• Journal of Chest Surgery
• /
• v.37 no.2
• /
• pp.119-130
• /
• 2004

Decrease in cardiac function after open heart surgery is due to an ischemia induced myocardial damage during surgery, and ischemic preconditioning, a condition in which the myocardial damage does not accumulate after repeated episodes of ischemia but protects itself from damage after prolonged ischemia due to myocytes tolerating the ischemia, is known to diminish myocardial damage, which also helps the recovery of myocardium after reperfusion, and decreases incidences of arrythmia. Our study is performed to display the ischemic preconditioning and show the myocardial protective effect by applying cardioplegic solution to the heart removed from rat. Material and Method: Sprague-Dawley male rats were used, They were fixed on a modified isolated working heart model after cannulation. The reperfusion process was according to non-working and working heart methods and the working method was executed for 20 minutes in which the heart rate, aortic pressure, aortic flow and coronary flow were measured and recorded. The control group is the group which the extracted heart was fixed on the isolated working heart model, recovered by reperfusion 60 minutes after infusion and preserved in the cardioplegic solution 20 minutes after the working heart perfusion and aortic cross clamp, The thesis groups were divided into group I, which ischemic hearts that were hypoxia induced were perfused by cardioplegic solution and preserved for 60 minutes; group II, the cardioplegic solution was infused 45 seconds (II-1), 1 minutes (II-2), 3 minutes (II-3), after the ischemia induction, 20 minutes after working heart perfusion and aortic cross clamp; and group III, hearts were executed on working heart perfusion for 20 minutes and aortic cross clamp was performed for 45 seconds (III-1), 1minute (III-2), 3 minutes (III-3), reperfused for 2 minutes to recover the heart, and then aortic cross clamping was repeated for reperfusion, all the groups were compared based on hemodynamic performance after reperfusion of the heart after preservation for 60 minutes. Result: The recovery time until spontaneous heart beat was longer in groups I, II-3, III-2 and III-3 to control group (p<0.01). Group III-1 (p<0.05) had better results in terms of recovery in number of heart rates compared to control group, and recovered better compared to II-1 (p<0.05). The recovery of aortic blood pressure favored group III-1 (p<0.05) and had better outcomes compared with II-1 (p<0.01). Group III-1 also showed best results in terms of cardiac output (p<0.05) and group III-2 was better compared to II-2 (p<0.05). Group I (p<0.01) and II-3 (p<0.05) showed more cardiac edema than control group. Conclusion: When the effects of other organs are dismissed, protecting the heart by infusion of cardioplegic solution after enforcing ischemia for a short period of time before the onset of abnormal heart beats for preconditioning has a better recovery effect in the cardioplegic group with preconditioning compared to the cardioplegic solution itself. we believe that further study is needed to find a more effective method of preconditioning.

• Journal of Chest Surgery
• /
• v.39 no.7 s.264
• /
• pp.534-543
• /
• 2006

Background: There are a lot of debates regarding the optimal timing of operation of acute myocardial infarction (AMI). Off pump coronary artery bypass grafting (OPCAB) has benefits by avoiding the adverse effects of the cardio-pulmonary bypass, but its efficacy in AMI has not been confirmed yet. The purpose of this study is to evaluate retrospectively early and mid-term results of OPCAB in patients with AMI according to transmurality and timing of operation. Material and Method: Data were collected in 126 AMI patients who underwent OPCAB between January 2002 and July 2005, Mean age of patients were 61.2 years. Male was 92 (73.0%) and female was 34 (27.2%). 106 patients (85.7%) had 3 vessel coronary artery disease or left main disease. Urgent or emergent operations were performed in 25 patients (19.8%). 72 patients (57.1%) had non-transmural myocardial infarction (group 1) and 52 patients (42.9%) had transmural myocardial infarction (group 2). The incidence of cardiogenic shock and insertion of intra-aortic balloon pump (IABP) was higher in group 2. The time between occurrence of AMI and operation was divided in 4 subgroups (<1 day, $1{\sim}3\;days,\;4{\sim}7\;days$, >8 days). OPCAB was performed a mean of $5.3{\pm}7.1$ days after AMI in total, which was $4.2{\pm}5.9$ days in group 1, and $6,6{\pm}8.3$ days in group 2. Result: Mean distal an-astomoses were 3.21 and postoperative IABP was inserted in 3 patients. There was 1 perioperative death in group 1 due to low cardiac output syndrome, but no perioperative new MI occurred in this study. There was no difference in postoperative major complication between two groups and according to the timing of operation. Mean follow-up time was 21.3 months ($4{\sim}42$ months). The 42 months actuarial survival rate was $94.9{\pm}2.4%$, which was $91.4{\pm}4.7%$ in group 1 and $98.0{\pm}2.0%$ in group 2 (p=0.26). The 42 months freedom rate from cardiac death was $97.6{\pm}1.4%$ which was $97.0{\pm}2.0%$ in group 1 and $98.0{\pm}2.0%$ in group 2 (p=0.74). The 42 months freedom rate from cardiac event was $95.4{\pm}2.0%$ which was $94.8{\pm}2.9%$ in group 1 and $95.9{\pm}2.9%$ in group 2 (p=0.89). Conclusion: OPCAB in AMI not only reduces morbidity but also favors hospital outcomes irrespective of timing of operation. The transmurality of myocardial infarction did not affect the surgical and midterm outcomes of OPCAB. Therefore, there may be no need to delay the surgical off-pump revascularization of the patients with AMI if surgical revascularization is indicated.

