• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.33-42
• /
• 2021

As smartphone-based tourism platforms have become active, policy establishment and service enhancement using review data are being made in various fields. In the case of the preceding studies using tourism review data, most of the studies centered on domestic tourists were conducted, and in the case of foreign tourist studies, studies were conducted only on data collected in some languages and text mining techniques. In this study, 3,515 review data written by foreigners were collected by designating the "Daegu attractions" keyword through the online review site. And LDA-based topic modeling was performed to derive tourism topics. The spatial approach through global and local spatial autocorrelation analysis for each topic can be said to be different from previous studies. As a result of the analysis, it was confirmed that there is a global spatial autocorrelation, and that tourist destinations mainly visited by foreigners are concentrated locally. In addition, hot spots have been drawn around Jung-gu in most of the topics. Based on the analysis results, it is expected to be used as a basic research for spatial analysis based on local government foreign tourism policy establishment and topic modeling. And The limitations of this study were also presented.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.1-9
• /
• 2021

In this paper, we propose a training algorithm of support vector machine (SVM) with a sensitive variable. Although machine learning models enable automatic decision making in the real world applications, regulations prohibit sensitive information from being used to protect privacy. In particular, the privacy protection of the legally protected attributes such as race, gender, and disability is compulsory. We present an efficient least square SVM (LSSVM) training algorithm using a fully homomorphic encryption (FHE) to protect a partial sensitive attribute. Our framework posits that data owner has both non-sensitive attributes and a sensitive attribute while machine learning service provider (MLSP) can get non-sensitive attributes and an encrypted sensitive attribute. As a result, data owner can obtain the encrypted model parameters without exposing their sensitive information to MLSP. In the inference phase, both non-sensitive attributes and a sensitive attribute are encrypted, and all computations should be conducted on encrypted domain. Through the experiments on real data, we identify that our proposed method enables to implement privacy-preserving sensitive LSSVM with FHE that has comparable performance with the original LSSVM algorithm. In addition, we demonstrate that the efficient sensitive LSSVM with FHE significantly improves the computational cost with a small degradation of performance.

• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.59-66
• /
• 2021

As the demand for elderly care service has been on rise due to the increasing of the aging population, the role of visiting caregivers becomes increasingly important. In this context, this study aims to examine whether there are moderating effects of social support and self-efficacy on the relationship between resilience of visiting caregivers and their burnouts. The hierarchical regression analysis was used for statistical analysis. The findings from the study are as follow. First, resilience has a negative effect on burnout. As the resilience increases, the burnout decreases. Second, social support has moderating effects on the relationship between a resilience sub-variable(positivity) and burnout. Third, self-efficacy has a moderating effect on the relationship between a resilience sub-variable(self-regulation) and burnout. The findings of the study suggest that nursing facilities pay attention to psychological characteristics of visiting caregivers as well as their job characteristics in designing burnout prevention programs for them.

• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.77-88
• /
• 2021

Cloud computing is getting a lot of attention by many people and businesses due to IT environmental changes such as the proliferation of smart devices, the increase of digital data, and the cost of IT resources. More individuals use personal cloud computing services for storing and managing information and data. Therefore, this study proposed determinants that are expected to have an influence on evaluating the value of cloud computing based on the value-based adoption model, examining the relationship between the continuous use intention of cloud computing. Results of the study show that usefulness, convenience of information access, extensibility had a positive impact on perceived value while privacy concerns and costs had a negative impact on perceived value. In addition, perceived value was found to have a significant effect on the intention to continue use of cloud computing. Finally, trust was found to have a significant effect on the perceived value and the intention to continue use of cloud computing. The findings are expected to provide useful information for understanding the factors that individual users consider important in the steadily growing cloud computing market.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.231-238
• /
• 2021

