-163
• /
• 2009

Statement of problem: Recently, there have been increased esthetic needs for posterior dental restorations. The failure of posterior dental ceramic restoration are possible not only by the characters of the component materials but also by the type of food. Purpose: The research aim was to compare the in vitro fracture resistance of simulated first molar crowns fabricated using 4 dental ceramic systems, full-porcelain-occlusal-surfaced PFG, half-porcelain-occlusal-surfaced PFG, Empress 2, Ice Zirkon and selected Korean foods. Material and methods: Eighty axisymmetric crowns of each system were fabricated to fit a preparation with 1.5- to 2.0-mm occlusal reduction. The center of the occlusal surface on each of 15 specimens per ceramic system was axially loaded to fracture in a Instron 4465, and the maximum load(N) was recorded. Afterwards, selected Korean foods specimens(boiled crab, boiled chicken with bone, boiled beef rib, dried squid, dried anchovy, round candy, walnut shell) were prepared. 15 specimens per each food were placed under the Instron and the maximum fracture loads for them were recorded. The 95% confidence intervals of the characteristic failure load were compared between dental ceramic systems and Korean foods. Afterwards, on the basis of previous results, 14Hz cyclic load was applied on the 4 systems of dental ceramic restorations in MTS. The reults were analyzed by analysis of variance and Post Hoc tests. Results: 95% confidence intervals for mean of fracture load 1. full porcelain occlusal surfaced PFG Crown: 2599.3 to 2809.1 N 2. half porcelain occlusal surfaced PFG Crown: 3689.4 to 3819.8 N 3. Ice Zirkon Crown: 1501.2 to 1867.9 N 4. Empress 2 Crown: 803.2 to 1188.5 N 5. boiled crab: 294.1 to 367.9 N 6. boiled chicken with bone: 357.1 to 408.6 N 7. boiled beef rib: 4077.7 to 4356.0 N 8. dried squid: 147.5 to 190.5 N 9. dried anchovy: 35.6 to 46.5 N 10. round candy: 1900.5 to 2615.8 N 11. walnut shell: 85.7 to 373.1 N under cyclic load(14Hz) in MTS, fracture load and masticatory cycles are: 1. full porcelain occlusal surfaced PFG Crown fractured at 95% confidence intervals of 4796.8-9321.2 cycles under 2224.8 N(round candy)load, no fracture under smaller loads. 2. half porcelain occlusal surfaced PFG Crown fractured at 95% confidence intervals of 881705.1-1143565.7 cycles under 2224.8 N(round candy). no fracture under smaller loads. 3. Ice Zirkon Crown fractured at 95% confidence intervlas of 979993.0-1145773.4 cycles under 382.9 N(boiled chicken with bone). no fracture under smaller loads. 4. Empress 2 Crown fractured at 95% confidence intervals of 564.1-954.7 cycles under 382.9 N(boiled chicken with bone). no fracture under smaller loads. Conclusion: There was a significant difference in fracture resistance between experimental groups. Under single load, Korean foods than can cause fracture to the dental ceramic restorations are boiled beef rib and round candy. Even if there is no fracture under single load, cyclic dynamic load can fracture dental posterior ceramic crowns. Experimental data with 14 Hz dynamic cyclic load are obtained as follows. 1. PFG crown(full porcelain occlusion) was failed after mean 0.03 years under fracture load for round candy(2224.8 N). 2. PFG crown(half porcelain occlusion) was failed after mean 4.1 years under fracture load for round candy(2224.8 N). 3. Ice Zirkon crown was failed after mean 4.3 years under fracture load for boiled chicken with bone(382.9 N). 4. Empress 2 crown was failed after mean 0.003 years under fracture load for boiled chicken with bone(382.9 N).

