• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1716-1722
• /
• 2021

Recently, the capacity of video content delivery services has been increasing significantly. Therefore, the importance of user recommendation is increasing. In addition, these contents contain a variety of characteristics, making it difficult to express the characteristics of the content properly only with a few keywords(Elements used in the search, such as titles, tags, topics, words, etc.) specified by the user. Consequently, existing recommendation systems that use user-defined keywords have limitations that do not properly reflect the characteristics of objects. In this paper, we compare the efficiency of between a method using voice data-based subtitles and an image comparison method using keyframes of images in recommendation module of educational video service systems. Furthermore, we propose the types and environments of video content in which each analysis technique can be efficiently utilized through experimental results.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.125-133
• /
• 2016

In recent years, various crimes such as "random killing' crime continue to rise. Despite the government's crime prevention efforts and crime related researches, crime increases and a different approach is needed. Therefore, this study proposes the alternative for crime prevention by analyzing big data. To achieve this objective, this study was to perform visualization utilizing the histogram, the bubble chart and the hit map and association analysis. To analyze the relationship between crime and some variables, this study analyzed data of Seongnam city, Korea National Police Agency and etc. The results of analysis showed that CCTV will be to reduce the crime rate and security light is not significantly relevant. And the result showed that other types of crime focused by time of the day and day of the week and showed that an increase of the foreigners and crime increase are associated. This study presents a scheme for reducing the crime rate on the basis of this analysis result.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.229-238
• /
• 2019

Before the scholarship loan system was implemented at the Korea Scholarship Foundation, the government's role was strengthened by the direct lending of student funds to banks and other financial institutions. However, the low repayment performance of student loans has raised concerns over the future of student loans and the government's financial burden. Moreover, since student loans are repaid even after graduating from college to support low-income families, it is highly unlikely that the repayment rate of student loans will improve unless the employment rate and income level of the borrower improve. In this paper, the final visualization graph is presented of the repayment amount of the student loan through the collection, storage, processing and analysis phase in the Big Data-based system. This could be the basis for visually checking the amount of student loans to come up with various ways to reduce the burden on the current student loan system.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.13-20
• /
• 2022

This study is to develop a named entity recognition model specialized in criminal investigation domains using deep learning techniques. Through this study, we propose a system that can contribute to analysis of crime for prevention and investigation using data analysis techniques in the future by automatically extracting and categorizing crime-related information from text-based data such as criminal judgments and investigation documents. For this study, the criminal investigation domain text was collected and the required entity name was newly defined from the perspective of criminal analysis. In addition, the proposed model applying KoELECTRA, a pre-trained language model that has recently shown high performance in natural language processing, shows performance of micro average(referred to as micro avg) F1-score 98% and macro average(referred to as macro avg) F1-score 95% in 9 main categories of crime domain NER experiment data, and micro avg F1-score 98% and macro avg F1-score 62% in 56 sub categories. The proposed model is analyzed from the perspective of future improvement and utilization.

• Journal of The Korean Society of Integrative Medicine
• /
• v.11 no.1
• /
• pp.141-148
• /
• 2023

Purpose : This study examined the relationship between suicidal thoughts, hand grip strength, socioeconomic status, educational level, and disease occurrence. Methods : Korean national health and nutrition examination survey 2017 were used in this study. 5,449 were analysed. For comparison between groups, cross-tabulation analysis and mean comparison were performed. Logistic regression analysis were performed to analyze the influencing factors between grip strength and suicidal ideation. Results : Our results are consistent with the literature on the importance of socioeconomic status in health. The lower the level of education, the higher the suicidal thoughts. Being single or divorced was also significantly associated with suicidal ideation. Moreover, a lower income level was significantly associated with a higher suicide intention. Furthermore, older ages, lower educational levels, and lower income were significantly associated with a higher odds ratio of suicidal thoughts. Interestingly, suicidal thoughts were significantly lower among non-smokers. In contrast, suicide intention did not differ significantly according to gender, age, monthly drinking habit, aerobic physical activity, and disease occurrence. Suicidal thoughts decreased as grip strength increased and this was statistically significant. Socioeconomic status, disease occurrence, and handgrip strength level affected the security of an individual's livelihood and were significant risk factors for suicidal thoughts. These associations remained significant in multiple logistic regression even after controlling for all covariates. Conclusion : Future prevention intervention efforts to reduce suicide risks should consider handgrip strength. Studies to explore the possible proximal risk factors and mediators between handgrip strength and suicidal thoughts are also warranted.

