• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.123-136
• /
• 2014

Recently, online shopping has further developed as the use of the Internet and a variety of smart mobile devices becomes more prevalent. The increase in the scale of such shopping has led to the creation of many Internet shopping malls. Consequently, there is a tendency for increasingly fierce competition among online retailers, and as a result, many Internet shopping malls are making significant attempts to attract online users to their sites. One such attempt is keyword marketing, whereby a retail site pays a fee to expose its link to potential customers when they insert a specific keyword on an Internet portal site. The price related to each keyword is generally estimated by the keyword's frequency of appearance. However, it is widely accepted that the price of keywords cannot be based solely on their frequency because many keywords may appear frequently but have little relationship to shopping. This implies that it is unreasonable for an online shopping mall to spend a great deal on some keywords simply because people frequently use them. Therefore, from the perspective of shopping malls, a specialized process is required to extract meaningful keywords. Further, the demand for automating this extraction process is increasing because of the drive to improve online sales performance. In this study, we propose a methodology that can automatically extract only shopping-related keywords from the entire set of search keywords used on portal sites. We define a shopping-related keyword as a keyword that is used directly before shopping behaviors. In other words, only search keywords that direct the search results page to shopping-related pages are extracted from among the entire set of search keywords. A comparison is then made between the extracted keywords' rankings and the rankings of the entire set of search keywords. Two types of data are used in our study's experiment: web browsing history from July 1, 2012 to June 30, 2013, and site information. The experimental dataset was from a web site ranking site, and the biggest portal site in Korea. The original sample dataset contains 150 million transaction logs. First, portal sites are selected, and search keywords in those sites are extracted. Search keywords can be easily extracted by simple parsing. The extracted keywords are ranked according to their frequency. The experiment uses approximately 3.9 million search results from Korea's largest search portal site. As a result, a total of 344,822 search keywords were extracted. Next, by using web browsing history and site information, the shopping-related keywords were taken from the entire set of search keywords. As a result, we obtained 4,709 shopping-related keywords. For performance evaluation, we compared the hit ratios of all the search keywords with the shopping-related keywords. To achieve this, we extracted 80,298 search keywords from several Internet shopping malls and then chose the top 1,000 keywords as a set of true shopping keywords. We measured precision, recall, and F-scores of the entire amount of keywords and the shopping-related keywords. The F-Score was formulated by calculating the harmonic mean of precision and recall. The precision, recall, and F-score of shopping-related keywords derived by the proposed methodology were revealed to be higher than those of the entire number of keywords. This study proposes a scheme that is able to obtain shopping-related keywords in a relatively simple manner. We could easily extract shopping-related keywords simply by examining transactions whose next visit is a shopping mall. The resultant shopping-related keyword set is expected to be a useful asset for many shopping malls that participate in keyword marketing. Moreover, the proposed methodology can be easily applied to the construction of special area-related keywords as well as shopping-related ones.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.1-18
• /
• 2016

Owing to the extensive use of Web media and the development of the IT industry, a large amount of data has been generated, shared, and stored. Nowadays, various types of unstructured data such as image, sound, video, and text are distributed through Web media. Therefore, many attempts have been made in recent years to discover new value through an analysis of these unstructured data. Among these types of unstructured data, text is recognized as the most representative method for users to express and share their opinions on the Web. In this sense, demand for obtaining new insights through text analysis is steadily increasing. Accordingly, text mining is increasingly being used for different purposes in various fields. In particular, issue tracking is being widely studied not only in the academic world but also in industries because it can be used to extract various issues from text such as news, (SocialNetworkServices) to analyze the trends of these issues. Conventionally, issue tracking is used to identify major issues sustained over a long period of time through topic modeling and to analyze the detailed distribution of documents involved in each issue. However, because conventional issue tracking assumes that the content composing each issue does not change throughout the entire tracking period, it cannot represent the dynamic mutation process of detailed issues that can be created, merged, divided, and deleted between these periods. Moreover, because only keywords that appear consistently throughout the entire period can be derived as issue keywords, concrete issue keywords such as "nuclear test" and "separated families" may be concealed by more general issue keywords such as "North Korea" in an analysis over a long period of time. This implies that many meaningful but short-lived issues cannot be discovered by conventional issue tracking. Note that detailed keywords are preferable to general keywords because the former can be clues for providing actionable strategies. To overcome these limitations, we performed an independent analysis on the documents of each detailed period. We generated an issue flow diagram based on the similarity of each issue between two consecutive periods. The issue transition pattern among categories was analyzed by using the category information of each document. In this study, we then applied the proposed methodology to a real case of 53,739 news articles. We derived an issue flow diagram from the articles. We then proposed the following useful application scenarios for the issue flow diagram presented in the experiment section. First, we can identify an issue that actively appears during a certain period and promptly disappears in the next period. Second, the preceding and following issues of a particular issue can be easily discovered from the issue flow diagram. This implies that our methodology can be used to discover the association between inter-period issues. Finally, an interesting pattern of one-way and two-way transitions was discovered by analyzing the transition patterns of issues through category analysis. Thus, we discovered that a pair of mutually similar categories induces two-way transitions. In contrast, one-way transitions can be recognized as an indicator that issues in a certain category tend to be influenced by other issues in another category. For practical application of the proposed methodology, high-quality word and stop word dictionaries need to be constructed. In addition, not only the number of documents but also additional meta-information such as the read counts, written time, and comments of documents should be analyzed. A rigorous performance evaluation or validation of the proposed methodology should be performed in future works.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.38 no.3
• /
• pp.225-236
• /
• 2012