• Journal of the Korean Geographical Society
• /
• v.29 no.2
• /
• pp.166-182
• /
• 1994

Kyonggi Province in the late Chosun dynasty was a center of superior government offices including 'Han' River water-road transportation and was located in the middle of an 'X'-shaped arterial road network. Because of these reasons, Kyonggi Province had a faster inflow of commodities, informations and technics compared with the other province. At this period of time, every local 'Eup' (name of administrative district) had not been affected by their above administrative districts and had their own autonomy. For this reason, every 'Eup' could be developed as a town, even if its size was small when it had sufficient internal growing conditions. Moreover, the markets ('Si-Jon') in big towns and periodical markets which were spread over the Kyonggi Province played role of commercial functions of town. And because military bases for the defence of the royal capital in Kyonggi Province also took parts of a non-agricultural city role, Xyonggi Provinc had much more possibilities of growing as a town rather than the other provinces. The towns of the late Chosun Dynasty were, except the capital and superior administrative districts which were governed by the 'You-Su', small towns which had only about 3, 000-5, 000 people. Most of the town dewellers were local officials, nobles, merchants, craftmen and slaves. And the farmers who lived near town became a pseudo-towner through suburb agriculture. Among these people, the merchants were leaders of townization. The downtowns were affected by the landform and traffic roads. The most fundamental function of towns were administrative. The opcial's grade, which was dispatched to the local administrative district ('Kun' or 'Hyun'), was decided by the size of population and agricultural land of each county. Large county which was governed by a high ranking opcial had more possibilities to develop as a large town. Because they supervised other opcials of lower rank and obtained more land and population for the town. The phonomena of farm abandonment after the Japanese Invasion of Korea in 1592-1598 stimulated the development of towns for commercial function. The commercial functions of towns were evident in the Si-Jon or Nan-Jon (names of markets) in the big cities such as Hansung and Kaesung, meanffwhile in the local areas it was emerged in the shape of periodical market networks as allied with near markets (which were called as Jang-Si) or permanent markets which were grown up from periodical markets. These facts of commercial development induced the birth of commercial town. Kyonggi Province showed the weak points of its defense system during both wars (Japanese Invasion in 1592 and Manchu's Invasion in 1636). The government reinforced its defense system by adding 4 'You-Su-Bus' and several military bases. Each local districts ('Eup'), where Geo-Jins were established, were stimulated to be a town while Jin-Kwan system were, adjusted and enforced. Among Dok-Jins(name of solitary military bases), Youngjongjin was grown up as a large garrison town which only played a role of defense. The number of towns that took roles of non-agricultural functions in Kyonggi Province was 52. Among these towns, 29 were developed as big towns which had above 3, 000 people and most of these towns were located on the northwest-southeast axes of 'X'-shaped arterial trafic network in the Chosn Dynasty, This fact points out that the traffic road is one of the important causes of the development of towns. When we make hierarchy of the towns of Kyonggi Province according to its population and how many functions it had, we can make it as 6 grades. The virst grade town 'Hansung' was the biggest central town of administration, commerce and defdnse. The 2nd grade town includes 'Kaesung' which had historical inertia that it had been the capital of the Koryo Dynesty. The 3rd grade towns include some 'You- Su-Bus' such as Soowon, Kanghwa, Kwangju and also include Mapo, Yongsan and from this we can imagine that the commercial development in the late Chosun Dynasty extremely affected the townization. The 4th-6th grade towns had smiliar population but it can be discriminated by how many town functions it had. So the 4th grade towns were the core of administration, commerce and defense function. 5th grade towns had administrative functions and one of commercial and defense functions. 6th grade towns had only one of these functions. When we research and town conditions of each grades as the ratio of non-agricultural population, we can find out that the towns from the 1st grade to 4th grade show difference by degree of townization but from the 4th grade to 6th grade towns do not show big difference in general.

