• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Information Systems Review
• /
• v.15 no.2
• /
• pp.1-19
• /
• 2013

Smart working sparked by iPhone3 opens a revolution in smart ways of working at any time, regardless of location and environment. Also, It provide real-time information processing and analysis, rapid decision-making and the productivity of businesses, including through the timely response and the opportunity to increase the efficiency. As a result, every company are developing mobile information systems. But company data is accessed from the outside, it has problems to solve like security, hacking and information leakage. Also, Mobile devices such as smart phones belonging to the privately-owned asset can't be always controlled to archive company security policy. In the meantime, public smart phones owned by company was always applied security policy. But it can't not apply to privately-owned smart phones. Thus, this paper is focused to archive company security policy, but also enable the individual's free to use of smart phones when we use mobile information systems. So, when we use smart phone as individual purpose, the normal operation of all smart phone functions. But, when we use smart phone as company purpose like mobile information systems, the smart phone functions are blocked like screen capture, Wi-Fi, camera to protect company data. In this study, we suggest the design and implementation of real time control and management of mobile device using MDM(Mobile Device Management) solution. As a result, we can archive company security policy and individual using of smart phone and it is the optimal solution in the BYOD(Bring Your Own Device) era.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.1
• /
• pp.9-16
• /
• 2018

Landscape architecture is an indispensable professional service in building sustainable land and urban environments. The landscape architecture industry is closely related to the promotion of the health and welfare of the people, urban revitalization and residential environment improvement as well as job creation. Despite various public interest values of landscape architecture, the growth engine of the landscape architecture industry, which is supposed to improve the quality of landscape services, has stagnated. In 2015, the Landscape Architecture Promotion Act was enacted to provide a landscape architectural promotion facility and complex system to support revitalization through the integration of the landscape architecture industry. The purpose of this study is to suggest an improvement plan to enhance the effectiveness of the landscape architectural promotion facility and complex system. The results of the analysis are as follows: First, workers and experts in landscape architecture recognized the need for policies and projects to promote the landscape architecture industry. Second, the industrial types suitable for the landscape architectural promotion facility were landscape design, landscape maintenance and management, and landscape construction industry. Meanwhile the industrial types suitable for a landscape architectural promotion complex were landscape trees and landscape facilities production and distribution. Third, the expected effect of the designation of the landscape architectural facility was 'the increase of the business opportunity through the expansion of the network'. On the other hand, that of the landscape architectural promotion complex was 'the activation of various information sharing'. Fourth, 'the size of the local government landscape architecture industry and the capacity to cultivate' was the most important among the designation criteria of the landscape architectural promotion facility. As for that of the landscape architectural promotion complex, the 'feasibility of promotion plan' was the most crucial. Fifth, 'tax benefit and deductible exemption' was considered as a necessary support method for the activation of the landscape architectural promotion facility, and 'maintenance and management fee support' was recognized in the case of the landscape architectural promotion complex.

• Journal of the Korean Institute of Gas
• /
• v.22 no.5
• /
• pp.53-61
• /
• 2018

Low-salinity water based polymerflooding (LSPF) is one of promising enhanced oil recovery (EOR) method that has the synergetic effect of combining polymer injection method and low-salinity water injection method. In order to maximize EOR efficiency, it is essential to design low-salinity water appropriately considering the properties of polymer. In this aspect, the main purpose of this study is to investigate the effect of pH and $SO_4{^{2-}}$ ion which one of PDI (Potential Determining Ion) on oil production when applying LSPF to carbonate oil reservoir. First, the stability and adsorption of polymer molecule were analyzed in different pH of injection water and $SO_4{^{2-}}$ concentration in injection water. As a result, regardless of pH and $SO_4{^{2-}}$ concentration, when $SO_4{^{2-}}$ ion was contained in injection water, the stability of polymer solution was obtained. However, from the result of polymer retention analysis, in neutral state of injection water, since $SO_4{^{2-}}$ interfered the adsorption of polymer, the adsorption thickness of polymer was thinner as $SO_4{^{2-}}$ concentration was higher. On the other hand, when injection water was acidic as pH 4, the amount of polymer adsorption increased with the injection of polymer solution, so the mobility of polymer solution was greatly lowered. From the results of wettability alteration due to low-salinity water effect, in the case of neutral injection water injected, as $SO_4{^{2-}}$ concentration was increased, more oil which attached on rock surface was detached, altering wettability from oil-wet to water-wet. On the other hand, in acidic condition, due to complex effect of rock dissolution and polymer adsorption, wettability of the entire core system was less altered relatively to neutral condition. Therefore, it was evaluated that better EOR efficiency was obtained when injecting low-salinity water based polymer solution containing high concentration of $SO_4{^{2-}}$ with neutral condition, enhancing the oil production up to 12.3% compared to low-salinity water injection method.

