• Korean Journal of Microbiology
• /
• v.37 no.4
• /
• pp.284-288
• /
• 2001

Respiratory viruses are one of the most infectious agent in human. Six different respiratory tract viruses were detected from Busan while working on the preventive surveillance in 1997-2000. The isolation rate from suspected specimens were 8.4%. Influenza virus A, B type, parainfluenza virus, adenovirus, mumps virus, and measles virus were examined from throat swabs, serum, and secretions of patients. Influenza A/Sydney/05/97(H3N2)-like, A/Johanesburg/33/94(H3N2)-like, A/Beijing/262/95(H1N1)-like and Influenza B/Beijing/262/95-like, B/Harbin/07/94-like, B/Guangdong/08/93-like were found. Adenovirus serotype 1, 2, 3 and 5 were detected, antibody of mumps both IgM and IgG were shown and outbreaks of measles were confirmed. Different antigenic types of influenza virus were detected every year, one outbreak of parainfluenza in 1999, mumps outbreak in 1999 and 2000, and incidence of measles in 2000 were noticeable. Monthly outbreaks were November through following March with influenza virus, January through June with adenovirus, February through May and December with mumps, April through August and November, December with measles, respectively. The size of isolated viruses were 130 nm with influenza virus B type, non-enveloped, icosahedron with 70 nm with adenovirus, 170 nm with mumps virus and 180 nm with parainfluenza virus in diameter, respectively.

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.55-62
• /
• 2018

In this study, we have developed a model for predicting the number of patients (flu, pneumonia, and outbreak) using Big Data, which has been mainly performed overseas. Existing patient number system by government adopt procedures that collects the actual number and percentage of patients from several big hospital. However, prediction model in this study was developed combing a real-time collection of disease-related words and various other climate data provided in real time. Also, prediction number of patients were counted by machine learning algorithm method. The advantage of this model is that if the epidemic spreads rapidly, the propagation rate can be grasped in real time. Also, we used a variety types of data to complement the failures in Google Flu Trends.

• Clinical and Experimental Pediatrics
• /
• v.48 no.3
• /
• pp.266-275
• /
• 2005

Purpose : Acute respiratory tract infections are the most common illnesses in children. The great majority of these infections involving lower respiratory tracts infections(LRTIs) are caused by respiratory viruses such as respiratory syncytial virus(RSV), parainfluenza virus(PIV), influenza virus (Flu), and adenovirus(ADV), etc. Our purpose was to determine seasonal epidemiology and clinical characteristic features of each viral infection. Methods : Nasopharyngeal aspirate(NPA)s were collected from 4,554 hospitalized children diagnosed as LRTIs on the first day of admission. The study period was from September 1998(Autumn) through May 2003(Spring). Respiratory viruses were detected in 881(19 percent) cases by isolation of the virus or by antigen detection method using indirect immunofluorescent staining. We reviewed the medical records of 837 cases retrospectively. Results : The identified pathogens were RSV in 485 cases(55 percent), PIV in 152 cases(17 percent), FluA in 114 cases(13 percent), ADV in 79 cases(9 percent) and FluB in 51 cases(6 percent). Outbreaks of RSV occurred every year, mostly in the November through December period and of PIV in the April through June period. LRTIs by FluA reached the highest level in January, 2002. FluB infection showed an outbreak in April, 2002. The clinical diagnoses of viral LRTIs were bronchiolitis in 395 cases(47 percent), pneumonia in 305 cases(36 percent), croup in 73 cases(9 percent) and tracheobronchitis in 64 cases(8 percent). Conclusion : Viruses are one of the major etiologic agents of acute LRTIs in chidren. Therefore, we must continue to study their seasonal occurrence and clinical features to focus on management, and also for reasons of prevention.

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.147-157
• /
• 2018

Since Google launched a prediction service for influenza-like illness(ILI), studies on ILI prediction based on web search data have proliferated worldwide. In this regard, this study aims to build short-term predictive models for ILI in Korea using ILI and web search data and measure the performance of the said models. In these proposed ILI predictive models specific to Korea, ILI surveillance data of Korea CDC and Korean web search data of Google and Naver were used along with the ARIMA model. Model 1 used only ILI data. Models 2 and 3 added Google and Naver search data to the data of Model 1, respectively. Model 4 included a common query used in Models 2 and 3 in addition to the data used in Model 1. In the training period, the goodness of fit of all predictive models was higher than 95% ($R^2$). In predictive periods 1 and 2, Model 1 yielded the best predictions (99.98% and 96.94%, respectively). Models 3(a), 4(b), and 4(c) achieved stable predictability higher than 90% in all predictive periods, but their performances were not better than that of Model 1. The proposed models that yielded accurate and stable predictions can be applied to early warning systems for the influenza pandemic in Korea, with supplementary studies on improving their performance.

