• Journal of Intelligence and Information Systems
• /
• 제24권1호
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of Intelligence and Information Systems
• /
• 제25권4호
• /
• pp.35-52
• /
• 2019

As public services are provided in various forms, including e-government, the level of public demand for public service quality is increasing. Although continuous measurement and improvement of the quality of public services is needed to improve the quality of public services, traditional surveys are costly and time-consuming and have limitations. Therefore, there is a need for an analytical technique that can measure the quality of public services quickly and accurately at any time based on the data generated from public services. In this study, we analyzed the quality of public services based on data using process mining techniques for civil licensing services in N city. It is because the N city's building license complaint service can secure data necessary for analysis and can be spread to other institutions through public service quality management. This study conducted process mining on a total of 3678 building license complaint services in N city for two years from January 2014, and identified process maps and departments with high frequency and long processing time. According to the analysis results, there was a case where a department was crowded or relatively few at a certain point in time. In addition, there was a reasonable doubt that the increase in the number of complaints would increase the time required to complete the complaints. According to the analysis results, the time required to complete the complaint was varied from the same day to a year and 146 days. The cumulative frequency of the top four departments of the Sewage Treatment Division, the Waterworks Division, the Urban Design Division, and the Green Growth Division exceeded 50% and the cumulative frequency of the top nine departments exceeded 70%. Higher departments were limited and there was a great deal of unbalanced load among departments. Most complaint services have a variety of different patterns of processes. Research shows that the number of 'complementary' decisions has the greatest impact on the length of a complaint. This is interpreted as a lengthy period until the completion of the entire complaint is required because the 'complement' decision requires a physical period in which the complainant supplements and submits the documents again. In order to solve these problems, it is possible to drastically reduce the overall processing time of the complaints by preparing thoroughly before the filing of the complaints or in the preparation of the complaints, or the 'complementary' decision of other complaints. By clarifying and disclosing the cause and solution of one of the important data in the system, it helps the complainant to prepare in advance and convinces that the documents prepared by the public information will be passed. The transparency of complaints can be sufficiently predictable. Documents prepared by pre-disclosed information are likely to be processed without problems, which not only shortens the processing period but also improves work efficiency by eliminating the need for renegotiation or multiple tasks from the point of view of the processor. The results of this study can be used to find departments with high burdens of civil complaints at certain points of time and to flexibly manage the workforce allocation between departments. In addition, as a result of analyzing the pattern of the departments participating in the consultation by the characteristics of the complaints, it is possible to use it for automation or recommendation when requesting the consultation department. In addition, by using various data generated during the complaint process and using machine learning techniques, the pattern of the complaint process can be found. It can be used for automation / intelligence of civil complaint processing by making this algorithm and applying it to the system. This study is expected to be used to suggest future public service quality improvement through process mining analysis on civil service.

• Journal of the East Asian Society of Dietary Life
• /
• 제21권5호
• /
• pp.731-738
• /
• 2011

Cholesterol is the precursor of various steroid hormones, bile acid, and vitamin D with functions related to regulation of membrane permeability and fluidity. However, the presence of excess blood cholesterol may lead to arteriosclerosis and hypertension. Moreover, dietary cholesterol may affect blood cholesterol levels. Generally, cholesterol determination is performed by spectrophotometric or chromatographic methods, but these methods are very time consuming and costly, and require complicated pretreatment. Thus, the development of a rapid and simple analysis method for measuring cholesterol concentration in food is needed. Multi-walled carbon nanotube (MWCNT) was functionalized to MWCNT-$NH_2$ via MWCNT-COOH to have high sensitivity to $H_2O_2$. The fabricated MWCNT-$NH_2$ was attached to a glassy carbon electrode (GCE), after which Prussian blue (PB) was coated onto MWCNT-$NH_2$/GCE. MWCNT-$NH_2$/PB/GCE was used as a working electrode. An Ag/AgCl electrode and Pt wire were used as a reference electrode and counter electrode, respectively. The sensitivity of the modified working electrode was determined based on the amount of current according to the concentration of $H_2O_2$. The response increased with an increase of $H_2O_2$ concentration in the range of 0.5~500 ${\mu}M$ ($r^2$=0.96) with a detection limit of 0.1 ${\mu}M$. Cholesterol oxidase was immobilized to aminopropyl glass beads, CNBr-activated sepharose, Na-alginate, and toyopearl beads. The immobilized enzyme reactors with aminopropyl glass beads and CNBr-activated sepharose showed linearity in the range of 1~100 ${\mu}M$ cholesterol. Na-alginate and toyopearl beads showed linearity in the range of 5~50 and 1~50 ${\mu}M$ cholesterol, respectively. The detection limit of all immobilized enzyme reactors was 1 ${\mu}M$. These enzyme reactors showed high sensitivity; especially, the enzyme reactors with CNBr-activated sepharose and Na-alginate indicated high coupling efficiency and sensitivity. Therefore, both of the enzyme reactors are more suitable for a cholesterol biosensor system.