In this study, the cellular protective effects on HaCaT cells and human erythrocytes and antioxidative effects of P. tricuspidata stem extracts were investigated. The ethyl acetate ($50{\mu}g/mL$) and aglycone fraction ($25{\mu}g/mL$) of P. tricuspidata stem extracts doesn't show any characteristics of cytotoxicity. When HaCaT cells were treated with 10 mM $H_2O_2$ and $30{\mu}M$ rose bengal, the ethyl acetate ($6.25{\sim}50{\mu}g/mL$) and aglycone ($6.25{\sim}25{\mu}g/mL$) fraction protected the cells against the oxidative damage in a concentration dependent manner. The P. tricuspidata stem extracts showed more prominent cellular protective effect than (+)-${\alpha}$-tocopherol, known as lipid antioxidant at $10{\mu}g/mL$. The ethylacetate fraction of P. tricuspidata stem extracts ($18.5{\mu}g/mL$) showed more free radical (1,1-diphenyl-2-picrylhydrazyl, DPPH) scavenging activity ($FSC5_{50}$). Reactive oxygen species (ROS) scavenging activity ($OSC_{50}$) of P. tricuspidata stem extracts on ROS generated in $Fe^{3+}$-EDTA/$H_2O_2$ system was investigated using the luminol-dependent chemiluminescence assay. The ethyl acetate ($1.72{\mu}g/mL$) and the aglycone fraction ($1.53{\mu}g/mL$) showed similar ROS scavenging activity of L-ascorbic acid ($1.50{\mu}g/mL$). These results indicate that extract/fractions of P. tricuspidata stem extracts can function as natural cytoprotective agents and antioxidants in biological systems, particularly skin exposed to UV radiation by protecting cellular membrane against ROS.

• Journal of Embryo Transfer
• /
• v.19 no.2
• /
• 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.

• Investigative Magnetic Resonance Imaging
• /
• v.3 no.2
• /
• pp.154-158
• /
• 1999

Purpose : The purpose of this study was to find the optimum TE value for enhancing $T_2^{*}$ weighting effect and minimizing the SNR degradation and to compare the BOLD effects according to the changes of TE in 1.5T and 3.0T MRI systems. Materials and Methods : Healthy normal volunteers (eight males and two females with 24-38 years old) participated in this study. Each volunteer was asked to perform a simple finger-tapping task (sequential opposition of thumb to each of the other four fingers) with right hand with a mean frequency of about 2Hz. The stimulus was initially off for 3 images and was then alternatively switched on and off for 2 cycles of 6 images. Images were acquired on the 1.5T and 3.0T MRI with the FLASH (fast low angle shot) pulse sequence (TR : 100ms, FA : $20^{\circ}$, FOV : 230mm) that was used with 26, 36, 46, 56, 66, 76ms of TE times in 1.5T and 16, 26, 36, 46, 56, 66ms of TE in 3.0T MRI system. After the completion of scan, MR images were transferred into a PC and processed with a home-made analysis program based on the correlation coefficient method with the threshold value of 0.45. To search for the optimum TE value in fMRI, the difference between the activation and the rest by the susceptibility change for each TE was used in 1.5T and 3.0T respectively. In addition, the functional $T_2^{*}$ map was calculated to quantify susceptibility change. Results : The calculated optimum TE for fMRI was $61.89{\pm}2.68$ at 1.5T and $47.64{\pm}13.34$ at 3.0T. The maximum percentage of signal intensity change due to the susceptibility effect inactivation region was 3.36% at TE 66ms in 1.5T 10.05% at TE 46ms in 3.0T, respectively. The signal intensity change of 3.0T was about 3 times bigger than of 1.5T. The calculated optimum TE value was consistent with TE values which were obtained from the maximum signal change for each TE. Conclusion : In this study, the 3.0T MRI was clearly more sensitive, about three times bigger than the 1.5T in detecting the susceptibility due to the deoxyhemoglobin level change in the functional MR imaging. So the 3.0T fMRI I ore useful than 1.5T.