• Journal of Distribution Research
• /
• v.17 no.1
• /
• pp.37-63
• /
• 2012

In franchise business, exclusive sales territory (sometimes EST in table) protection is a very important issue from an economic, social and political point of view. It affects the growth and survival of both franchisor and franchisee and often raises issues of social and political conflicts. When franchisee is not familiar with related laws and regulations, franchisor has high chance to utilize it. Exclusive sales territory protection by the manufacturer and distributors (wholesalers or retailers) means sales area restriction by which only certain distributors have right to sell products or services. The distributor, who has been granted exclusive sales territories, can protect its own territory, whereas he may be prohibited from entering in other regions. Even though exclusive sales territory is a quite critical problem in franchise business, there is not much rigorous research about the reason, results, evaluation, and future direction based on empirical data. This paper tries to address this problem not only from logical and nomological validity, but from empirical validation. While we purse an empirical analysis, we take into account the difficulties of real data collection and statistical analysis techniques. We use a set of disclosure document data collected by Korea Fair Trade Commission, instead of conventional survey method which is usually criticized for its measurement error. Existing theories about exclusive sales territory can be summarized into two groups as shown in the table below. The first one is about the effectiveness of exclusive sales territory from both franchisor and franchisee point of view. In fact, output of exclusive sales territory can be positive for franchisors but negative for franchisees. Also, it can be positive in terms of sales but negative in terms of profit. Therefore, variables and viewpoints should be set properly. The other one is about the motive or reason why exclusive sales territory is protected. The reasons can be classified into four groups - industry characteristics, franchise systems characteristics, capability to maintain exclusive sales territory, and strategic decision. Within four groups of reasons, there are more specific variables and theories as below. Based on these theories, we develop nine hypotheses which are briefly shown in the last table below with the results. In order to validate the hypothesis, data is collected from government (FTC) homepage which is open source. The sample consists of 1,896 franchisors and it contains about three year operation data, from 2006 to 2008. Within the samples, 627 have exclusive sales territory protection policy and the one with exclusive sales territory policy is not evenly distributed over 19 representative industries. Additional data are also collected from another government agency homepage, like Statistics Korea. Also, we combine data from various secondary sources to create meaningful variables as shown in the table below. All variables are dichotomized by mean or median split if they are not inherently dichotomized by its definition, since each hypothesis is composed by multiple variables and there is no solid statistical technique to incorporate all these conditions to test the hypotheses. This paper uses a simple chi-square test because hypotheses and theories are built upon quite specific conditions such as industry type, economic condition, company history and various strategic purposes. It is almost impossible to find all those samples to satisfy them and it can't be manipulated in experimental settings. However, more advanced statistical techniques are very good on clean data without exogenous variables, but not good with real complex data. The chi-square test is applied in a way that samples are grouped into four with two criteria, whether they use exclusive sales territory protection or not, and whether they satisfy conditions of each hypothesis. So the proportion of sample franchisors which satisfy conditions and protect exclusive sales territory, does significantly exceed the proportion of samples that satisfy condition and do not protect. In fact, chi-square test is equivalent with the Poisson regression which allows more flexible application. As results, only three hypotheses are accepted. When attitude toward the risk is high so loyalty fee is determined according to sales performance, EST protection makes poor results as expected. And when franchisor protects EST in order to recruit franchisee easily, EST protection makes better results. Also, when EST protection is to improve the efficiency of franchise system as a whole, it shows better performances. High efficiency is achieved as EST prohibits the free riding of franchisee who exploits other's marketing efforts, and it encourages proper investments and distributes franchisee into multiple regions evenly. Other hypotheses are not supported in the results of significance testing. Exclusive sales territory should be protected from proper motives and administered for mutual benefits. Legal restrictions driven by the government agency like FTC could be misused and cause mis-understandings. So there need more careful monitoring on real practices and more rigorous studies by both academicians and practitioners.