• Journal of Intelligence and Information Systems
• /
• 제23권2호
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Journal of Embryo Transfer
• /
• 제19권2호
• /
• pp.133-145
• /
• 2004

Serum-contain is commoly used for the production of in vitro-derived bovine embryos. However, were biological activity of serum varies from lot to lot, time consuming to choose better serum with good quality and risks of virus, bacteria and mycoplasma infection. This study established serum-free culture systems of in vitro embryo development to efficiently obtain a large number of blastocysts from ovaries of Hanwoo and oocytes maturation, cell number, tlerance of cryopreservation. Secondly, serum-contain medium is suspected of contributing to the large calf size, dystocia, cersarean sections, calf mortality and confirmed these blastocysts are high quality in terms of cyotolerance, high rates of pregancy and normal birth. For these reasons, Culture media (IVMD101 and IVD101) designed specifically for the preimplantation bovine embryo are rather simplistic, being based on salt solutions with additional energy substrates and growth factors. An improved serum-free medium (IVMD101) was developed for bovine oocytes maturation in vitro. Proportions of embryos developing to the blastocyst stage cultured in both IVD101(32.4%) and IVD101(34.5%) serum-free media were higher than in TCM199+10% FBS(12.4%) serumcontaining medium. Futhermore, the cell numbers per blastosyst obtained in the serum-free media were superior to those of blastocysts developed in serum-supplemented medium. Also, cell numbers of blastocysts obtained in the serum-free media were similar with blastocysts derived in vivo. Survival rate blastocysts after 24 hr incubation after thawing, the blastocysts cultured in both IVD101(94.5%) and IVD101(95.8%) serum-free media were higher than in TCM199+10% FBS (52.5%) serum-containing medium. After 72 hr incubation after thawing, hatching rates of blastocysts developed in IVD101(78.4%) and IVMD101(83.7%) were sighnificantly higher than that developed in the serum-supplemented medium(32.0%). The pregnancy rates almost not different between fresh blastocysts(38.2%) and frozen blastocysts(34.9%). The results suggested that the improved serum-free media(IVMD101 and IVD101) offer several advantages over culture in serum-cotaining medium, including increased rates of blastocyst formation and high cel numbers. Additionally, the survival and hatching rates of embryos product in serum-free media after post-thaw culture were superior to those of embryos produced in the serum-containg medium and useful for the production of high quality bovine embryos for cryo-preservation. These improved serum-free media are beneficial not only for the study of the mechanisms of early embryogenesis but also for mass production of good quality embryos for embryo transfer, cloning and transgenesis.

• Journal of the Korean Society of Food Science and Nutrition
• /
• 제36권11호
• /
• pp.1399-1408
• /
• 2007