• Korean Journal of Food Science and Technology
• /
• v.9 no.2
• /
• pp.123-130
• /
• 1977

A laboratory study was made to develop a simple and economic model method for the systematic determination of functional properties of 'Soy Protein Isolates (SPI)' prepared from defatted soybean meal. These are required to evaluate and to predict how SPI may behave in specific systems and such proteins can be used to simulate or replace conventional proteins. Data concerning the effects of pH, salt concentration, temperature, and protein concentration on the functional properties which include solubility, heat denaturation, gel forming capacity, emulsifying capacity, and foaming capacity are presented. The results are as follows: 1) The yield of SPI from defatted soybean meal increased to 83.9 % as the soybean meal was extracted with 0.02 N NaOH. 2) The suitable viscocity of a dope solution for spinning fiber was found to be 60 Poises by using syringe needle (0.3 mm) with 15 % SPI in 0.6 % NaOH. 3) Heat caused thickening and gelation in concentration of 8 % with a temperature threshold of $70^{\circ}C$. At $8{\sim}12\;%$ protein concentration, gel was formed within $10{\sim}30\;min$ at $70{\sim}100\;^{\circ}C$. It was, however, disrupted rapidly at $125\;^{\circ}C$ of overheat treatment. The gel was firm, resilient and self-supporting at protein concentration of 14 % and less susceptible to disruption of overheating. 4) The emulsifying capacity (EC) of SPI was correlated positively to the solubility of protein at ${\mu}=0$. At pH of the isoelectric point of SPI (pH 4.6), EC increased as concentration of sodium chloride increased. Using model system$(mixing\;speed:\;12,000\;r.p.m.,\;oil\;addition\;rate:\;0.9\;ml/sec,\;and\;temperature\;:\;20{\pm}1\;^{\circ}C)$, the maximum EC of SPI was found to be 47.2 ml of oil/100 mg protein, at the condition of pH 8.7 and ${\mu}=0.6$. The milk casein had greater EC than SPI at lower ionic strength while the EC of SPI was the same as milk casein at higher ionic strength. 5) The shaking test was used in determining the foam-ability of proteins. Progressively increasing SPI concentration up to 5 % indicated that the maximum protein concentration for foaming capacity was 2 %. Sucrose reduced foam expansion slightly but enhanced foam stability. The results of comparing milk casein and egg albumin were that foaming properties of SPI were the same as egg albumin, and better than milk casein, particularly in foam stability.

• Applied Biological Chemistry
• /
• v.44 no.3
• /
• pp.148-152
• /
• 2001

This study investigated the role of excitatory amino acid systems in the initiation of organophosphate-induced seizures and brain damages in rats through quantitative in vivo microdialysis. Microdialysates were collected from the hippocampus of rat brain, treated with diisopropylfluorophosphate (DFP; 2.67 mg/kg, s.c.) alone, and/or atropine sulfate (15 mg/kg, i.m.) and procyclidine (30 mg/kg, i.m.). The protective effects of atropine, a muscarinic blocker, and/or procyclidine, a N-methyl-D-aspartate and cholinergic antagonist, against DFP were examined. DFP treatment increased the levels of aspartate (Asp) and glutamate (Glu) significantly in the hippocampal persuate with the induction of seizures. Treatment of procyclidine could effectively block the increase of Asp and Glu levels. Atropine treatment showed no significant anticonvulsive effects against DFP-induced seizures. The increases of Asp and Glu levels by DFP were also completely blocked through the combined treatment of atropine and procyclidine. Histopathological findings on the hippocampus confirmed the above results. More effective protection was observed through the treatments of procyclidine alone or of both procyclidine and atropine than atropine alone against DFP-induced brain damage. Procyclidine was shown to be effective in DFP-induced seizures.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.22 no.4
• /
• pp.62-71
• /
• 2014

