• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.19-42
• /
• 2012

Consumer consumption patterns are shifting rapidly as buyers migrate from offline markets to e-commerce routes, such as shopping channels on TV and internet shopping malls. In the offline markets consumers go shopping, see the shopping items, and choose from them. Recently consumers tend towards buying at shopping sites free from time and place. However, as e-commerce markets continue to expand, customers are complaining that it is becoming a bigger hassle to shop online. In the online shopping, shoppers have very limited information on the products. The delivered products can be different from what they have wanted. This case results to purchase cancellation. Because these things happen frequently, they are likely to refer to the consumer reviews and companies should be concerned about consumer's voice. E-commerce is a very important marketing tool for suppliers. It can recommend products to customers and connect them directly with suppliers with just a click of a button. The recommender system is being studied in various ways. Some of the more prominent ones include recommendation based on best-seller and demographics, contents filtering, and collaborative filtering. However, these systems all share two weaknesses : they cannot recommend products to consumers on a personal level, and they cannot recommend products to new consumers with no buying history. To fix these problems, we can use the information which has been collected from the questionnaires about their demographics and preference ratings. But, consumers feel these questionnaires are a burden and are unlikely to provide correct information. This study investigates combining collaborative filtering with the centrality of social network analysis. This centrality measure provides the information to infer the preference of new consumers from the shopping history of existing and previous ones. While the past researches had focused on the existing consumers with similar shopping patterns, this study tried to improve the accuracy of recommendation with all shopping information, which included not only similar shopping patterns but also dissimilar ones. Data used in this study, Movie Lens' data, was made by Group Lens research Project Team at University of Minnesota to recommend movies with a collaborative filtering technique. This data was built from the questionnaires of 943 respondents which gave the information on the preference ratings on 1,684 movies. Total data of 100,000 was organized by time, with initial data of 50,000 being existing customers and the latter 50,000 being new customers. The proposed recommender system consists of three systems : [+] group recommender system, [-] group recommender system, and integrated recommender system. [+] group recommender system looks at customers with similar buying patterns as 'neighbors', whereas [-] group recommender system looks at customers with opposite buying patterns as 'contraries'. Integrated recommender system uses both of the aforementioned recommender systems to recommend movies that both recommender systems pick. The study of three systems allows us to find the most suitable recommender system that will optimize accuracy and customer satisfaction. Our analysis showed that integrated recommender system is the best solution among the three systems studied, followed by [-] group recommended system and [+] group recommender system. This result conforms to the intuition that the accuracy of recommendation can be improved using all the relevant information. We provided contour maps and graphs to easily compare the accuracy of each recommender system. Although we saw improvement on accuracy with the integrated recommender system, we must remember that this research is based on static data with no live customers. In other words, consumers did not see the movies actually recommended from the system. Also, this recommendation system may not work well with products other than movies. Thus, it is important to note that recommendation systems need particular calibration for specific product/customer types.

• Journal of Korean Neurosurgical Society
• /
• v.30 no.10
• /
• pp.1210-1219
• /
• 2001

