• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.121-142
• /
• 2023

As the number and weight of imported food are steadily increasing, safety management of imported food to prevent food safety accidents is becoming more important. The Ministry of Food and Drug Safety conducts on-site inspections of foreign food facilities before customs clearance as well as import inspection at the customs clearance stage. However, a data-based safety management plan for imported food is needed due to time, cost, and limited resources. In this study, we tried to increase the efficiency of the on-site inspection by preparing a machine learning prediction model that pre-selects the companies that are expected to fail before the on-site inspection. Basic information of 303,272 foreign food facilities and processing businesses collected in the Integrated Food Safety Information Network and 1,689 cases of on-site inspection information data collected from 2019 to April 2022 were collected. After preprocessing the data of foreign food facilities, only the data subject to on-site inspection were extracted using the foreign food facility_code. As a result, it consisted of a total of 1,689 data and 103 variables. For 103 variables, variables that were '0' were removed based on the Theil-U index, and after reducing by applying Multiple Correspondence Analysis, 49 characteristic variables were finally derived. We build eight different models and perform hyperparameter tuning through 5-fold cross validation. Then, the performance of the generated models are evaluated. The research purpose of selecting companies subject to on-site inspection is to maximize the recall, which is the probability of judging nonconforming companies as nonconforming. As a result of applying various algorithms of machine learning, the Random Forest model with the highest Recall_macro, AUROC, Average PR, F1-score, and Balanced Accuracy was evaluated as the best model. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the selection reason for nonconforming facilities of individual instances, and discuss applicability to the on-site inspection facility selection system. Based on the results of this study, it is expected that it will contribute to the efficient operation of limited resources such as manpower and budget by establishing an imported food management system through a data-based scientific risk management model.

• Journal of the Korean Vacuum Society
• /
• v.17 no.1
• /
• pp.16-22
• /
• 2008

We studied plasma etching of polycarbonate in $O_2/SF_6$, $O_2/N_2$ and $O_2/CH_4$. A capacitively coupled plasma system was employed for the research. For patterning, we used a photolithography method with UV exposure after coating a photoresist on the polycarbonate. Main variables in the experiment were the mixing ratio of $O_2$ and other gases, and RF chuck power. Especially, we used only a mechanical pump for in order to operate the system. The chamber pressure was fixed at 100 mTorr. All of surface profilometry, atomic force microscopy and scanning electron microscopy were used for characterization of the etched polycarbonate samples. According to the results, $O_2/SF_6$ plasmas gave the higher etch rate of the polycarbonate than pure $O_2$ and $SF_6$ plasmas. For example, with maintaining 100W RF chuck power and 100 mTorr chamber pressure, 20 sccm $O_2$ plasma provided about $0.4{\mu}m$/min of polycarbonate etch rate and 20 sccm $SF_6$ produced only $0.2{\mu}m$/min. However, the mixed plasma of 60 % $O_2$ and 40 % $SF_6$ gas flow rate generated about $0.56{\mu}m$ with even low -DC bias induced compared to that of $O_2$. More addition of $SF_6$ to the mixture reduced etch of polycarbonate. The surface roughness of etched polycarbonate was roughed about 3 times worse measured by atomic force microscopy. However examination with scanning electron microscopy indicated that the surface was comparable to that of photoresist. Increase of RF chuck power raised -DC bias on the chuck and etch rate of polycarbonate almost linearly. The etch selectivity of polycarbonate to photoresist was about 1:1. The meaning of these results was that the simple capacitively coupled plasma system can be used to make a microstructure on polymer with $O_2/SF_6$ plasmas. This result can be applied to plasma processing of other polymers.

• 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.

• Journal of Hospice and Palliative Care
• /
• v.12 no.4
• /
• pp.228-233
• /
• 2009

Purpose: The purpose of this study was to retrospectively examine the factors and characteristics of cancer patients who visited the emergency room, as well as to offer some educational materials for to manage acute symptoms. Methods: Data for this study were selected from the period of January to December, 2006. A total of 564 patients were examined using the tool which we developed by ourselves for the study. The collected data were analyzed using the SAS program for frequencies and percentage. Results: As for disease-related characteristics of the subjects, 28.9% of them had gastric and colorectal cancer; 66.9% were in stage 4; 51.6% had been in chemotherapy prior to visiting the emergency room; and 82.5% had their anticancer drug administrated average 1~5 times. As for the characteristics in regard to visit the emergency room, 62.9% were admitted to hospital within 2 weeks of being treated. As for chief complaints for visiting the emergency room, the worst symptom was pain, followed by symptoms such as gastro-intestinal symptoms, respiratory symptoms, high fever, and weakness. As for the disease-related symptoms, the worst symptom that gastric, colorectal, pancreatic, liver and gallbladder cancer patients complained of was pain, high fever for lymphoma patients was respiratory symptoms for lung cancer patients, and gastrointestinal symptoms for head and neck cancer and other patients. Conclusion: Therefore, according to their need and background, an individualized consultation and teaching program should be provided to cancer patients.

