• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.4
• /
• pp.405-412
• /
• 2019

SOLAS requires that ECDIS be installed on ships of more than 500 gross tonnage engaged in international navigation until the first inspection arriving after July 1, 2018. Several accidents related to the use of ECDIS have occurred with its installation as a new major navigation instrument. The 12 incident reports issued by MAIB, BSU, BEAmer, DMAIB, and DSB were analyzed, and the cause of accident was determined to be related to the operation of the navigator and the ECDIS system. The text was analyzed using the R-program to quantitatively analyze words related to the cause of the accident. We used text mining techniques such as Wordcloud, Wordnetwork and Wordweight to represent the importance of words according to their frequency of derivation. Wordcloud uses the N-gram model as a way of expressing the frequency of used words in cloud form. As a result of the uni-gram analysis of the N-gram model, ECDIS words were obtained the most, and the bi-gram analysis results showed that the word "Safety Contour" was used most frequently. Based on the bi-gram analysis, the causative words are classified into the officer and the ECDIS system, and the related words are represented by Wordnetwork. Finally, the related words with the of icer and the ECDIS system were composed of word corpus, and Wordweight was applied to analyze the change in corpus frequency by year. As a result of analyzing the tendency of corpus variation with the trend line graph, more recently, the corpus of the officer has decreased, and conversely, the corpus of the ECDIS system is gradually increasing.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.99-107
• /
• 2024

In an environment where computer-related technologies are rapidly changing, cyber threats continue to emerge as they are advanced and diversified along with new technologies. Therefore, in this study, we would like to collect security-related news articles, conduct LDA topic modeling, and examine trends. To that end, news articles from January 2020 to August 2023 were collected and major topics were derived through LDA analysis. After that, the flow by topic was grasped and the main origin was analyzed. The analysis results show that ransomware attacks in 2021 and hacking of virtual asset exchanges in 2023 are major issues in the recent security sector. This allows you to check trends in security issues and see what research should be focused on in the future. It is also expected to be able to recognize the latest threats and support appropriate response strategies, contributing to the development of effective security measures.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.1
• /
• pp.32-42
• /
• 2024

In this study, 1,474 effective patents were derived for quantitative analysis of five major countries, including Korea, China, Japan, the United States and Europe, for marine space policy simulator technology used as a support for integrated marine space management means, and domestic technology competitiveness and domestic and foreign technology trends were identified through annual and national patent application trends and word cloud analysis. This diagnosed the need for active policy support for research and development of marine space policy simulator technology at the government level and preparation through linkage strategies such as patent application consideration and standardization preoccupation for surrounding technologies to prepare for China-led market monopoly and preoccupation.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.22 no.1
• /
• pp.113-129
• /
• 2020

In this study we examined the topic analysis and correlation analysis by text mining to extract meaningful information or rules from the self introduction letter of freshman at Korea National College of Agriculture and Fisheries in 2020. The analysis items are described in items related to 'academic' and 'in-school activities' during high school. In the text mining results, the keywords of 'academic' items were 'study', 'thought', 'effort', 'problem', 'friend', and the key words of 'in-school activities' were 'activity', 'thought', 'friend', 'club', 'school' in order. As a result of the correlation analysis, the key words of 'thinking', 'studying', 'effort', and 'time' played a central role in the 'academic' item. And the key words of 'in-school activities' were 'thought', 'activity', 'school', 'time', and 'friend'. The results of frequency analysis and association analysis were visualized with word cloud and correlation graphs to make it easier to understand all the results. In the next study, TF-IDF(Term Frequency-Inverse Document Frequency) analysis using 'frequency of keywords' and 'reverse of document frequency' will be performed as a method of extracting key words from a large amount of documents.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.22 no.2
• /
• pp.99-114
• /
• 2020

In this study we examined the topic analysis and correlation analysis by text mining from the self introduction letter of freshman at Korea National College of Agriculture and Fisheries(KNCAF) in 2020. The analysis items of the 3rd question were and the 4th question were the motivation for applying to college, the academic plan and the career plan. The text mining to the 3rd question showed that the frequency of 'friends' was overwhelmingly high, followed by keywords such as 'thought', 'time', 'opinion', 'activity', and 'club'. In the 4th question, keyword frequency such as 'thought', 'agriculture', 'KNCAF', 'farm', 'father' was high. The result of association rules analysis for each question showed that the relationship with the highest support level, which means the frequency and importance of the rule, was the {friend} <=> {thought}, {thought} <=> {KNCAF}. The confidence level of a correlation between keywords was the highest in the rules of {teacher}=>{friend}, {agriculture, KNCAF}=>{thought}. Also the lift level that indicates the closeness of two words was the highest in the rules of {friend} <=> {teacher}, {knowledge} <=> {professional}. These keywords are found to play a very important roles in analyzing betweenness centrality and analyzing degree centrality between keywords. The results of frequency analysis and association analysis were visualized with word cloud and correlation graphs to make it easier to understand all the results.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.87-97
• /
• 2018