• Journal of Korean Academy of Nursing
• /
• v.21 no.2
• /
• pp.129-149
• /
• 1991

Circadian rhythm is entrained in the 24-hour time interval by periodic factors in the environment, known as zeitgeber. But most rotating work schedules are outside the range of the entrainment of the pacemaker timing the human circadian sleep - wake cycle. It has been postulated that physiological and emotional disturbances occur in most human functions when the circadian rhythm is disturbed. So application of circadian principles to the design of shift schedules can aid in maintaining the temporal integrity of the circadian system and thereby minimize for the shift worker any detrimental consequences of circadian disruption. This study was a quasi-experimental study to test the effect of shift intervals for the clinical nurse on the circadian rhythm. Twenty nurses newly employed in general units of two hospitals were selected as an experimental group and twelve college nursing students as a control group. Both groups were selected according to an established criteria using a purposive sampling technique. Ten subjects were assigned to a weekly shift group and another ten to a biweekly shift group engaged in a semi -continuous shift schedule(sunday off) with a backward direction, that is, morning -evening - night shift. The control group worked a morning shift for 42 days. Oral temperature rhythm, waking tim, sleep - wake cycle, fatigue, and mental performance were measured during the experimental period. The data collection period was from April 30, 1990 to June 10, 1990. MANOVA, paired t-test, ANOVA, and Student Newman Keuls method were used for statistical analysis. The results are summarized as follows. 1. Phase delay in the acrophase of temperature rhythm was shown according to the backward rotating shift. A complete adaptation to work on the night shift was achieved between the sixth and ninth day of the night shift. 2. There was no difference in either waking time or sleep- wake cycle according to the duration of the working day for every shift group. Significant difference was found in the waking time and the sleep -wake cycle for subjects on the morning, evening, and night shift in both of the shift groups(weekly shift group : λ＝0.121, p＜0.01, λ＝0.112, p＜0.01, biweekly shift group : λ＝0.116, p＜0.01, λ＝0.084, p＜0.01). 3. There was no difference in fatigue between the first working day and the last working day for the control group and for the biweekly shift group. In the weekly shift group, physical fatigue was significantly different for the first day and the sixth day of the night shift(t＝-2.28, p＜0.05). Physical fatigue and total fatigue on the first day of the night shift showed a significant difference among the control group, the weekly shift group, and the biweekly shift group(F＝5.79, p＜0.01, F＝4.56, p＜0.05). There was a significant difference between the shift groups and the control group(p＜0.05), Physical fatigue, neurosensory fatigue and total fatigue on the last day of the night shift showed a significant difference among the control group, the weekly shift group, and the biweekly shift group(F＝12.65, p＜0.01, F＝7.77, p＜0.01, F＝9.68, p＜0.01). There was a significant difference between the shift groups and the control group(p＜0.05). 4. No difference in mental performance was seen between the first day and the last day of work in each case. An arithmatic test on the first day of the night shift revealed a significant difference among the control group, the weekly shift group, and the biweekly shift group(F＝3.79, p＜0.05). There was a significant difference between the shift groups and the control group(p＜0.05) . The digital symbol substitution test and the arithmetic test on the last day of the night shift showed a significant difference among the control group, the weekly shift group, and the biweekly shift group(F＝3.68, p＜0.05, F＝5.55, p＜0.01), and both showed a significant difference between the shift groups and the control group(p＜0.05). Accordingly, this study showed that during night duty, the waking time, sleep- wake cycle, and fatigue increased and mental performance decreased compared with morning and evening duty. It was also found that the weekly shift group had a higher fatigue score on the sixth day of night duty as compared to the -first day, but the waking time, sleep- wake cycle, and mental performance revealed no difference for the duration of the night duty or between shift groups, and complete adaptation of temperature rhythm was achieved between the sixth and ninth day of night duty. It is possible to conclude from these results that for intermediate circadian type in a healthy young woman, a biweekly shift system is more compatible with the circadian timing system than weekly shift system.