• Journal of dental hygiene science
• /
• v.15 no.3
• /
• pp.259-264
• /
• 2015

For this experiment, specimen was manufactured by injecting polymer and monomer into silicon mold with volume ratio of 2.5:1 based on ISO 20795-2 so that average thickness, width and length of specimen would be maintained as 3.3 mm, 10.0 mm and 65.0 mm, respectively depending on spray on technique. Specimen was divided into 3 groups ($25^{\circ}C$, $40^{\circ}C$, $70^{\circ}C$) depending on polymerization temperature and 10 specimen was manufactured for each group and it was polymerized in water tank of ${\pm}1^{\circ}C$ under the setting condition of polymerization time of 15 minutes and pressure of 3 bar. After keeping specimen in distilled water of $37^{\circ}C$ for over 48 hours before experiment, flexural strength (FS) and elasticity modulus (EM) of specimen being tested by using Intron (3344; Instron; Instron). SPSS ver. 16.0 was used for analysis and post-hoc test of Scheffe was performed after using one-way ANOVA. When comparing mean value of FS of resin for orthodontics, it was represented in the range of 71.500 MPa for $25^{\circ}C$ group, 74.920 MPa for $40^{\circ}C$ group and 76.880 MPa for $70^{\circ}C$ group and difference was shown in the order of $25^{\circ}C$ group <$40^{\circ}C$ group <$70^{\circ}C$ group but such difference was not significant statistically (p=0.052). Result of EM mean value of resin for orthodontics was more polymerization temperature was high, the more was significant difference represented in the order of $25^{\circ}C$ group <$40^{\circ}C$ group <$70^{\circ}C$ group (p<0.039).

• Journal of Life Science
• /
• v.21 no.1
• /
• pp.1-8
• /
• 2011

The purpose of this study was to investigate whether 12-weeks of movement training would increase the psoas major cross-sectional area (CSA) in senior men and women. Fifty eight men and women aged 65 to 80 years old ($69.6{\pm}3.7$, 30 male, 28 female) were divided into a control (n=19) and exercise group (n=39). Subjects were assessed before and after the training program for stature, body mass, and magnetic resonance imaging of the psoas major and the quadriceps muscle. The experimental group performed exercises using machines designed to improve the movement of the hip at a frequency of twice every week, with a total of 23 trainings in 12-weeks. Magnetic resonance images of both thighs and the abdomen and psoas major were obtained, aimed at 50% of the length of the greater trochanter and the lower edge of the femur and between the fourth (L4) and fifth (L5) lumbars. A 9.4% increase in the psoas major CSA in the training group was observed. In the male and female breakdown, a 11.5% and 8.4% change was observed in males and females, respectively. In the quadriceps, there was no significant statistical improvement in either males or females. Furthermore, in the control group, there was no significant change seen in either the psoas major or the quadriceps. As a result of conducting training that enables upkeep of posture and smooth linkage of the lumbar spine, the pelvis and thighbone, the psoas major CSA of older adults were improved in a short period of time. For this reason, the possibility of improving the psoas CSA, which decreases remarkably with increased age, by improving the linkage of the body trunk is also suggested.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.35-48
• /
• 2014