This study was conducted to compare health and nutritional status of 45 home-living elderly people receiving free Meals on Wheels (MOW) (13 men, 32 women) and 81 low income class elderly people receiving free congregate meals (CM) (10 men, 71 women) served in Seoul. Data were obtained from questionnaires, anthropometry and interviews for the 24-hour dietary recall methods. There were no significant differences between the two groups in age and body mass index. Education level, type of housing, family type and income of the two groups also were not significantly different. In MOW, frequencies of exercise were lower while the prevalence of stroke, respiratory disease and loneliness were higher, compared with the CM. The scores of ADL, IADL and food habit of MOW were lower than those of CM. The average daily nutritional intake of both MOW and CM were as a whole under the DRI for Koreans. Energy and macro-nutrient intakes of MOW were tended to be lower than CM (except protein intakes for female). Ca, K, vitamin A, vitamin $B_1$, vitamin $B_2$, vitamin C and folate intakes of MOW were less than 50% of DRI. Percentages of subjects consuming energy less than 75% of EER and 4 nutrients intakes less than EAR were higher in MOW (42.2%) than in CM (1.2%). Our results indicated that dietary nutritional status of MOW was very poor, especially in the case of female elderly groups. For the welfare of the home-living elderly people receiving free MOW, meal service programs should be improved in quality of diet by national supports.

• Radiation Oncology Journal
• /
• 제20권1호
• /
• pp.81-90
• /
• 2002

Purpose : To establish and verify the proper and the practical IMRT (Intensity--modulated radiation therapy) patient QA (Quality Assurance). Materials and Methods : An IMRT QA which consists of 3 steps and 16 items were designed and examined the validity of the program by applying to 9 patients, 12 IMRT cases of various sites. The three step OA program consists of RTP related QA, treatment information flow QA, and a treatment delivery QA procedure. The evaluation of organ constraints, the validity of the point dose, and the dose distribution are major issues in the RTP related QA procedure. The leaf sequence file generation, the evaluation of the MLC control file, the comparison of the dry run film, and the IMRT field simulate image were included in the treatment information flow procedure QA. The patient setup QA, the verification of the IMRT treatment fields to the patients, and the examination of the data in the Record & Verify system make up the treatment delivery QA procedure. Results : The point dose measurement results of 10 cases showed good agreement with the RTP calculation within $3\%$. One case showed more than a $3\%$ difference and the other case showed more than $5\%$, which was out side the tolerance level. We could not find any differences of more than 2 mm between the RTP leaf sequence and the dry run film. Film dosimetry and the dose distribution from the phantom plan showed the same tendency, but quantitative analysis was not possible because of the film dosimetry nature. No error had been found from the MLC control file and one mis-registration case was found before treatment. Conclusion : This study shows the usefulness and the necessity of the IMRT patient QA program. The whole procedure of this program should be peformed, especially by institutions that have just started to accumulate experience. But, the program is too complex and time consuming. Therefore, we propose practical and essential QA items for institutions in which the IMRT is performed as a routine procedure.

• Journal of Nutrition and Health
• /
• 제36권9호
• /
• pp.898-907
• /
• 2003

Antioxidative function of uncooked powdered food (Sangsik) was evaluated in rats consuming nutritionally unbalanced diet including 1％ cholesterol, high proportion of animal lipids (lard : soybean oil : 8 . 2) , sub-optimal levels of vitamin and mineral mixture along with 0.5% ethanol in drinking water. The uncooked powdered food tested in the present study was a mixture composed of 42 kinds of plant foods (cereals, legumes, seaweeds, vegetables, and fruits) supplemented with vitamins and minerals, and dietary fiber. Control rats were fed the semi-purified diet based on the AIN-93G composition, and nutritionally unbalanced rats were divided into 3 groups, and fed one of the following diets with 0.5% ethanol in drinking water for 5 weeks : unbalanced control diet (UC) ,20% Sangsik powder supplemented diet (S20), and 40% Sangsik powder supplemented diet (S40) . Food efficiency ratio was significantly higher in rats fed S40 compared to the value for rats fed UC (p < 0.05). Hepatic level of thiobarbituric acid reactive substances (TBARS) was significantly lower in rats fed UC compared to that for control rats (p < 0.05) , and was not influenced by dietary supplementation of the Sangsik powder. Hepatic superoxide dismutase (SOD) activity was significantly higher in rats fed UC compared to that for control rats (p < 0.05) , and significantly reduced in rats fed S20 or S40 compared to the value for unbalanced control rats. Feeding unbalanced control diet significantly reduced the ratio of hepatic GSH-Px ＋ catalase/SOD activities compared to the value for control rats, and this decrease in the ratio of antioxidant enzyme activities was reversed by adding the Sangsik powder to the diet at 20% (p <0.05) . Based on the results of antioxidant enzyme activities, feeding uncooked powdered diet appears to provide a favorable environment for body's antioxidative defense mechanism. Serum levels of Fe and Cu were significantly lower in rats fed the Sangsik powder supplemented diets compared to the value for unbalanced control rats (p < 0.05) , and levels of Se, Mn, and Zn were also tended to be decreased by dietary supplementation of the Sangsik powder. These results postulate the possibility that ingredients used in the uncooked powdered food may decrease the bioavailability of trace elements in rats.