• Journal of Food Hygiene and Safety
• /
• v.30 no.1
• /
• pp.43-50
• /
• 2015

In this study, single PCR and multiplex PCR tests were examined for identification of four types of squid species (giant squid, cuttlefish, octopus, beka squid) purchased from fish market as well as aquatic processed products in Busan. To design the specific primers against each species, the nucleotide sequences of the mitochondrial 16s rRNA gene of Architeuthis dux, Todarodes pacificus, Enteroctopus dofleini, Enteroctopus megalocyathus, Uroteuthis chinensis, Uroteuthis duvauceli, Uroteuthis edulis groups were analyzed for the identification of each species registered in the GeneBank (www.ncbi.nlm.nih.gov) and have been used for comparative analysis. In order to obtain the size variation of amplified fragments on multiplex PCR, we designed KOJ-F, OJ-F, OCT-F, HAN-F, ALLR primers for each species. The optimal PCR conditions and primers were selected for four types of squid species to determine target base sequences in its PCR products. In the case of single PCR, giant squid was only amplified by KOJ-F/ALLR primer; cuttlefish was only amplified by OJ-F/ALLR primer; octopus was only amplified by OCT-F/ALLR primer; and beka squid was only amplified by HAN-F/ALLR primer. For multiplex PCR, the mixture of four kinds of genomic DNA (giant squid, cuttlefish, octopus, beka squid) been prepared as a template and used together with the mixture of KOJ-F/OJ-F/OCT-F/HAN-F/ALLR primers in the reaction. By the multiplex PCR, it is confirmed that four samples are correspond to multiple simultaneous amplicon. Finally, we validated the established methods of multiplex PCR in the aquatic processed products. Although the mitochondrial 16s rRNA primers used in this study was useful as a marker for detection of each species among them, the study indicated that the established multiplex PCR method can be more useful tool for monitoring the processed products.

• Journal of Distribution Science
• /
• v.15 no.5
• /
• pp.75-83
• /
• 2017

Purpose - With the rise of the fourth industrial revolution, it has converged with the existing industrial revolution to give shape to increased accessibility of knowledge and information. As a result, it has become easier for scholars to actively persue and compile research in various fields. This current study aims to focus and assess the current standing of KODISA: the Journal of Distribution Science (JDS), International Journal of Industrial Distribution & Business(IJIDB), the East Asian Journal of Business Management (EAJBM), the Journal of Asian Finance, Economics and Business (JAFEB) in a rapidly evolving era. Novel strategies for creating the future vision of KODISA 2020 will also be examined. Research design, data, and methodology - The current research will analyze published journals of KODISA in order to offer a vision for the KODISA 2020 future. In part 1, this paper will observe the current address of the KODISA journal and its overview of past achievements. Next, part 2 will discuss the activities that will be needed for journals of KODISA, JDS, IJIDB, EAJBM, JAFEB to branch out internationally and significant journals will be statistically analyzed in part 3. The last part 4 will offer strategies for the continued growth of KODISA and visions for KODISA 2020. Results - Among the KODISA publications, IJIDB was second, JDS was 23rd (in economic publications of 54 journals), and EAJBM was 22nd (out of 79 publications in management field journals). This shows the high quality of the KODISA publication journals. According to 2016 publication analysis, JDS, IJIDB, etc. each had 157 publications, 15 publications, 16 publications, and 28 publications. In the case of JDS, it showed an increase of 14% compared to last year. Additionally, JAFEB showed a significant increase of 68%. This shows that compared to other journals, it had a higher rate of paper submission. IJIDB and EAJBM did not show any significant increases. In JDS, it showed many studies related to the distribution, management of distribution, and consumer behavior. In order to increase the status of the KODISA journal to a SCI status, many more international conferences will open to increase its international recognition levels. Second, the systematic functions of the journal will be developed further to increase its stability. Third, future graduate schools will open to foster future potential leaders in this field and build a platform for innovators and leaders. Conclusions - In KODISA, JDS was first published in 1999, and has been registered in SCOPUS February 2017. Other sister publications within the KODISA are preparing for SCOPUS registration as well. KODISA journals will prepare to be an innovative journal for 2020 and the future beyond.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.6
• /
• pp.24-36
• /
• 2019