• Journal of Chest Surgery
• /
• v.40 no.1 s.270
• /
• pp.37-44
• /
• 2007

Background: It is known that long-term survival rate in patients underwent bronchial sleeve lobectomy for primary lung cancer is at least equal to that in patients underwent pneumonectomy, and bronchial sleeve lobectomy is performed in patients with suitable tumor location even in patients have adequate pulmonary function. Sleeve pneumonectomy is performed when carina was invaded by tumor or tumor location was near to the carina. We performed this study to know our results of sleeve resection for primary lung cancer. Material and Method: We analyzed retrospectively the medical records of 45 patients who underwent sleeve lobectomy or sleeve pneumonectomy for primary lung cancer by one thoracic surgeon from May 1990 to July 2003 in Department of Thoracic & Cardiovascular Surgery, College of Medicine, Kyung Hee University. Follow-up loss was absent and last follow-up was performed in April 5, 2005. Kaplan-Meyer method and log-lank test were used to know long-term survival rate and p-value. Result: Mean age was 60 years old and male to female ratio 41:1. Histologic types were squamous cell carcinoma were 39, adenocarcinoma were 4, and others were 2 patients. Pathologic stages were I 14, II 14, and III 17 patients. Nodal stages were N0 23, N1 13, and N2 9 patients. Types of operation were sleeve lobectomy 40 and sleeve pneumonectomy 5 patients. Operative mortality was 3 patients and its cause was respiratory complications. Early complications were pneumonia 4, atelectasis 8, air leakage more than 7 days 6, and atrial fibrillation 4 patients. In 19 patients tumor was recurred. Local recurrence was 10 and systemic metastasis was 9 patients. Overall 5, 10-year survival rate were 54.2%, 42.5%. The 5, 10-year survival rates according to the pathologic stage were 83.9%, 67.1% in stage I, 55%, 47.1% in II, 33.3%, 25% in III, and significance difference was present between stage I and III. The 5, 10-year survival rate according to the lymph node involvement were 63.9%, 54.6% in N0, 53,8%, 46.5% in N1, 28.5%, 14.2% in N2, and significance difference was present between N0 and N2. Conclusion: Because bronchial sleeve lobectomy for primary lung cancer could be performed safely and shows acceptable long-term survival rate, it could be considered primary in case of suitable tumor location if complete resection is possible. Although sleeve pneumonectomy for primary lung cancer shows somewhat high operative mortality rate, it could be considered in view of curative treatment.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.10 no.3
• /
• pp.154-163
• /
• 2005

Irregular discharges of freshwater through the water gates of the Keum River Estuarine Weir, Korea, whose construction had been completed in 1998 with its water gates being operated as late as August 1994, drastically modified the estuarine environment. Sharp decrease of salinity along with the altered concentrations of inorganic nutrients are accompanied with the irregular discharges of freshwater into the estuary under the influence of regular semi-diurnal tidal effect. Field sampling was carried out on the time of high tide at 2 fixed stations(St.1 near the Estuarine Weir and St.2 off Kunsan Ferry Station) every other day for 4 months from mid-February 2004 to investigate into the semi-weekly variation of spring phytoplankton community in relation to the freshwater discharges from Keum River Estuarine Weir. CV(coefficient of variation) of salinity measurements was roughly 2 times greater in St.1 than that in St.2, reflecting extreme salinity variation in St.1 Among inorganic nutrients, concentrations of N-nutrients($NO_3^-,\;NO_2^-$ and $NH_4^+$) were clearly higher in St.1, to imply the more drastic changes of the nutrient concentrations in St.1. than St.2 following the freshwater discharges. As a component of phytoplankton community, diatoms were among the top dominants in terms of species richness as well as biomass. Solitary centric diatom, Cyclotella meneghiniana, and chain-forming centric diatom, Skeletonema costatum, dominated over the phytoplankton community in order for S-6 weeks each (Succession Interval I and II), and the latter succeeded to the former from the time of <$10^{\circ}C$ of water temperature. Cyanobacterial species, Aphanizomenon Posaquae and Phormidium sp., which might be transported into the estuary along with the discharged freshwater, occupied high portion of total biomass during Succession Interval III(mid-April to late-May). During this period, freshwater species exclusively dominated over the phytoplankton community except the low concentrations of the co-occurring 2 estuarine diatoms, Cyclotella meneghiniana and Skeletonema costatum. During the 4th Succession Interval when the water temperature was over $18^{\circ}C$, the diatom, Guinardia delicatula, was predominant for a week with the highest dominance of $75\%$ in discrete samples. To summarize, during all the Succession Intervals other than Succession Interval III characterized by the extreme variation of salinity under cooler water temperature than $18^{\circ}C$, the diatoms were the most important dominants for species succession in spring. If the scale and frequency of the freshwater discharge could have been adjusted properly even during the Succession Interval III, the dominant species would quite possibly be replaced by other estuarine diatom species rather than the two freshwater cyanobacteria, Aphanizomenon flosaquae and Phormidium sp.. The scheme of field sampling every other day for the present study was concluded to be the minimal requirement in order to adequately explore the phytoplankton succession in such estuarine environment as in Keum River Estuary: which is stressed by the unpredictable and unavoidable discharges of freshwater under the regular semi-diurnal tide.