• Journal of Nutrition and Health
• /
• 제44권3호
• /
• pp.231-242
• /
• 2011

The objective of this study was to investigate the effects of nutrition education based on ubiquitous healthcare (u-health) service on changes in dietary habits, nutrition intake, and risk factors for metabolic syndrome in male workers. In total, 72 male office workers with at least three risk factors of the National Cholesterol Education Program-Adult Treatment Panel III were recruited as subjects. Anthropometric measurements and biochemical analyses were conducted on all subjects. Dietary habits and nutrient intake were determined by a questionnaire using the 24-hour dietary recall method before and after nutrition education. Subjects measured their body composition, blood pressure, and physical activity more than once per week during the 12 weeks using the u-health care equipment and sent these data to a central database system using a personal computer. Individual nutrition counseling was provided four times on the first, fourth, eight, and twelfth weeks. The results showed significant decreases in abdominal circumference, body fat (%), diastolic blood pressure, serum triglycerides, and serum total cholesterol during the 12 weeks. Subjects with more than 12 measurements showed significant reductions in abdominal circumference, body fat (%), serum triglyceride, and serum total cholesterol. Mean intake of dietary fiber, animal calcium, potassium, vitamin C, and folic acid after nutrition education were higher than those before nutrition education. Participants showed significant increases in the frequencies of consuming protein foods (meat, fish, eggs, beans, tofu, etc.) and vegetables. In conclusion, nutrition education through the u-health service resulted in positive effects on the risk factors for metabolic syndrome, nutrient intake, and dietary habits.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2008년도 학술발표회 논문집
• /
• pp.869-877
• /
• 2008

The purpose of this study is to investigate the trends and patterns of variou kind of water uses in a household by metering in Korea. Water use components are classified by toilet, washbowl, bathing, laundry, kitchen, etc. Flow meters are installed in 146 household selected by sampling in all around Korea. The data are gathered by web-based data collection system from the year 2002 to 2006, considering pre-investigated data such as occupation, revenue, family members, housing types, age, floor area, water saving devices, education, etc. Reliable data are selected by upper fence method for each observed water use component and statistical characteristics are estimated for each residential type to determine liter per capita per day. Estimated domestic per capita day show an indoor water use with the range from $150{\ell}pcd$ to $169{\ell}pcd$ for each housing type as the order of high rise apartment, multi-house, and single house. As the order of consuming amount among water use components, it is investigated that toilet($38.5{\ell}pcd$) is the first, and the second is laundry water($30.8{\ell}pcd$), the third is kitchen($28.4{\ell}pcd$), the fourth is bathtub($24.7{\ell}pcd$), the next is washbowl($15.4{\ell}pcd$). The results are compared with water uses in U.K. and U.S. As life style has been changed into western style, pattern of water use in Korea is tend to be similar with the U.S. water use pattern. Compared with the surveying results by Bradley, on 1985. Thirty liter of total use increased with the advancement of economic level, and a little change of water use pattern can be found. Especially, toilet water take almost half part of total water use and laundry water shows lowest as 11% in surveying at the year of 1985. But, this study shows that 39 liter, 28% of toilet water, has been decreased by the spread of saving devices and campaign. It is supposed that the spread large sized laundry machine make by-hand laundry has been decreased and water use increased. Unit water amount of each end-use in household can be applied to design factor for water and wastewater facilities, and it play a role as information in establishing water demand forecasting and conservation policy.