• Advanced Industrial SCIence
• /
• v.2 no.2
• /
• pp.25-30
• /
• 2023

The purpose of this study is to empirically analyze the impact of corporate innovation activities on corporate innovation performance using data from companies participating in the smart farm project. A company's innovation activities were divided into planning capacity, R&D capacity, and commercialization capacity, and the impact of each innovation activity on the company's sales and patent creation was estimated. The moderating effect was also analyzed. Regression analysis was conducted as a research method, and as a result of the analysis, it was found that planning capacity, R&D capacity, and commercialization capacity related to innovation within a company have an impact on corporate performance creation. appeared to be In order to increase the business performance of technology commercialization, it was confirmed that planning and R&D capabilities as well as governmental technology policy support are needed.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.165-171
• /
• 2020

Most of the stock price prediction research using text mining uses news and SNS data. However, there is a weakness that it is difficult to get honest and vivid information about companies from them. This paper deals with the problem of the prediction for the direction of stock price by doing text mining the online company reviews of internal staff indicating employee satisfaction. The comparative analysis of the prediction models for the direction of stock price showed the prediction model, which adds internal employee reviews, has better performance than those that did not. This paper presents the convergence study using natural language processing in financial engineering. In the field of stock price prediction, This paper pursued a new methodology that used employee satisfaction. In practice, it is expected to provide useful information in the field of forecasting stock price direction.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.59-71
• /
• 2020

The paper reports on a systematic literature review results concerning the smart factory research in Korea. 144 papers were identified from the articles published in Korean journals listed in the Korean citation index by keyword search related to smart factory. Bibliometric analyses were conducted by way of co-occurrence and network analysis using the VOSViewer. Automation, intelligence, and bigdata were identifed as three critical clusters of research while, operating systems, international policy and cases, concept analysis as other three clusters of research. Internet of Things turned out to be a key technology of smart factory linking all of these areas. Servitization studies were small in numbers but seemed to have a lot of potential. Security researches seemed to be lacking connections with other areas of studies. Results of this study can be used as a milestone for identifying future research issues in smart factories.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.4
• /
• pp.247-258
• /
• 2017

Since 2016 when the regulations related to vehicle structure and device modification were drastically revised, the car tuning market has been growing rapidly. Particularly, many drivers are showing interest in changing the interior and exterior according to their preference, or improving the specifications of their cars by changing the engine and powertrain, among others. Also, as the initial engine settings such as horse power and torque of the vehicle are made for stable driving of the vehicle, it is possible to change the engine performance, via Engine Control Unit (ECU) mapping, to the driver's preference. However, traditionally, ECU mapping could be only performed by professional car engineers and the settings were also decided by them. Therefore, this study proposed a system that collects data related to the driver's driving habits for a certain period and sends them to a cloud server in order to analyze them and recommend ECU mapping values. The traditional mapping method only aimed to improve the car's performance and, therefore, if the changes were not compatible with the driver's driving habits, could cause problems such as incomplete combustion or low fuel efficiency. However, the proposed system allows drivers to set legally permitted ECU mapping based on analysis of their driving habits, and, therefore, different drivers can set it differently according to the vehicle specifications and driving habits. As a result, the system can optimize the car performance by improving output, fuel efficiency, etc. within the range that is legally permitted.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.125-130
• /
• 2017

Since field control equipment such as PLC has no function to log key event information in the log, it is difficult to analyze the accident. Therefore, it is necessary to secure information that can analyze when a cyber accident occurs by logging the main event information of the field control equipment such as PLC and IED. The protocol analyzer is required to analyze the field control device (the embedded device) communication protocol for event logging. However, the conventional analyzer, such as Wireshark is difficult to process the data identification and extraction of the large variety of protocols for event logging is difficult analysis of the payload data based and classification. In this paper, we developed a system for Big Data based on field control device communication protocol payload data extraction for event logging of large studies.