Introduction : The purpose of this study was to analyze the safety, pullout strength and radiographic characteristics of unicortical and bicortical screws of cervical facet within cadaveric specimens and evaluate the influence of level of training on the positioning of these screws. Methods : Twenty-one cadavers, mean 78.9 years of age, underwent bilateral placement of 3.5mm AO lateral mass screw from C3-C6(n=168) using a slight variation of the Magerl technique. Intraoperative imaging was not used. The right side(unicortical) utilized only 14mm screws(effective length of 11mm) while on the left side to determine the length of the screw after the ventral cortex had been drilled. Three spine surgeons(attending, fellow, chief resident) with varying levels of spine training performed the procedure on seven cadavers each. All spines were harvested and lateral radiographs were taken. Individual cervical vertebrae were carefully dissected and then axial radiographs were taken. The screws were evaluated clinically and radiographically for their safety. Screws were graded clinically for their safety with respect to the spinal cord, facet joint, nerve root and vertebral artery. The grades consisted of the following categories : "satisfactory", "at risk" and "direct injury". Each screw was also graded according to its zone placement. Screw position was quantified by measuring a sagittal angle from the lateral radiograph and an axial angle from the axial radiograph. Pull-out force was determined for all screws using a material testing machine. Results : Dissection revealed that fifteen screws on the left side actually had only unicortical and not bicortical purchase as intended. The majority of screws(92.8%) were satisfactory in terms of safety. There were no injuries to the spinal cord. On the right side(unicortical), 98.9% of the screws were "satisfactory" and on the left side(bicortical) 68.1% were "satisfactory". There was a 5.8% incidence of direct arterial injury and a 17.4% incidence of direct nerve root injury with the bicortical screws. There were no "direct injuries" with the unicortical screws for the nerve root or vertebral artery. The unicortical screws had a 21.4% incidence of direct injury of the facet joint, while the bicortical screws had a 21.7% incidence. The majority of "direct injury" of bicortical screws were placed by the surgeon with the least experience. The performance of the resident surgeon was significantly different from the attending or fellow(p<0.05) in terms of safety of the nerve root and vertebral artery. The attending's performance was significantly better than the resident or fellow(p<0.05) in terms of safety of the facet joint. There was no relationship between the safety of a screw and its zone placement. The axial deviation angle measured $23.5{\pm}6.6$ degrees and $19.8{\pm}7.9$ degrees for the unicortical and bicortical screws, respectively. The resident surgeon had a significantly lower angle than the attending or fellow(p<0.05). The sagittal angle measured $66.3{\pm}7.0$ degrees and $62.3{\pm}7.9$ degrees for the unicortical and bicortical screws, respectively. The attending had a significantly lower sagittal angle than the fellow or resident(p<0.05). Thirty-three screws that entered the facet joint were tested for pull-out strength but excluded from the data because they were not lateral mass screws per-se and had deviated substantially from the intended final trajectory. The mean pull-out force for all screws was $542.9{\pm}296.6N$. There was no statistically significant difference between the pull-out force for unicortical($519.9{\pm}286.9N$) and bicortical($565.2{\pm}306N$) screws. There was no significant difference in pull-out strengths with respect to zone placement. Conclusion : It is our belief that the risk associated with bicortical purchase mandates formal spine training if it is to be done safely and accurately. Unicortical screws are safer regardless of level of training. It is apparent that 14mm lateral mass screws placed in a supero-lateral trajectory in the adult cervical spine provide an equivalent strength with a much lower risk of injury than the longer bicortical screws placed in a similar orientation.

• Radiation Oncology Journal
• /
• v.22 no.3
• /
• pp.192-199
• /
• 2004

Purpose: To determine the patterns on evaluation and treatment in the patient with early breast cancer treated with conservative surgery and radiotherapy and to improve the radiotherapy techiniques, nationwide survey was peformed. Materials and Methods: A web-based database system for korean Patterns of Care Study (PCS) for 6 common cancers was developed. Two hundreds sixty-one randomly selected records of eligible patients treated between 1998$\~$1999 from 15 hospitals were reviewed. Results: The patients ages ranged from 24 to 85 years(median 45 years). Infiltrating ductal carcinoma was most common histologic type (88.9$\%$) followed by medullary carcinoma (4.2$\%$) and infiltrating lobular carcinoma (1.5$\%$). Pathologic T stage by AJCC was T1 in 59.7$\%$ of the casses, T2 in 29.5$\%$ of the cases, Tis in 8.8$\%$ of the cases. Axillary lymph node dissection was peformed I\in 91.2$\%$ of the cases and 69.7$\%$ were node negative. AJCC stage was 0 in 8.8$\%$ of the cases, stage I in 44.9$\%$ of the cases, stage IIa in 33.3$\%$ of the cases, and stage IIb in 8.4$\%$ of the cases. Estrogen and progesteron receptors were evaluated in 71.6$\%$, and 70.9$\%$ of the patients, respectively. Surgical methods of breast-conserving surgery was excision/lumpectomy in 37.2$\%$, wide excision in 11.5$\%$, quadrantectomy in 23$\%$ and partial mastectomy in 27.5$\%$ of the cases. A pathologically confirmed negative margin was obtained in 90.8$\%$ of the cases. Pathological margin was involved with tumor in 10 patients and margin was close (less than 2 mm) in 10 patients. All the patients except one recieved more than 90$\%$ of the planned radiotherapy dose. Radiotherapy volume was breast only In 88$\%$ of the cases, breast+supraclavicular fossa (SCL) in 5$\%$ of the cases, and breast+ SCL+ posterior axillary boost in 4.2%$\%$of the cases. Only one patient received isolated internal mammary lymph node irradiation. Used radiation beam was Co-60 in 8 cases, 4 MV X-ray in 115 cases, 6 MV X-ray in 125 cases, and 10 MV X-ray in 11 cases. The radiation dose to the whole breast was 45$\~$59.4 Gy (median 50.4) and boost dose was 8$\~$20 Gy (median 10 Gy). The total radiation dose delivered was 50.4$\~$70.4 Gy (median 60.4 Gy). Conclusion: There was no major deviation from current standard in the patterns of evaluation and treatment for the patients with early breast cancer treated with breast conservation method. Some varieties were identified in boost irradiation dose. Separate analysis for the datails of radiotherapy planning will be followed and the outcome of treatment is needed to evaluate the process.