• Journal of Hospice and Palliative Care
• /
• v.6 no.1
• /
• pp.51-57
• /
• 2003

Purpose : Anorexia-cachexia syndrome is one of the most common symptoms and main cause of death in terminal cancer patients. This symptom is due to the enlarged cancer mass as well as tumor released cytokines. Some doctors have suggested that vitamin C was preferentially toxic to tumor cells in vitro and in vivo, and improved clinical symptoms in terminal cancer patients. Therefore, we measured cytokines in serum of terminal cancer patients to determine whether vitamin C treatment improved the anorexia-cachexia syndrome. Methods : We investigated that 49 terminal cancer patients admitted to the department of family medicine, National Health Insurance Corporation Ilsan hospital from March 1, 2002 to August 31, 2002. The study was done on 22 patients who were given 10 g/day of vitamin C infusions during 1 week and 27 patients who were not infused. We measured the cytokines levels ($IL-1{\beta}$, IL-6, and $TNF-{\alpha}$) before and after 1 week between terminal cancer patients treated vitamin C and without vitamin C. Results : Out of 49 patients, patents treated with vitamin C infusions were 22 (12 male, 10 female), and these without vitamin C were 27 (18 male, 9 female). In patients treated with vitamin C, $IL-1{\beta}\;were\;6.19{\pm}5.17$ before day and $8.76{\pm}5.72$ after 1 week, IL-6 were $3.07{\pm}8.09$ before day and $1.31{\pm}2.36$ after 1 week, and $TNF-{\alpha}\;were\;2.74{\pm}14.24$ before day and $0.50{\pm}2.00$ after 1 week. In patients treated without vitamin C, $IL-1{\beta}\;were\;2.50{\pm}3.58$ before day and $6.49{\pm}12.01$ after 1 week, IL-6 were $1.00{\pm}2.19$ before day and $17.16{\pm}81.55$ after 1 week, and $TNF-{\alpha}\;were\;1.19{\pm}2.98$ before day and $1.27{\pm}1.52$ after 1 week. The level of cytokines in patients treated with vitamin C decreased more than those without vitamin C. However, this represented no statistical value (P=0.0598 in $IL-1{\beta}$, P=0.1664 in IL-6, and P=0.5395 in $TNF-{\alpha}$). Conclusion : In terminal cancer, even if there was no statistical difference in the cytokines levels between patients treated with vitamin C and those not treated, those who were treated had a decrease all cytokines levels. Vitamin C is very safe with almost no side effects. Therefore, vitamin C treatment in terminal cancer patients can be seen as beneficial and helpful for clinical symptoms.

• The Korean Society of Law and Medicine
• /
• v.21 no.2
• /
• pp.105-162
• /
• 2020

In the pandemic of infectious disease, restrictions of individual liberty have been justified in the name of public health and public interest. In March 2020, the National Assembly of the Republic of Korea passed the revised bill of the 「Infectious Disease Control and Prevention Act.」 The revised bill newly established the legal basis for forced testing and disclosure of the information of confirmed cases, and also raised the penalties for violation of self-isolation and treatment refusal. This paper examines whether and how these individual liberty limiting clauses be justified, and if so on what ethical and philosophical grounds. The authors propose the theories of the philosophy of law related to the justifiability of liberty-limiting measures by the state and conceptualized the dual-aspect of applying the liberty-limiting principle to the infected patient. In COVID-19 pandemic crisis, the infected person became the 'Patient as Victim and Vector (PVV)' that posits itself on the overlapping area of 'harm to self' and 'harm to others.' In order to apply the liberty-limiting principle proposed by Joel Feinberg to a pandemic with uncertainties, it is necessary to extend the harm principle from 'harm' to 'risk'. Under the crisis with many uncertainties like COVID-19 pandemic, this shift from 'harm' to 'risk' justifies the state's preemptive limitation on individual liberty based on the precautionary principle. This, at the same time, raises concerns of overcriminalization, i.e., too much limitation of individual liberty without sufficient grounds. In this article, we aim to propose principles regarding how to balance between the precautionary principle for preemptive restrictions of liberty and the concerns of overcriminalization. Public health crisis such as the COVID-19 pandemic requires a population approach where the 'population' rather than an 'individual' works as a unit of analysis. We propose the second expansion of the harm principle to be applied to 'population' in order to deal with the public interest and public health. The new concept 'risk to population,' derived from the two arguments stated above, should be introduced to explain the public health crisis like COVID-19 pandemic. We theorize 'the extended harm principle' to include the 'risk to population' as a third liberty-limiting principle following 'harm to others' and 'harm to self.' Lastly, we examine whether the restriction of liberty of the revised 「Infectious Disease Control and Prevention Act」 can be justified under the extended harm principle. First, we conclude that forced isolation of the infected patient could be justified in a pandemic situation by satisfying the 'risk to the population.' Secondly, the forced examination of COVID-19 does not violate the extended harm principle either, based on the high infectivity of asymptomatic infected people to others. Thirdly, however, the provision of forced treatment can not be justified, not only under the traditional harm principle but also under the extended harm principle. Therefore it is necessary to include additional clauses in the provision in order to justify the punishment of treatment refusal even in a pandemic.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.141-166
• /
• 2019