This study shows that the role of residents in landscape management is becoming increasingly important. The purpose of this study is to suggest elements that can continue the operation of landscape agreements and directions for promoting them. Therefore, 1)the operational elements considering the sustainability of the landscape agreements were proposed by way of literature research, expert interviews, and surveys. 2)The sustainable operation of elements of the landscape agreement were applied and best practices were developed through interviews with participants and literature analysis. 3)The final plan operational elements considering the sustainability of the landscape agreements and the directions for implementation were presented. As for the results, it was first presented that the elements of continuous operation of the landscape agreement, consisted of 3 major categories, 10 subcategories, and 25 details. These include resident awareness, practical applicability, effectiveness of administrative means, securing the budget, maintenance, public relations, expert support, dedicated support organization, sustainability of participation, and resident participation and communication methods. It is a detailed list of items that should be considered in the preparation phase, maintenance phase, and conclusion phase. Second, it suggested the direction for the sustainable operation of the landscape agreements be highly backed by the residents, and after reaching consensus on a landscape agreement, it is necessary that the agreement is based on contents that the residents can execute themselves. In addition, it was found that there is a need for a system to prepare the basis for securing the budget for the continuity of work, preparation of the landscape agreements, and consultation and activity costs during the maintenance phase. In addition, continuous exchanges and capacity building among residents have signed landscape agreements, and step-by-step support from experts in accordance with the level of involvement of residents is necessary. Third, even if a landscape agreement is concluded in connection with public projects, it is understood that the residents have the capacity to participate and can continue to support the administration and experts to enable the continued operation of the landscape agreement.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.4
• /
• pp.347-365
• /
• 2020

In order to resolve traffic problems in urban areas and to increase the area of green spaces, tunnels in downtown areas are being increased. Additionally, the application of large port smoke extraction ventilation systems is increasing as a countermeasure to smoke extraction ventilation for tunnels with high potential for traffic congestion. It is known that the smoke extraction performance of the large port smoke extraction system is influenced not only by the amount of the extraction flow rate, but also by various factors such as the shape of the extraction port (damper) and the extraction air velocity through a damper. Therefore, in this study, the design standards and installation status of each country were investigated. When the extraction air flow rate was the same, the smoke extraction performance according to the size of the damper was numerically simulated in terms of smoke propagation distance, compared and evaluated, and the following results were obtained. As the cross-sectional area of the smoke damper increases, the extraction flow rate is concentrated in the damper close to the extraction fan, and the smoke extraction rate of the damper in downstream decreases, thereby increasing the smoke propagation distance on the downstream side. In order to prevent such a phenomenon, it is necessary to reduce the cross-sectional area of the smoke damper and increase the velocity of passing air through the damper so that the pressure loss passing through the damper increases, thereby reducing the non-uniformity of smoke extraction flow rate in the extraction section. In this analysis, it was found that when the interval distance of the extraction damper was 50 m, the air velocity passing through damper was 4.4 m/s or more, and when the interval distance of the extraction dampers was 100 m, the air velocity passing through damper was greater than 4.84 m/s, it was found to be advantageous to ensure smoke extraction performance.