According to the 2013 construction market outlook report, the liquidation of construction companies is expected to continue due to the ongoing residential construction recession. Bankruptcies of construction companies have a greater social impact compared to other industries. However, due to the different nature of the capital structure and debt-to-equity ratio, it is more difficult to forecast construction companies' bankruptcies than that of companies in other industries. The construction industry operates on greater leverage, with high debt-to-equity ratios, and project cash flow focused on the second half. The economic cycle greatly influences construction companies. Therefore, downturns tend to rapidly increase the bankruptcy rates of construction companies. High leverage, coupled with increased bankruptcy rates, could lead to greater burdens on banks providing loans to construction companies. Nevertheless, the bankruptcy prediction model concentrated mainly on financial institutions, with rare construction-specific studies. The bankruptcy prediction model based on corporate finance data has been studied for some time in various ways. However, the model is intended for all companies in general, and it may not be appropriate for forecasting bankruptcies of construction companies, who typically have high liquidity risks. The construction industry is capital-intensive, operates on long timelines with large-scale investment projects, and has comparatively longer payback periods than in other industries. With its unique capital structure, it can be difficult to apply a model used to judge the financial risk of companies in general to those in the construction industry. Diverse studies of bankruptcy forecasting models based on a company's financial statements have been conducted for many years. The subjects of the model, however, were general firms, and the models may not be proper for accurately forecasting companies with disproportionately large liquidity risks, such as construction companies. The construction industry is capital-intensive, requiring significant investments in long-term projects, therefore to realize returns from the investment. The unique capital structure means that the same criteria used for other industries cannot be applied to effectively evaluate financial risk for construction firms. Altman Z-score was first published in 1968, and is commonly used as a bankruptcy forecasting model. It forecasts the likelihood of a company going bankrupt by using a simple formula, classifying the results into three categories, and evaluating the corporate status as dangerous, moderate, or safe. When a company falls into the "dangerous" category, it has a high likelihood of bankruptcy within two years, while those in the "safe" category have a low likelihood of bankruptcy. For companies in the "moderate" category, it is difficult to forecast the risk. Many of the construction firm cases in this study fell in the "moderate" category, which made it difficult to forecast their risk. Along with the development of machine learning using computers, recent studies of corporate bankruptcy forecasting have used this technology. Pattern recognition, a representative application area in machine learning, is applied to forecasting corporate bankruptcy, with patterns analyzed based on a company's financial information, and then judged as to whether the pattern belongs to the bankruptcy risk group or the safe group. The representative machine learning models previously used in bankruptcy forecasting are Artificial Neural Networks, Adaptive Boosting (AdaBoost) and, the Support Vector Machine (SVM). There are also many hybrid studies combining these models. Existing studies using the traditional Z-Score technique or bankruptcy prediction using machine learning focus on companies in non-specific industries. Therefore, the industry-specific characteristics of companies are not considered. In this paper, we confirm that adaptive boosting (AdaBoost) is the most appropriate forecasting model for construction companies by based on company size. We classified construction companies into three groups - large, medium, and small based on the company's capital. We analyzed the predictive ability of AdaBoost for each group of companies. The experimental results showed that AdaBoost has more predictive ability than the other models, especially for the group of large companies with capital of more than 50 billion won.

• Radiation Oncology Journal
• /
• v.23 no.2
• /
• pp.61-70
• /
• 2005

Purpose: Uterine cervix cancer is one of the most prevalent women cancer in Korea. We analysed published papers in Korea with comparing Patterns of Care Study (PCS) articles of United States and Japan for the purpose of developing and processing Korean PCS. Materials and Methods: We searched PCS related foreign-produced papers in the PCS homepage (212 articles and abstracts) and from the Pub Med to find Structure and Process of the PCS. To compare their study with Korean papers, we used the internet site 'Korean Pub Med' to search 99 articles regarding uterine cervix cancer and radiation therapy. We analysed Korean paper by comparing them with selected PCS papers regarding Structure, Process and Outcome and compared their items between the period of before 1980's and 1990's. Results: Evaluable papers were 28 from United States, 10 from the Japan and 73 from the Korea which treated cervix PCS items. PCS papers for United States and Japan commonly stratified into $3\~4$ categories on the bases of the scales characteristics of the facilities, numbers of the patients, doctors, Researchers restricted eligible patients strictly. For the process of the study, they analysed factors regarding pretreatment staging in chronological order, treatment related factors, factors in addition to FIGO staging and treatment machine. Papers in United States dealt with racial characteristics, socioeconomic characteristics of the patients, tumor size (6), and bilaterality of parametrial or pelvic side wail invasion (5), whereas papers from Japan treated of the tumor markers. The common trend in the process of staging work-up was decreased use of lymphangiogram, barium enema and increased use of CT and MRI over the times. The recent subject from the Korean papers dealt with concurrent chemoradiotherapy (9 papers), treatment duration (4), tumor markers (B) and unconventional fractionation. Conclusion: By comparing papers among 3 nations, we collected items for Korean uterine cervix cancer PCS. By consensus meeting and close communication, survey items for cervix cancer PCS were developed to measure structure, process and outcome of the radiation treatment of the cervix cancer. Subsequent future research will focus on the use of brachytherapy and its impact on outcome including complications. These finding and future PCS studies will direct the development of educational programs aimed at correcting identified deficits in care.