• Journal of radiological science and technology
• /
• v.32 no.3
• /
• pp.335-341
• /
• 2009

Purpose : The medical imaging issuance is changed from conventional film method to Digital Compact Disk solution because of development on IT technology. However other medical record department's are undergoing identification check through and through whereas medical imaging department cannot afford to do that. So, we examine present applicant's recognition of private intelligence safeguard, and medical imaging issuance condition by CD & DVD medium toward various medical facility and then perform comparative analysis associated with domestic and foreign law & recommendation, lastly suggest standard for medical imaging issuance and process relate with internal environment. Materials and methods : First, we surveyed issuance process & required documents when situation of medical image issuance in the metropolitan medical facility by wire telephone between 2008.6.1$\sim$2008.7.1. in accordance with the medical law Article 21$\sim$clause 2, suggested standard through applicant's required documents occasionally - (1) in the event of oneself $\rightarrow$ verifying identification, (2) in the event of family $\rightarrow$ verifying applicant identification & family relations document (health insurance card, attested copy, and so on), (3) third person or representative $\rightarrow$ verifying applicant identification & letter of attorney & certificate of one's seal impression. Second, also checked required documents of applicant in accordance with upper standard when situation of medical image issuance in Kyung-hee university medical center during 3 month 2008.5.1$\sim$2008.7.31. Third, developed a work process by triangular position of issuance procedure for situation when verifying required documents & management of unpreparedness. Result : Look all over the our manufactured output in the hospital - satisfy the all conditions $\rightarrow$ 4 place(12%), possibly request everyone $\rightarrow$ 4 place(12%), and apply in the clinic section $\rightarrow$ 9 place(27%) that does not medical imaging issuance office, so we don't know about required documents condition. and look into whether meet or not the applicant's required documents on upper 3month survey - satisfy the all conditions $\rightarrow$ 629 case(49%), prepare a one part $\rightarrow$ 416 case(33%), insufficiency of all document $\rightarrow$ 226case(18%). On the authority of upper research result, we are establishing the service model mapping for objective reception when image export situation through triangular position of issuance procedure and reduce of friction with patient and promote the patient convenience. Conclusion : The PACS is classified under medical machinery that mean indicates about higher importance of medical information therefore medical information administrator's who already received professional education & mind, are performer about issuance process only and also have to provide under ID checking process exhaustively.

