• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Journal of Korean Orthopaedic Sports Medicine
• /
• v.9 no.1
• /
• pp.48-57
• /
• 2010

Purpose: To compare the incidence and risk factors for osteoarthritis after anterior cruciate ligament (ACL) reconstruction between two groups using bone-patellar tendon-bone (BPTB) and hamstring tendon (HT) autograft. Materials and Methods: 53 cases of ACL reconstruction using patellar tendon and 40 cases using hamstring tendon were followed up at least 8 years. Radiographic evaluation was done according to the Kellgren and Lawrence's classification. Clinical functional testing (Lysholm Knee Scores, the Tegner activity scores) and laxity testing (Lachman, pivot shift tests), and the instrumented laxity testing with $Telos^{(R)}$ were all examined in relation to the development of osteoarthritis. Results: Radiographic osteoarthritic changes were detected in 24 patients (45.3%) in BPTB group and 14 patients (35.0%) in HT group. Accompanying meniscal injury (BPTB p<0.001; HT p=0.091), intervals from the injury to reconstruction of > 12 months (BPTB p=0.037; HT p=0.021), and patient's age at reconstruction of > 25 years (BPTB p=0.003; HT p=0.048) were found to be significant independent predictors of osteoarthritis. However, no statistically significant correlations were found between the development of osteoarthritis and the clinical outcome or the radiographic stability in both groups. Conclusion: Although ACL reconstruction using BPTB or HT autograft had good clinical results at an average follow-up of 10 years, considerable incidence of radiographic osteoarthritic changes were noted. Various factors such as accompanying meniscal injury, protracted time from injury to reconstruction, more than 25 years old at the time of reconstruction were related to radiographic osteoarthritic changes.

• Journal of Nutrition and Health
• /
• v.50 no.4
• /
• pp.391-401
• /
• 2017

Purpose: The purpose of this study was to estimate the dietary flavonoid intakes of Korean adults according to socioeconomic status. Methods: Using data from the 2007~2012 Korea National Health and Nutrition Examination Survey, a total of 31,112 subjects aged over 19 years were included in this study. We estimated individuals' daily intakes of total flavonoids and seven flavonoid subclasses, including flavonols, flavones, flavanones, flavan-3-ols, anthocyanins, proanthocyanidin, and isoflavones,by linking food consumption data with the flavonoids database for commonly consumed Korean foods. We compared intakes of flavonoids according to the levels of household income and education. Results: Average dietary flavonoid intakes of the study subjects were 321.8 mg/d in men and 308.3 mg/d in women. Daily flavonoid intakes were positively associated with household income level (p < 0.0001) and education level (p < 0.0001). The subjects in the highest household income and highest education level group (OR 0.37, 95% CI 0.30~0.45, p < 0.0001 in men, OR 0.50, 95% CI 0.41~0.60, p < 0.0001 in women) had a lower likelihood of having low total flavonoid intake (less than 25 percentile) compared to the lowest household income and lowest education level group. The food group that contributed to total flavonoid intake with the biggest difference between the lowest and highest groups for both household income level and education level was beverages. Conclusion: This study shows that socioeconomic status was positively associated with flavonoid intake in a representative Korean population. Further research is needed to analyze the association of flavonoid intake with health outcomes according to socioeconomic status such as household income and education level.

• Pediatric Infection and Vaccine
• /
• v.12 no.1
• /
• pp.67-74
• /
• 2005

Purpose : The incidence of mortality associated with respiratory difficulties is decreasing nowadays contributed to the development of neonatology. However, complications associated with mechanical ventilator are increasing. This study is to determine clinical manifestations, diagnositc availability of the endotracheal tip culture in patients with Ventilator-Associated Pneumonia(VAP) in neonatal intensive care unit(NICU). Methods : A retrospective analysis of 50 neonates who were admitted to the NICU of Kangnam Sacred Heart Hospital and had given mechanical ventilator from 1 January 2000 to 30 June 2003. VAP group defined as neonates who had pneumonia with mechanical ventilation longer than 48 hours. They were classified into VAP group(n=13) and control group (n=37) and the prevalence, microorganisms cultured from the endotracheal tube tip and risk factors were investigated. Results : The prevalence of VAP was 26.0%(n=13) and the most dominant microorganism cultured in our NICU was methicillin-resistant coagulase negative staphylococcus(MR-CNS) in 4 cases. Other microorganisms were Pseudomonas, Enterobacter, methicillin-resistant Staphylococcus aureus(MRSA) and Klebsiella. Gestational age, birth weight, Apgar score, respiratory distress syndrome, retinopathy of prematurity, bronchopulmonary dysplasia, sepsis, renal failure, pulmonary hemorrhage, pneumothorax were not different significantly between two groups except intraventricular hemorrhage(P<0.001) and patent ductus arteriosus(P<0.05). Duration of hospital stay and mortality rate were also not different significantly. Conclusion : VAP occurred at a significant rate among mechanically ventilated NICU patients. Despite of limitation of encotracheal tip culture, the most common microorganism was MR-CNS. We should be aware of occurrence of VAP in NICU neonate who were with mechanical ventilator and should treat with great care.