• Journal of Nutrition and Health
• /
• v.50 no.4
• /
• pp.402-414
• /
• 2017

Purpose: The purpose of the study was to evaluate the status of safety accidents and importance-performance analysis (IPA) between regular and non-regular employees in industry foodservices. Methods: The participants were regular employees (n = 119) and non-regular employees (n = 163) in industry foodservices in the Jeonbuk area. Demographic characteristics, status of safety accidents, safety education, and importance and performance status were assessed using a self-administered questionnaire. Results: Approximately 66.4% of regular employees and 53.4% of non-regular employees experienced safety accidents (p < 0.05). Types of safety accidents of regular and non-regular employees were mostly burns, and causes were mostly from their own negligence. Approximately 98.3% of regular employees and 95.1% of non-regular employees experienced safety education. Approximately 88.9% of regular employees and 96.8% of non-regular employees received safety education from dietitians. Approximately 41.9% of regular employees and 50.0% of non-regular employees had difficulty applying the contents of safety education due to lack of time during work. As a result of IPA, regular and non-regular employees were aware of the importance of the following and performed them well: 'Clean the floor of the work place', 'Arrange in the work area', 'Wear safety shoes', 'Check for heater cord', and 'Safety cooking when using oil'. On the other hand, they were not aware of the importance of the following and performed them insufficiently: 'Check for the MSDS', 'Aware of chemical signs', 'Wear protection gloves etc.', 'Do stretching exercise', and 'Using ancillary tools'. Conclusion: Therefore, it is necessary to improve the consciousness of dietitians for effective application of safety education contents, development of contents, especially MSDS, and related things.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.71-90
• /
• 2020

Recently, the global insurance industry is rapidly developing digital transformation through the use of artificial intelligence technologies such as machine learning, natural language processing, and deep learning. As a result, more and more foreign insurers have achieved the success of artificial intelligence technology-based InsurTech and platform business, and Ping An Insurance Group Ltd., China's largest private company, is leading China's global fourth industrial revolution with remarkable achievements in InsurTech and Digital Platform as a result of its constant innovation, using 'finance and technology' and 'finance and ecosystem' as keywords for companies. In response, this study analyzed the InsurTech and platform business activities of Ping An Insurance Group Ltd. through the ser-M analysis model to provide strategic implications for revitalizing AI technology-based businesses of domestic insurers. The ser-M analysis model has been studied so that the vision and leadership of the CEO, the historical environment of the enterprise, the utilization of various resources, and the unique mechanism relationships can be interpreted in an integrated manner as a frame that can be interpreted in terms of the subject, environment, resource and mechanism. As a result of the case analysis, Ping An Insurance Group Ltd. has achieved cost reduction and customer service development by digitally innovating its entire business area such as sales, underwriting, claims, and loan service by utilizing core artificial intelligence technologies such as facial, voice, and facial expression recognition. In addition, "online data in China" and "the vast offline data and insights accumulated by the company" were combined with new technologies such as artificial intelligence and big data analysis to build a digital platform that integrates financial services and digital service businesses. Ping An Insurance Group Ltd. challenged constant innovation, and as of 2019, sales reached $155 billion, ranking seventh among all companies in the Global 2000 rankings selected by Forbes Magazine. Analyzing the background of the success of Ping An Insurance Group Ltd. from the perspective of ser-M, founder Mammingz quickly captured the development of digital technology, market competition and changes in population structure in the era of the fourth industrial revolution, and established a new vision and displayed an agile leadership of digital technology-focused. Based on the strong leadership led by the founder in response to environmental changes, the company has successfully led InsurTech and Platform Business through innovation of internal resources such as investment in artificial intelligence technology, securing excellent professionals, and strengthening big data capabilities, combining external absorption capabilities, and strategic alliances among various industries. Through this success story analysis of Ping An Insurance Group Ltd., the following implications can be given to domestic insurance companies that are preparing for digital transformation. First, CEOs of domestic companies also need to recognize the paradigm shift in industry due to the change in digital technology and quickly arm themselves with digital technology-oriented leadership to spearhead the digital transformation of enterprises. Second, the Korean government should urgently overhaul related laws and systems to further promote the use of data between different industries and provide drastic support such as deregulation, tax benefits and platform provision to help the domestic insurance industry secure global competitiveness. Third, Korean companies also need to make bolder investments in the development of artificial intelligence technology so that systematic securing of internal and external data, training of technical personnel, and patent applications can be expanded, and digital platforms should be quickly established so that diverse customer experiences can be integrated through learned artificial intelligence technology. Finally, since there may be limitations to generalization through a single case of an overseas insurance company, I hope that in the future, more extensive research will be conducted on various management strategies related to artificial intelligence technology by analyzing cases of multiple industries or multiple companies or conducting empirical research.