• Journal of Chest Surgery
• /
• v.37 no.1
• /
• pp.27-34
• /
• 2004

Background: Infective endocarditis shows higher operative morbidity and mortality rates than other cardiac diseases. The vast majority of studies on infective endocarditis have been made on aortic endocarditis, with little attention having been paid to infective endocarditis on the mitral valve. This study attempts to investigate the clinical aspects and operative results of infective endocarditis on the mitral valve. Meterial and Method: The subjects of this study consist of 23 patients who underwent operations for infective endocariditis on the mitral valve from June 1995 to May 2003. Among them, 2 patients suffered from prosthetic valvular endocarditis and the other 21 from native valvular endocarditis. The subjects were evenly distributed age-wise with an average age of 44.8$\pm$15.7 (11∼66) years. Emergency operations were performed on seventeen patients (73.9%) due to large vegetation or instable hemodynamic status. In preoperative examinations, twelve patients exhibited congestive heart failure, four patients renal failure, two patients spleen and renal infarction, and two patients temporary neurological defects, while one patient had a brain abscess. Based on the NYHA functional classification, seven patients were determined to be at Grade II, 9 patients at Grade III, and 6 patients at Grade IV. Vegetations were detected in 20 patients while mitral regurgitation was dominant in 19 patients with 4 patients showing up as mitral stenosis dominant on the preoperative echocardiogram. Blood cultures for causative organisms were performed on all patients, and positive results were obtained from ten patients, with five cases of Streptococcus viridance, two cases of methicillin-sensitive Staphylococcus aureus, and one case each of Corynebacteriurn, Haemophillis, and Gernella. Operations were decided according to the AA/AHA guidelines (1988). The mean follow-up period was 27.6 $\pm$23.3 (1 ∼ 97) months. Result: Mitral valve replacements were performed on 43 patients, with mechanical valves being used on 9 patients and tissue valves on the other 4. Several kinds of mitral valve repair or mitral valvuloplasty were carried out on the remaining 10 patients. Associated procedures included six aortic valve replacements, two tricuspid annuloplasty, one modified Maze operation, and one direct closure of a ventricular septal defect. Postoperative complications included two cases of bleeding and one case each of mediastinitis, low cardiac output syndrome, and pneumonia. There were no cases of early deaths, or death within 30 days following the operation. No patient died in the hospital or experienced valve related complications. One patient, however, underwent mitral valvuloplasty 3 months after the operation. Another patient died from intra-cranial hemorrhage in the 31st month after the operation. Therefore, the valve-related death rate was 4.3%, and the valve-related complication rate 8.6% on mid-term follow-up. 1, 3-, and 5-year valve- related event free rates were 90.8%, 79.5%, and 79.5%, respectively, while 1, follow-up. 1, 3-, and 5-year valve- related event free rates were 90.8%, 79.5%, and 79.5%, respectively, while 1, 3-, and 5-year survival rates were 100%, 88.8%, and 88.8%, respectively. Conclusion: The findings suggest that a complete removal of infected tissues is essential in the operative treatment of infectious endocarditis of the mitral valve. It is also suggested that when infected tissues are completely removed, neither type of material nor method of operation has a significant effect on the operation result. The postoperative results also suggest the need for a close follow-up observation of the patients suspected of having brain damage, which is caused by preoperative blood contamination or emboli from vegetation, for a possible cerebral vascular injury such as mycotic aneurysm.

• Nuclear Medicine and Molecular Imaging
• /
• v.42 no.5
• /
• pp.383-393
• /
• 2008

Purpose: Cancer specific killing can be achieved by therapeutic gene activated by cancer specific promotor. Expression of sodium iodide symporter (NIS) gene causes transportation and concentration of iodide into the cell, therefore radioiodine treatment after NIS gene transfer to cancer cell could be a form of radionuclide gene therapy. luciferase (Luc) gene transfected cancer cell can be monitored by in vivo optical imaging after D-luciferin injection. Aims of the study are to make vector with both therapeutic NIS gene driven by AFP promoter and reporter Luc gene driven by CMV promoter, to perform hepatocellular carcinoma specific radiodiodine gene therapy by the vector, and assessment of the therapy effect by optical imaging using luciferase expression. Materials and Methods: A Vector with AFP promoter driven NIS gene and CMV promoter driven Luc gene (AFP-NIS-CMV-Luc) was constructed. Liver cancer cell (HepG2, Huh-7) and non liver cancer cell (HCT-15) were transfected with the vector using liposome. Expression of the NIS gene at mRNA level was elucidated by RT-PCR. Radioiodide uptake, perchlorate blockade, and washout tests were performed and bioluminescence also measured by luminometer in these cells. In vitro clonogenic assay with 1-131 was performed. In vivo nuclear imaging was obtained with gamma camera after 1-131 intraperitoneal injection. Results: A Vector with AFP-NIS-CMV-Luc was constructed and successfully transfected into HepG2, Huh-7 and HCT-15 cells. HepG2 and Huh-7 cells with AFP-NIS-CMV-Luc gene showed higher iodide uptake than non transfected cells and the higher iodide uptake was totally blocked by addition of perchlorate. HCT-15 cell did not showed any change of iodide uptake by the gene transfection. Transfected cells had higher light output than control cells. In vitro clonogenic assay, transfected HepG2 and Huh-7 cells showed lower colony count than non transfected HepG2 and Huh-7 cells, but transfected HCT-15 cell did not showed any difference than non transfected HCT-15 cell. Number of Huh-7 cells with AFP-NIS-CMV-Luc gene transfection was positively correlated with radioidine accumulation and luciferase activity. In vivo nuclear imaging with 1-131 was successful in AFP-NIS-CMV-Luc gene transfected Huh-7 cell xenograft on nude mouse. Conclusion: A Vector with AFP promoter driven NIS and CMV promoter driven Luc gene was constructed. Transfection of the vector showed liver cancer cell specific enhancement of 1-131 cytotoxicity by AFP promoter, and the effect of the radioiodine therapy can be successfully assessed by non-invasive luminescence measurement.