The traffic accident reports that are generated by the Traffic Broadcasting Networks(TBN) are unstructured data. It, however, has the value as some sort of real-time traffic information generated by the viewpoint of the drives and/or pedestrians that were on the roads, the time and spots, not the offender or the victim who caused the traffic accidents. However, the traffic accident reports, which are big data, were not applied to traffic accident analysis and traffic related research commonly. This study adopting text-mining technique was able to provide a clue for utilizing it for the impacts of traffic accidents. Seven years of traffic reports were grasped by this analysis. By analyzing the reports, it was possible to identify the road names, accident spot names, time, and to identify factors that have the greatest influence on other drivers due to traffic accidents. Authors plan to combine unstructured accident data with traffic reports for further study.

• Convergence Security Journal
• /
• v.15 no.4
• /
• pp.11-18
• /
• 2015

The new environments arrive such as ICT convergence, cloud computing, and big data, etc., how to take advanta ge of the existing software engineering technologies has become an important key. In addition, the importance of re quirement analysis for secure software and design phase has been shown in the IoT environment While the existing studies have focused on the utilization of the technique applied to IoT environment, the studies for enhancing analys is and design, the prerequisite steps for safely appling these techniques to the site, have been insufficient. So, we tr y to organize research trends based on software engineering and analyze their relationship in this paper. In detail, w e classify the research trends of software engineering to perform research trends meta-analysis, and analyze an ann ual development by years. The flow of the major research is identified by analyzing the correlation of the key word s. We propose the strategies for enhancing the utilization of software engineering techniques to develop high-quality software in the IoT environment.

• Knowledge Management Research
• /
• v.18 no.3
• /
• pp.81-99
• /
• 2017

This study is to compare the main subjects of domestic and foreign knowledge management research in terms of keywords and to clarify whether domestic knowledge management research reflects research trends in overseas knowledge management research. Specifically, we try to find out whether the central activities such as knowledge sharing, knowledge generation, and acquisition, which are knowledge management activities of knowledge management research, are being studied without bias. In order to analyze this, we analyzed the data of domestic and foreign knowledge management research for the last 5 years from 2012 to 2016. In Korea, the Knowledge Management Society of Korea collected 167 papers and 787 keywords, and collected 132 papers and 640 keywords from the Korea Society of Management Information Systems in order to distinguish the research areas. Overseas papers collected 315 papers and 1,746 keywords published by Emerald. Also, we collected 382 papers and 1,633 keywords in the Korean Management Review and collected 646 papers and 2,879 keywords in the Korean Business Education Review. Frequency analysis and network analysis of 1,642 papers and 7,685 keywords are summarized as follows. The Knowledge Management Society of Korea has focused on knowledge sharing, and in 2016, interest in knowledge transfer and knowledge search has shifted. The Journal of Knowledge Management, which is published by Emerald, has been a major concern for knowledge transfer and knowledge sharing. The research trends of the Korea Society of Management Information Systems to distinguish a clear identity of knowledge management research are focusing on smart area and mobile domain such as information security domain, cloud, smart phone, and smart work. In the Korea Society of Management Information Systems research, the main subject of knowledge sharing is also commonly found.

• Journal of Cadastre & Land InformatiX
• /
• v.49 no.2
• /
• pp.67-82
• /
• 2019

The purpose of this study is to analyze the issues and perceptions of smart cities. First, based on the big data analysis platform, big data analysis on smart cities were conducted to derive keywords by year, word cloud, and frequency of generation of smart city keywords by time. Second, trend and flow by area were analyzed by reclassifying major keywords by year based on meta-keywords. Third, emotional recognition flow for smart cities and major emotional keywords were derived. While U-City in the past is mostly centered on creating infrastructure for new towns, recent smart cities are focusing on sustainable urban construction led by citizens, according to the analysis. In addition, it was analyzed that while infrastructure, service, and technology were emphasized in the past, management and methodology were emphasized recently, and positive perception of smart cities was growing. The study could be used as basic data for the past, present and future of smart cities in Korea at a time when smart city services are being built across the country.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.845-854
• /
• 2016

Sentiment analysis or opinion mining is a technique of text mining employed to identify subjective information or opinions of an individual from documents in blogs, reviews, articles, or social networks. In the literature, only a problem of binary classification of ratings based on review texts in an online review. However, because there can be positive or negative reviews as well as neutral reviews, a multi-class classification will be more appropriate than the binary classification. To this end, we consider the multi-class classification of ratings based on review texts. In the preprocessing stage, we extract words related with ratings using chi-square statistic. Then the extracted words are used as input variables to multi-class classifiers such as support vector machines and proportional odds model to compare their predictive performances.