Three types of diffuser systems were manufactured and applied to investigate the effect of liquid fertilization of pig manure slurry by application of aeration processes. In the first type reactor, commonly used diffuser system, which diffuse air upward by diffusing aerator fixed at the bottom of the reactor is installed. In case of the second type, air diffuser is installed 10 cm above of the bottom of a reactor. In the third type reactor, the venturi-type air diffuser is installed at circulation pipe, which return pig slurry in the reactor(mixing-in-pipe process). The pig manure slurry separated to solid/liquid was flowed into the experimental reactor, and left as it for one week to precipitate solids. The concentration of organic matter, T-N, T-P and BOD in the raw pig manure slurry flowed into the reactor of bottom-fixed type aeration process were 1.82%, 4,400 mg/L, 360 mg/L and 13,542 mg/L, respectively. After aeration the concentration of organic matters, T-N, T-P and BOD in the slurry were 2.01%, 4,400 mg/L, 420 mg/L and 16,824 mg/L, respectively. The concentration of organic matter, T-N, T-P and BOD in the mixing-in-pipe type changed from 1.58%, 3,700 mg/L, 260 mg/L and 15,735 mg/L to 1.96%, 4,000 mg/L, 340 mg/L, and 18,098 mg/L, respectively. Changes of the concentration of organic matter, T-N, T-P and BOD of the pig manure slurry collected from the middle layers of two aeration reactors; bottom aeration process and the mixing-in-pipe process, were 10.4%, 0%, 16.7% and 24.2% and 24.0%, 8.1%, 30.8% and 15.0%, respectively. The thickness of foam layer generated on the surface of pig manure slurry in aeration tank was thinner in mixing-in-pipe reactor than bottom-fixed type aeration reactor.

• Journal of Korea Technology Innovation Society
• /
• v.10 no.2
• /
• pp.284-309
• /
• 2007

Technology transfer (TT) consortium is an affiliation of two or more public research institutions (PRIs) that participate in a common technology transfer activity or pool their resources together, with the objective of facilitating technology transfer. Based on empirical analysis of five regional TT consortia (2002-2006) operating in Korea, this paper suggests their effectiveness by employing a TT performance index (TTPI) and identifies possible characteristics involved, such as motivations, facilitators, barriers, and challenges. TTPI devised in the paper is a new composite TT performance index to measure how much the TT performance of a PH changed in a designated year compared to a base year. All the performance indicators of TTPI are well-structured based on the unique TT process that is prevalent in Korea. Further, TTPI can bring different size and focus of PRIs to the same scale for comparison by double-normalizing. The paper tests the effectiveness of TT consortium for the escalation of TT performances in member PRIs by highlighting the differences of TTPI's between 2005 and 2001. As a result, the paper found that the escalation of TTPI for member PRIs was greater than that for non-member PRIs. As for the characteristics of TT consortia, their respective factors obtained by TT expert survey were computed with proportion tests of differences (Z tests) to compare two perspectives between intramural and extramural groups. One of key findings is that there is general homogeneity in stakeholder perspectives regarding motivations, facilitators, barriers, and challenges. Some notable responses are as follow; the most probable motivation to join TT consortium is to share or exchange TT competences for enhanced performance. Second, the most probable facilitator is professional capability of consortium-hired personnel. Third, the foremost probable barriers to effective TT consortium are frequent change of consortium director and passive participation of member PRIs. Lastly, both publicizing TT consortia and developing performance metrics are the most important for the improvement of TT consortia. The understanding of the characteristics of TT consortia increases the likelihood of accelerated success, because TT consortia path from formation to termination encompasses many concepts, processes, principles, and factors. Finally, an analysis of the survey data combined with expert interview and observation data led the authors to derive five conditions as being critical to viable TT consortia in Korea at early stage of technology transfer systems. These conditions include policy infrastructure, proactive participation, excellent professionals, personal motivation, and teaming mechanisms. It is expected that the Korean evidence is a starting point to develop and refine the theory of TT consortia and for additional studies in other countries.