SNS data can catch the user's thoughts and actions. And the trend of the search portal is a representative service that can observe the interests of users and their changes. In this paper, the relationship was analyzed by comparing statistics on narcotics incidents and the degree of exposure to narcotics related words in tweets of SNS and in the trends of search portal. It was confirmed that the trend of SNS and search portal trends was the same in the statistics of the prosecution office with a certain time difference.In addition, cluster analysis was performed to understand the meaning of tweets in which narcotics related words were mentioned. In the 50,000 tweets collected in January 2020, it was possible to find meaning related to the sale of actual drugs. Therefore, through SNS monitoring alone it is possible to monitor narcotics-related incidents and to find specific sales or purchase-related information, and this can be used in the investigation process. In the future, it is expected that crime monitoring and prediction systems can be proposed as related crime analysis may be possible not only with text but also images.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.195-204
• /
• 2020

The purpose of this study is to look for the relationship between export weight and control volume, inland cargo, export cargo transport, ship departure. The analysis period were used for a total of 113 monthly data from January 2011 to May 2020. Data were retrieved from the Korean Statistical Information Service of the Statistics Korea. The data used in this study were performed numerical analysis, index analysis and model analysis using the rate of change from the same month of the previous year. In the trend of the increase rate, the amount of control has plummeted from 150% to 60% due to the influence of Corona 19 in the beginning of 2020. At the same time, export weight and export cargo transport also decreased. As a result of the analysis, export weight showed relatively high synchronization with export cargo transport and control volume. On the other hand, export weight and inland cargo showed relatively low synchronization. Export weight is expected to continue in 2020 after the fluctuation rate began to decrease after 2019. If we can find the point of rebound in control volume or export cargo transport in the future, we can predict the point of increase in export weight. We expect to see an increase in export weight as soon as possible.

• International Journal of Advanced Culture Technology
• /
• v.9 no.1
• /
• pp.16-21
• /
• 2021

As the average age of national veterans has increased from 69 years old(2011) to 71 years old(since 2015) over the past five years, the overall medical service cost of veterans has increased by about 20%. The main cause of this phenomenon is 'ultra-aging', which accounts for 67% of veterans, while the proportion of health insurance patients aged 70 or older is 9%. Therefore, it is judged that the analysis of the trend of use of medical services at veterans hospitals in each region that is in charge of severe medical services of national veterans can serve as an opportunity to seek countermeasures for the severe medical system of national veterans. First of all, based on the details of major medical expenses (hospitalization, outpatient, pharmaceutical expenses) by region for the last 10 years(2010-2019), data significance was performed through a chi-square test, and the Central Veterans Hospital and Non-Central Veterans Hospital using EXCEL. 'Expected frequency' was calculated by year. By applying the CHITEST(observation frequency, expected frequency) function again, the p-value(p<0.05) was calculated, and the profit bias of each region's veterans hospital could be determined. The specific research method is for the last 10 years(2010-2019) for state-sponsored patients_outpatient treatment income, state-sponsored patients_hospitalization income, exempt patients_outpatients at the Central Veterans Hospital, Busan Veterans Hospital, Gwangju Veterans Hospital, Daegu Veterans Hospital, and Daejeon Veterans Hospital. A one-way analysis of variance was conducted to verify the significance of the difference between group averages on the status of 5 medical revenues of veterans hospitals in each of the 5 regions, including medical treatment income, reduced patients_hospitalization income, and reduced patients_medicine expenses. It was found to be significant(p<0.05) at all levels, including region and type. Finally, the bias in the profit structure of regional veterans hospitals was the highest in 2017(p=0.0004) and the lowest in 2013(p=0.0349). In addition, in the profit structure of the Veterans Hospital, the year in which the'regional' variable worked the most was 2019, and the year with the least affected was 2010. The order of the former is Jungang(=31,674,713), Busan(=12,314,614), Gwangju(=11,957,038), Daegu(=10,168,015), and Daejeon(=6,991,034), and the order of the latter is Jungang(=57,868,791), and Busan(=19,183,194). Gwangju(=17,904,712), Daegu(=15,656,034), and Daejeon(=14,377,395). In conclusion, the profit bias of veterans hospitals repeatedly raced the lowest(p=0.01986) and highest(p=0.03499) for the past five years(2010-2014) year by year, with the 'regional' variable being the most in the veterans hospital's profit structure It was identified as a major influence factor. On the other hand, for the last 5 years (2015-2019), the influence factors of the'regional' variable every year were in 2015(p=0.02015), 2016(p=0.01741), 2017(p=0.00045), and 2018(p=0.00394). in 2019(p=0.00227), a significant difference was confirmed at a very low level.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.87-95
• /
• 2020