• The Journal of Dong Guk Oriental Medicine
• /
• v.2 no.1
• /
• pp.73-105
• /
• 1993

To say nothing of the orient and the west, the human beings discover the method of Jin Mac(診脈) by the way that observe disease. But oriental medicine devise special method of Jin Mac(診脈) in the study of Kyoung Mac(經脈). Although sip-ei Kyoung Mac Jin(十二經脈診), Sam Bu Gu Who Jin(三部九候診), In Young Mac Gu Jin(人迎脈口診), Chon Kwan Chuck Jin(寸關尺診) namely Yuk Bu Jung Wee Jin Mac (六部定位診脈) that is used today are devised, it has changed naturally by the changing treatment and the introduction of Yuin Yang(陰陽) and five element(五行). Many methods dg Jin Mac(診脈), it had not developped successing alternative, it had developped of declined by it's own way. 1. Results for the birth of Mac(脈) 1) Mac(脈), it means Kyoung Mac(經脈), at first entirelly Mac(脈), is seized a blood vessel that flows in the body. As presumed today, after finding many acupunture point, a general idea of Mac(脈) is not maked by the line that connect point and point, it connect between acupunture point and acupunture point. 2) Like blood flows in Hyul Mac(血脈), Gie(氣) flows in Kyoung Mac(經脈). The two things relate deeply each other. In a general idea or actrally Kyoung Rak(經洛), the two things sometimes accord, sometimes seperate, sometimes mix alternative. 3) Hyul Mac(血脈) and Kyoung Mac(經脈), we call it Mac(脈) entirely Kyoung Mac(經脈), is a way that manifest disease through Kyoung Mac(經脈) or a boundary that disease belongs to it method of Mac Jin(脈診) individual that disease of Kyoung Mac(經脈) is diagnosed by the jumping situation of Hyul Mac(血脈). 4) In method of Moxa, athough the pathology and the diagnostic of Mac(脈) are created by finding Mac(脈). Finding acupunture have opportunitty fot Mac Jin(脈診) and treatment. 2. Results of Kyoung Mac Mac Jin(經脈脈診) 1) In theory of kyoung Rak(經洛), disease are resumed for malfunction of Young Wee(榮衛) that flows in Kyung Rak(經洛). So to speak, in treatment of Kyoung Rak area, the purpose of diagnosis observe the situation of disease and cause. For fitting the purpose of diagnosis, the dead had esatablised four-diagnosis method mangMunMnnJeul(望聞問切), in four-diagnosis(四診法), the core is Mac Jin(脈診). 2) sip-ei Kyoung Mac Mac Jin(十二經脈診) had existed as Kyoung Mac Mac Jin(經脈脈診), it precedes Sam Bu Gu Who Jin(三部九候診). In Young Ki Gu Mac(人迎脈口診). 3) Although Bu Yang Mac(趺陽脈), So Um Mac(少陰脈) is a part of Sip-ei Kyoung Mac(十二經脈診), they developped especially because they located in the point of Won Hyul(原穴) and they are convenient for diagnose. 4) Sip-ei Kyoung Mac Mac Jin(十二經脈診), which belongs to Bu Yang Mac(趺陽脈) and So Urn Mac(少陰脈), is not important for the comming age medical books compared with Mac Kyoung(脈經). 3. Results gor Sam Bu Gu Who Jin(三部九候診) 1) Mac Jin(脈診) of Sam Bu Gu Who(三部九候), which is noted in the theory of Sam Bu Gu Who(三部九候診) of So Mun(素問), belongs to Kyoung Mac Mac Jin's(經脈脈診) geneology, Sip-ei Kyoung Mac Mac Jin(十二經脈診) is arranged, simplicated by the idealogy three talents(三才思想) in the heaven and the earth. 2) What Sam Bu Gu Jin(三部九候診) is regardded as very important in So Mun(素問), the editor of So Mun(素問) recognize the meaning that one discover disease early in this method of diagnosis. 3) After Young chu(靈樞), Nan Kyoung(難經) it is lacked the method of Sam Bu Gu Who Jin(三部九候診) in the books that treatment has changed. Sam Bu Gu Who Jin(三部九候診) based on actually clinic appropriate. 