Recently, channels like social media and SNS create enormous amount of data. In all kinds of data, portions of unstructured data which represented as text data has increased geometrically. But there are some difficulties to check all text data, so it is important to access those data rapidly and grasp key points of text. Due to needs of efficient understanding, many studies about text summarization for handling and using tremendous amounts of text data have been proposed. Especially, a lot of summarization methods using machine learning and artificial intelligence algorithms have been proposed lately to generate summary objectively and effectively which called "automatic summarization". However almost text summarization methods proposed up to date construct summary focused on frequency of contents in original documents. Those summaries have a limitation for contain small-weight subjects that mentioned less in original text. If summaries include contents with only major subject, bias occurs and it causes loss of information so that it is hard to ascertain every subject documents have. To avoid those bias, it is possible to summarize in point of balance between topics document have so all subject in document can be ascertained, but still unbalance of distribution between those subjects remains. To retain balance of subjects in summary, it is necessary to consider proportion of every subject documents originally have and also allocate the portion of subjects equally so that even sentences of minor subjects can be included in summary sufficiently. In this study, we propose "subject-balanced" text summarization method that procure balance between all subjects and minimize omission of low-frequency subjects. For subject-balanced summary, we use two concept of summary evaluation metrics "completeness" and "succinctness". Completeness is the feature that summary should include contents of original documents fully and succinctness means summary has minimum duplication with contents in itself. Proposed method has 3-phases for summarization. First phase is constructing subject term dictionaries. Topic modeling is used for calculating topic-term weight which indicates degrees that each terms are related to each topic. From derived weight, it is possible to figure out highly related terms for every topic and subjects of documents can be found from various topic composed similar meaning terms. And then, few terms are selected which represent subject well. In this method, it is called "seed terms". However, those terms are too small to explain each subject enough, so sufficient similar terms with seed terms are needed for well-constructed subject dictionary. Word2Vec is used for word expansion, finds similar terms with seed terms. Word vectors are created after Word2Vec modeling, and from those vectors, similarity between all terms can be derived by using cosine-similarity. Higher cosine similarity between two terms calculated, higher relationship between two terms defined. So terms that have high similarity values with seed terms for each subjects are selected and filtering those expanded terms subject dictionary is finally constructed. Next phase is allocating subjects to every sentences which original documents have. To grasp contents of all sentences first, frequency analysis is conducted with specific terms that subject dictionaries compose. TF-IDF weight of each subjects are calculated after frequency analysis, and it is possible to figure out how much sentences are explaining about each subjects. However, TF-IDF weight has limitation that the weight can be increased infinitely, so by normalizing TF-IDF weights for every subject sentences have, all values are changed to 0 to 1 values. Then allocating subject for every sentences with maximum TF-IDF weight between all subjects, sentence group are constructed for each subjects finally. Last phase is summary generation parts. Sen2Vec is used to figure out similarity between subject-sentences, and similarity matrix can be formed. By repetitive sentences selecting, it is possible to generate summary that include contents of original documents fully and minimize duplication in summary itself. For evaluation of proposed method, 50,000 reviews of TripAdvisor are used for constructing subject dictionaries and 23,087 reviews are used for generating summary. Also comparison between proposed method summary and frequency-based summary is performed and as a result, it is verified that summary from proposed method can retain balance of all subject more which documents originally have.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Trans-
• /
• v.12
• /
• pp.51-79
• /
• 2022

This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photos within the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency of daytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not been used in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting values of color distribution and frequency from this study would serve as references for color planning of digital design regarding natural scenery in the geographic scope of Korea. Also, the two experiments are meaningful attempts for searching the methods for deriving colors that can be a useful reference among numerous images for content creator users of the relevant field.