The Incheon airport is a gateway to and from the Republic of Korea and has a great influence on the image of the country. Therefore, it is necessary to predict the number of airport passengers in the long term in order to maintain the quality of service at the airport. In this study, we compared the predictive performance of various time series models to predict the air passenger demand at Incheon Airport. From 2002 to 2019, passenger data include trend and seasonality. We considered the naive method, decomposition method, exponential smoothing method, SARIMA, PROPHET. In order to compare the capacity and number of passengers at Incheon Airport in the future, the short-term, mid-term, and long-term was forecasted by time series models. For the short-term forecast, the exponential smoothing model, which weighted the recent data, was excellent, and the number of annual users in 2020 will be about 73.5 million. For the medium-term forecast, the SARIMA model considering stationarity was excellent, and the annual number of air passengers in 2022 will be around 79.8 million. The PROPHET model was excellent for long-term prediction and the annual number of passengers is expected to be about 99.0 million in 2024.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1331-1340
• /
• 2020

Object detection in maritime means that the captain detects floating objects that has a risk of colliding with the ship using the computer automatically and as accurately as human eyes. In conventional ships, the presence and distance of objects are determined through radar waves. However, it cannot identify the shape and type. In contrast, with the development of AI, cameras help accurately identify obstacles on the sea route with excellent performance in detecting or recognizing objects. The computer must calculate high-volume pixels to analyze digital images. However, the CPU is specialized for sequential processing; the processing speed is very slow, and smooth service support or security is not guaranteed. Accordingly, this study developed maritime object detection software and implemented it with FPGA to accelerate the processing of large-scale computations. Additionally, the system implementation was improved through embedded boards and FPGA interface, achieving 30 times faster performance than the existing algorithm and a three-times faster entire system.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.545-552
• /
• 2021

Under the Act amended on August 4, 2011, a special fire-fighting investigation was conducted by the relevant person (owner, manager, oil refineries), and the responsibility was also given to the relevant person. Instead of directly entering all existing fire-fighting targets and investigating the maintenance and management status of fire-fighting facilities, the fire-fighting agency selects and visits some targets every year, checks the maintenance and management status of fire-fighting facilities, corrects them, and imposes fines, etc. Reasons for the introduction of the system were the establishment of a private autonomous correction system by strengthening the responsibility of officials, lack of firefighting professionals, possible corruption due to frequent public contact, and responsibility of fire agencies. However, many problems arose even after the introduction of a special fire investigation system. A special fire investigation, one of the fire safety systems, checks whether related public officials and especially fire officials are properly installed, maintained and managed in accordance with relevant laws. Special firefighting investigations were introduced as firefighting inspections at the time the firefighting law was enacted in 1958, and have undergone a revised process more than 30 times until recently. Firefighting Facility Installation, Maintenance and Safety Management Act", the existing firefighting inspection was changed to a special firefighting investigation and accepted. At the time of enactment of the Fire Service Act in 1958, a special firefighting investigation was introduced as a firefighting inspection, and until recently, more than 30 revisions have been made. In 2003, as the existing fire fighting system was divided into four laws, it was approved by changing the existing fire fighting inspection to a special fire fighting investigation in the "Fire Fighting Facility Installation, Maintenance and Safety Management Act".