4. results for In Young Mac Gu Jin(人迎脈口診) 1) In Young Mac Gu Jin(人迎脈口診) is the method of comparative Mac Jin(脈診) according to the theory of Yin Yang(陰陽), it is presumed after Sam Bu Gu Who Jin(三部九候診), it had perished in parallel with the development of the theory of five elelment(五行). The development of the acupunture, the perishment of the treatment of negative(刺絡). 2) In Young Mac Gu Jin(人迎脈口診), Wang Suk Wha(王叔和) recreated that the left is In Young(人迎), the right is Kie Gu(氣口). In future generations by Jin Mu Taek(陳無擇) who is the writer of Sam In Bang(三因方). In Young Mac Gu Jin(人迎脈口診) is a measure for disease which classify it's inside and outside cause. 5. Results for Chon Gu Mac Jin(寸口脈診) 1) What we say Mac Jin(脈診) of Chon Gu(寸口) two means are used in commn. First case, we simply say the area of Chon Gu(寸口), second case, we say Chon Kwan Chuk Jin(寸口尺診) reducingly. Chon Gu(寸口) is the area which is the radial artery of wrist joint. What we attemp diagnose by only Chon Gu Mac(寸口脈), it is clearly shoued in the method of Nan Kyoung, five Nan(難經五難). 2) Because Jin Mac(診脈) is made in only Chon Gu(寸口), that is the area in which is concentated Kyoung Kee(經氣). That is the birth of Jin Kee(眞氣) and Jin Kee(眞氣) is related with disease. We can diagnose disease by taking Chon Gu(寸口). 3) Chuk Jin(尺診) in Nae Kyoung(難經) have two things. One is Il Chuk(一尺), the other is Chon Kwan Chu(寸關尺). 4) Chuk Chon Jin(尺寸診) is the method which diagnose the difference of point and the condition of Mac(脈) by dividing a part of Chuk(尺) in the area of Chon Gu(寸口). In Chon Gu Jin(寸口診), by introducing the theory of Yin Yang(陰陽), the method of Chon Gu Jin(寸口診) is developed by chon Gu Jin(寸口診). 5) What Chuk Kwan Chon Jin(寸關尺診) is that area of the Chon Gu(寸口) are divided fot three point, we can diagnose. By consulting Sam Bu Gu Who Jin(三部九候診), developping of the method of acupunture, utilzing the theory of five element(五行) it is devised by concentrating way of thinking of the method mac Jin(脈診) exiting. 6) Chon Kwan Chuk Jin MaC(寸關尺診脈) begin from Nae Kyoung(內徑) exiting. After Nan Kyoung(內徑), spread out widely from Mac Kyoung(脈診) of Wang Suk wha(王叔和), the future medicins followed it. Yang Hyun Jo(楊玄操) and established Chon Kwan Chuk Jin(寸關尺診) which is used widely today. This right and left Chon Kwan Chuk Jin(寸關尺診), we call it method of Yuk Bu Jung Wee Jin Mac(六部定位診脈). 7) We can think the base which presume the arrangement of the viscera for Chon Kwan Chuk(寸關尺) of the right and the left. 8) The origin, which seperate the right and the left of Mac(脈), is showed at the treory of Ji Jin Yo Dae(至眞要大論) in So Mun(素問) which Chon Chuk(寸尺) seperate the right and the left. But the method of diagnosis in Nan Kyoung(難經) have no seperation the fight and the left. Otherwise this. there is clearly writtened the seperation for the right origin of the method of Yuk Bu Jung Wee Jin Mac(六部定位診脈) seek for Cang Gong(倉公). 9) Yang Hyun Jo(楊玄操) notice that the Chuk(尺) is mentioned for Sam Cho(三焦) in the method of Mac Kyuong(脈經), Sim Po Kyung(心包經) which put together with Sam Cho(三焦) allot on this, he had established the method of Yuk Bu Jung Wee Jin Mac(六部定位診脈). 10) On the method of Paen Jak Yin Yang Mac(扁鵲陰陽脈) in Mac Kyoung(脈經), equal article exist with the theory of Pyung In Kee Sang(平人氣象論) in So Mun(素問). When Wang Suk Wha(王叔和) write Mac Kyung(脈經), we can presume that the book of Mac(脈) which Paen Jak(扁鵲) had experienced the origin have exited besides So Mun(素問), Young Chu(靈樞). If so he must be make Chon Kwan Chuk Jin(寸關尺診) very fairly standard. So Nae Kyoung(內經), which must be fllowed the method of Paen Jak Mac(扁鵲脈), do the method diagnosis of Chon Kwan Chuk(寸關尺), diagnise of disease and treat.