• The Journal of Korean Society for Radiation Therapy
• /
• v.26 no.1
• /
• pp.83-89
• /
• 2014

Purpose : In case of the intensity modulated radiation therapy (IMRT) using Tomotherapy and linear accelerator (Linac), it was to compare and to evaluate the imaging dose of MVCT and CBCT that were performed daily for the correct set up of the patient. Materials and Methods : The human body model Phantom (Anderson rando Phantom, USA) was divided into the three parts as Head, Thorax, pelvis, and after GafChromic EBT3 film cut to the size of $0.5{\times}0.5cm2$.in the center of the recording area were situated on the ant, post, left, and right surface of the phantom and 2cm in depth from the ant, post, left, right, and center surface of the phantom, the surface dose and inner dose were measured repeatedly three times, respectively, using the tomotherapy (Hi Art) and the OBI of NovalisTx. The measured film calculated the output value by RIP version6.0 and then the average value of the dose was calculated by the one-way analysis of variance. Results : Using the human body model phantom, the results of MVCT and CBCT performance were that measurements of MVCT inner dose were showed $15.43cGy{\pm}6.05$ in the head, $16.62cGy{\pm}3.08$ in the thorax, $16.81cGy{\pm}5.24$ in the pelvis, and measurements of CBCT inner dose were showed $13.28{\pm}3.68$ in the head, from $13.66{\pm}4.04$ in the thorax, $15.52{\pm}3.52$ in the pelvis. The measurements of surface dose were showed in case of MVCT performance, $11.64{\pm}4.05$ in the head, $12.16{\pm}4.38$ in the thorax, $12.05{\pm}2.71$ in the pelvis, and in case of CBCT performance, $14.59{\pm}3.51$ in the head, $15.82{\pm}2.89$ in the thorax, $17.48{\pm}2.80$ in the pelvis, respectively. Conclusion : In case of Inner dose, the MVCT using MV energy showed higher than the CBCT using kV energy at 1.16 times in the head, at 1.22 times in the thorax, at 1.08 times in the pelvis, and in case of surface dose, the CBCT was higher than MVCT, at 1.25 times in the head, at 1.30 times in the thorax, at 1.45 times in the pelvis. Imaging dose was a small amount compared to the therapeutic dose but it was thought to affect partially to normal tissue because it was done in daily schedule. However, IMRT treatment was necessarily parallel with the IGRT treatment through the image-guide to minimize errors between planned and actual treatment. Thus, to minimize imaging dose that the patients receive, when planning the treatment, it should be set up a treatment plan considering imaging dose, or it must be performed by minimizing the scan range when shooting MVCT.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.109-122
• /
• 2014