• Archives of design research
• /
• v.19 no.2 s.64
• /
• pp.53-62
• /
• 2006

E-mail has indeed developed from 'a means of instant communication' to an indispensable part of online marketing. Therefore, companies need to implement consistent customer management. Communication with customers and marketing through e-mail is a powerful way of communication and adapting one-to-one marketing strategies to customer trends, habits and taste preferences. Since setting accurate targets is especially important in the fashion industry, e-mail marketing is the most effective way to communicate with customers and one-to-one marketing constitutes a very important strategy. In this study, I will analyze this powerful one-on-one marketing tool, particularly actual e-mail messages sent by an Internet Shopping Mall from June 12 to July 30, 2005, examine the effect of these messages on sales growth and analyze actual feedback received. Regarding e-mail read rates broken down by age and gender, 1 found that females in their late twenties recorded the highest rate at 21.66% and their contribution to sales growth was recorded at 3.5% From actual sales records, found that 28.10% of total sales were attributable to people in their late twenties, showing that the age group that reads e-mails the most also buys the most. Regarding feedback by e-mail title, e-mails from the 'Casual' category seemed to be the most effective, in that most of these e-mails were read. Also, messages sent on Tuesdays were read the most, according to the feedback analysis by weekday. Section e-mails were read more often than regular e-mails. Regarding the view rate according to the time e-mails were sent, messages sent to females in their late twenties at two o'clock in the afternoon were read by 20.93% of recipients, recording the highest read rate. By offering informative content and practical tips, visitors will be attracted to the site and generate site traffic. Therefore, we can conclude that sending e-mail messages can greatly contribute to sales growth and e-mail marketing is very effective. Also, in order to make e-mail campaigns more effective and improve marketing results, we need to analyze actual results and apply our findings in future e-mail campaigns. With this, we get successful marketing results.

• Journal of Chest Surgery
• /
• v.34 no.6
• /
• pp.477-484
• /
• 2001

Background: Initial symptoms for esophageal perforation have not been clarified, but when there is no early diagnosis and proper treatment to follow immediately after the diagnosis, it is fatal for the patients. Therefore, this study attempted to discover the factors that influence the prognosis of esophageal perforation to contribute to the improvement of the treatment result. Material and Method: The subjects of this study are 32 patients who came to the hospital with esophageal perforation from October, 1984 to June, 2000. This study examined the items for clinical observation such as patients' sex, age, cause of the perforation, perforation site, the time spent until the beginning of the treatment, symptoms caused by the perforation and its complication, and treatment methods. This study tried to find out the relationship between the survival of patients and each item. Result: There were 24 male and 8 female patients and their mean age was 49.7+16.4. For the causes of perforation, there were 14 cases(43%) of iatrogenic perforation, which ranked first, caused by the medical instrument operation and surgical damage. As for the perforation sites, thoracic esophagus was the most common site(26 cases of 81.2%) and chest pain was the most frequent symptom. The complication caused by esophageal perforation showed the highest cases in the order of mediastinitis, empyema, sepsis and peritonitis. After the treatment, there were 23 cases of survival and 9 cases of mortality. The total mortality rate was 28.1% and the main causes of mortality were sepsis and acute respiratory distress syndrome(ARDS). As for the treatment, 8 cases(25.0%) treated the perforation successfully using conservative treatment only. As for the surgical treatment, there were 5 cases(15.6%) of cervical drainage, 7 cases (21.8%) of primary repair and 12 cases(37.5%) of esophageal reconstruction after performing an exclusion-diversion. There were 18 cases(56.2%) of complete treatment of esophageal perforation at its initial treatment and in 14 cases(43.8%) of treatment failure at its initial treatment, patients were completely cured in the next treatment stage or died during the treatment. The cases of perforation in thoracic esophagus, complication into severe mediastinitis or sepsis and the cases of failure at initial treatment showed a statistically significant mortality rate (p<0.05).