• The Korean Journal of Applied Statistics
• /
• v.20 no.1
• /
• pp.91-102
• /
• 2007

The major purpose of this article is to formulate a class of Space Time Autoregressive Moving Average(STARMA) model and Space Time Bilinear model(STBL), to discuss some of the their statistical properties such as model, identification approaches, some procedure for estimation and the predictions, and to compare the STARMA model with the STBL model. For illustration, The Mumps data reported from eight city & provinces monthly over the years 2001-2006 are used and the result from STARMA and STBL model are compared with using SSF(Sum of Square Prediction Error).

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.31-39
• /
• 2022

Stock prices are influenced by a number of external factors, such as laws and trends, as well as number-based internal factors such as trading volume and closing prices. Since many factors affect stock prices, it is very difficult to accurately predict stock prices using only fragmentary stock data. In particular, since the value of a company is greatly affected by the perception of people who actually trade stocks, emotional information about a specific company is considered an important factor. In this paper, we propose a deep learning-based stock price prediction model using sentiment analysis with news data considering temporal characteristics. Stock and news data, two heterogeneous data with different characteristics, are integrated according to time scale and used as input to the model, and the effect of time scale and sentiment index on stock price prediction is finally compared and analyzed. Also, we verify that the accuracy of the proposed model is improved through comparative experiments with existing models.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.4
• /
• pp.78-95
• /
• 2022

The result of previous studies and epidemiological invstigations for infectious diseases epidemic in livestock have shown that trips made by livestock-related vehicles are the main cause of the spread of these epidemics. In this study, the OD traffic volume of livestock freight vehicle during the week in each zone was calculated using livestock facility visit history data and digital tachograph data. Based on this, a model for predicting the spread of infectious diseases in livestock was developed. This model was trained using zonal records of foot-and-mouth disease in Gyeonggi-do for one week in January and February 2015 and in positive, it was succesful in predicting the outcome in all out of a total 13 actual infected samples for test.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.195-204
• /
• 2022

The tourism industry is facing a crisis due to the recent COVID-19 pandemic, and it is vital to improving profitability to overcome it. In situations such as COVID-19, it would be more efficient to sell additional products other than guest rooms to customers who have visited to increase the unit price rather than adopting an aggressive sales strategy to increase room occupancy to increase profits. Previous tourism studies have used machine learning techniques for demand forecasting, but there have been few studies on cross-selling forecasting. Also, in a broader sense, a resort is the same accommodation industry as a hotel. However, there is no study specialized in the resort industry, which is operated based on a membership system and has facilities suitable for lodging and cooking. Therefore, in this study, we propose a cross-selling prediction model using various machine learning techniques with an actual resort company's accommodation data. In addition, by applying the explainable artificial intelligence XAI(eXplainable AI) technique, we intend to interpret what factors affect cross-selling and confirm how they affect cross-selling through empirical analysis.

• Journal of Korea Game Society
• /
• v.10 no.2
• /
• pp.67-80
• /
• 2010

Investigating the trend of online gamers plays an important role in forecasting, marketing and making policy decision in gaming industry. In this regards, various studies on gamers' trend and characteristics have been conducted. However, these precedent studies show limitation that they're static analysis since they are usually based on the surveys at a certain point. Therefore, this paper aims to identify some implications on forthcoming directions of gaming industry by analyzing dynamic trend of gamers based on the 8 years(from 2002 to 2009) of data from White Paper on Korean Games. Major implications found in this paper are as follows. Negative perception of games increases as the number of gamers increases. Among juveniles, games became a substitute for TV and the amount of time they play games depends on the existence and type of popular games of that time. Also, most item trading is intensively done by a small number of gamers.

• Archives of design research
• /
• v.13 no.1
• /
• pp.149-156
• /
• 2000

This study focuses on the analyzing the factors that determined Wedding furniture design in Modern period. Final conculusions based of the above mentioned findings are as follows; First, Jangnong has been an essential Wedding furniture item since modern period and little change in the style has been found. Second, Wedding furniture items became more various in kind such as Jangnong, Moon gap, dresser, etc,. The design of these were became bigger in size and more various furniture for storing was included. Third, factors that determired Wedding furniture design were change of family, marriage and Korea's Honsu norms, economic development, industrialization, commercialism, housing and lifestyle. Factors of housing and lifestyle were mainly affected in Wedding furniture design. Fourth, criteria for Wedding furniture design were functionality, fashion, decorativeness, tradition and symbol. But the symbolic importance of Wedding furniture has been weakened as a variety of essential Honsu items. Fifth, it was concluded that a proposed theoretical model of this study was appropriate for analyzing Wedding furniture design.