People are nowadays creating a tremendous amount of data on Social Network Service (SNS). In particular, the incorporation of SNS into mobile devices has resulted in massive amounts of data generation, thereby greatly influencing society. This is an unmatched phenomenon in history, and now we live in the Age of Big Data. SNS Data is defined as a condition of Big Data where the amount of data (volume), data input and output speeds (velocity), and the variety of data types (variety) are satisfied. If someone intends to discover the trend of an issue in SNS Big Data, this information can be used as a new important source for the creation of new values because this information covers the whole of society. In this study, a Twitter Issue Tracking System (TITS) is designed and established to meet the needs of analyzing SNS Big Data. TITS extracts issues from Twitter texts and visualizes them on the web. The proposed system provides the following four functions: (1) Provide the topic keyword set that corresponds to daily ranking; (2) Visualize the daily time series graph of a topic for the duration of a month; (3) Provide the importance of a topic through a treemap based on the score system and frequency; (4) Visualize the daily time-series graph of keywords by searching the keyword; The present study analyzes the Big Data generated by SNS in real time. SNS Big Data analysis requires various natural language processing techniques, including the removal of stop words, and noun extraction for processing various unrefined forms of unstructured data. In addition, such analysis requires the latest big data technology to process rapidly a large amount of real-time data, such as the Hadoop distributed system or NoSQL, which is an alternative to relational database. We built TITS based on Hadoop to optimize the processing of big data because Hadoop is designed to scale up from single node computing to thousands of machines. Furthermore, we use MongoDB, which is classified as a NoSQL database. In addition, MongoDB is an open source platform, document-oriented database that provides high performance, high availability, and automatic scaling. Unlike existing relational database, there are no schema or tables with MongoDB, and its most important goal is that of data accessibility and data processing performance. In the Age of Big Data, the visualization of Big Data is more attractive to the Big Data community because it helps analysts to examine such data easily and clearly. Therefore, TITS uses the d3.js library as a visualization tool. This library is designed for the purpose of creating Data Driven Documents that bind document object model (DOM) and any data; the interaction between data is easy and useful for managing real-time data stream with smooth animation. In addition, TITS uses a bootstrap made of pre-configured plug-in style sheets and JavaScript libraries to build a web system. The TITS Graphical User Interface (GUI) is designed using these libraries, and it is capable of detecting issues on Twitter in an easy and intuitive manner. The proposed work demonstrates the superiority of our issue detection techniques by matching detected issues with corresponding online news articles. The contributions of the present study are threefold. First, we suggest an alternative approach to real-time big data analysis, which has become an extremely important issue. Second, we apply a topic modeling technique that is used in various research areas, including Library and Information Science (LIS). Based on this, we can confirm the utility of storytelling and time series analysis. Third, we develop a web-based system, and make the system available for the real-time discovery of topics. The present study conducted experiments with nearly 150 million tweets in Korea during March 2013.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.73-85
• /
• 2013

Nowadays, in today's information society, the importance of the knowledge service using the information to creative value is getting higher day by day. In addition, depending on the development of IT technology, it is ease to collect and use information. Also, many companies actively use customer information to marketing in a variety of industries. Into the 21st century, companies have been actively using the culture arts to manage corporate image and marketing closely linked to their commercial interests. But, it is difficult that companies attract or maintain consumer's interest through their technology. For that reason, it is trend to perform cultural activities for tool of differentiation over many firms. Many firms used the customer's experience to new marketing strategy in order to effectively respond to competitive market. Accordingly, it is emerging rapidly that the necessity of personalized service to provide a new experience for people based on the personal profile information that contains the characteristics of the individual. Like this, personalized service using customer's individual profile information such as language, symbols, behavior, and emotions is very important today. Through this, we will be able to judge interaction between people and content and to maximize customer's experience and satisfaction. There are various relative works provide customer-centered service. Specially, emotion recognition research is emerging recently. Existing researches experienced emotion recognition using mostly bio-signal. Most of researches are voice and face studies that have great emotional changes. However, there are several difficulties to predict people's emotion caused by limitation of equipment and service environments. So, in this paper, we develop emotion prediction model based on vision-based interface to overcome existing limitations. Emotion recognition research based on people's gesture and posture has been processed by several researchers. This paper developed a model that recognizes people's emotional states through body gesture and posture using difference image method. And we found optimization validation model for four kinds of emotions' prediction. A proposed model purposed to automatically determine and predict 4 human emotions (Sadness, Surprise, Joy, and Disgust). To build up the model, event booth was installed in the KOCCA's lobby and we provided some proper stimulative movie to collect their body gesture and posture as the change of emotions. And then, we extracted body movements using difference image method. And we revised people data to build proposed model through neural network. The proposed model for emotion prediction used 3 type time-frame sets (20 frames, 30 frames, and 40 frames). And then, we adopted the model which has best performance compared with other models.' Before build three kinds of models, the entire 97 data set were divided into three data sets of learning, test, and validation set. The proposed model for emotion prediction was constructed using artificial neural network. In this paper, we used the back-propagation algorithm as a learning method, and set learning rate to 10%, momentum rate to 10%. The sigmoid function was used as the transform function. And we designed a three-layer perceptron neural network with one hidden layer and four output nodes. Based on the test data set, the learning for this research model was stopped when it reaches 50000 after reaching the minimum error in order to explore the point of learning. We finally processed each model's accuracy and found best model to predict each emotions. The result showed prediction accuracy 100% from sadness, and 96% from joy prediction in 20 frames set model. And 88% from surprise, and 98% from disgust in 30 frames set model. The findings of our research are expected to be useful to provide effective algorithm for personalized service in various industries such as advertisement, exhibition, performance, etc.