• The Korean Journal of Food And Nutrition
• /
• v.23 no.1
• /
• pp.30-38
• /
• 2010

This study was conducted to determine the effects of vitamin C on the activity of liver function enzymes and electromicrographic changes in white rats treated with aflatoxin $B_1(AFB_1)$ or X-ray and $AFB_1$. Six week-old male Sprague-Dawley rats were randomly divided into five groups: a control group, $AFB_1$ treated group, $AFB_1$ treated group with vitamin C, X-ray and $AFB_1$ co-treated group, X-ray and $AFB_1$ co-treated group with vitamin C. On the first day of the experiment, only one dose of X-rays was exposed to the entire liver at 1,500 cGy. Next, vitamin C was injected at 10 mg/kg body weight by intraperitoneal injection, followed 1 hr later by the administration of 0.4 mg/kg of $AFB_1$ by intraperitoneal injection. These treatments were then administered every three days over a period of 15 days. On the 16th day of treatments, the animals were sacrificed. Analysis of the activity of the liver function enzymes, GOT, ALK phatase and LDH, in the sera of rats revealed that they were somewhat increased by $AFB_1$ treatment, X-ray and $AFB_1$ co-treatment when compared to the control group. Furthermore, the activity of these enzymes decreased in response to administration of vitamin C. Especially, the levels of GOT were remarkably decreased in the $AFB_1$ treated group treated with vitamin C when compared to the group treated with $AFB_1$ alone(p<0.001). Electromicrographic analysis revealed cloudy swelling, necrosis, vesicular degeneration and fat accumulation of hepatocytes in response to treatment with $AFB_1$ or co-treatment with X-ray and $AFB_1$. However, the destruction of hepatic cells was considerably lower in the vitamin C-treated group. These results indicate that vitamin C had ameliorating effects on the hepatic cell damage.

• Journal of Plant Biotechnology
• /
• v.42 no.1
• /
• pp.25-33
• /
• 2015

A PyrcpPR-10 gene with differentially expressed was isolated by using the suppression subtractive hybridization assay between '93-3-98' (highly resistant against scab caused by Venturia nashicola) and 'Sweat Skin'(highly susceptible) and analyzed the expression pattern according to organs and cultivars. The full length of PyrcpPR-10 was cloned as 743bp with 480bp's ORP, and was determined to encode a protein of 159 amino acid residues. On analyzing PyrcpPR-10 gene sequence compared with resistant and susceptible cultivars, 'Hwangsilri' (resistant), 'Gamcheonbae' (moderately resistant), 'Wonhwang' (moderately susceptible), 'Niitaka' (highly susceptible), and 'Sweat Skin' (highly susceptible) had identical gene sequence but 'Bartlett' (highly resistant) showed partly different sequences. The deduced amino acid sequence showed 64 ~ 98% homology and had the GXGGXG motif to known amino acid of other plants PR-10 by the BLAST X analysis. Among several organs or tissues, petal was showed highest expression level of PyrcpPR-10 gene followed by leaf, floral axis, bud, and bark. The expression level of PyrcpPR-10 gene was dramatically increased at 24 hr after inoculation in all cultivars and also up-regulated in accordance with resistant degree of cultivars. While resistant cultivars ('Bartlett', '93-3-98', and 'Hwangsilri') induced relatively high expression level of PyrcpPR-10 gene, susceptible cultivars ('Niitaka', and 'Sweat Skin') showed low expression level. PyrcpPR-10 gene is assumed that it is directly connected with defense mechanisms to pear scab.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.33 no.2
• /
• pp.67-77
• /
• 2015

The purpose of this paper is to draw historic valuable resources to conserve through the analysis about the preservation status of historic urban environment in Suwon Hwaseong Fortress. As for the conservation of urban environment, it is important to protect the resources showing historical continuity and to manage the resources remaining characteristics of place, the analysis of the preservation status is focused on the perspective of preservation of physical form and land use. This paper makes progress through three phases. First, in order to understand urban environment in Hwaseong Fortress overall, it compares land registration original map in 1911 to current map in 2014 by the four items of topography, water environment, streets and sites. Next, changes of four items in urban environment have been reviewed further by the research of maps, relative literatures, field survey and interview, and are classified according to the criteria of preservation-partially preservation-disappearance. After analysing preservation status, valuable urban historic cultural resources are drawn separately by being preserved continually and by being preserved partially but remaining characteristics of place. As a result, natural factors of topography and waterway and urban factor of streets are remained considerably preserved. And even if these factors are changed, the ground environment features support to understand historic urban context. Second, as preservation of topography, water environment, streets and sites are closely related to each other, integrated conservation frameworks are needed to enhance urban historic landscape. Third, modern historic resources in Hwaseong are remained unchanged and thus it is necessary to understand urban historic environment by the layers of various times besides Joseon Dynasty period. Fourth, historic sites and streets which had been preserved through urban development process are destroyed by recent historic cultural restoration policies, therefore urban historic resources worthy of conservation should be treated prudently.