여단급 KCTC 훈련결과 빅데이터를 활용한 전투승리요인 분석 방법론 연구 : 보병대대 공격작전 분석을 중심으로

이민호 ( Minho Lee ),한정욱 ( Jungwook Han ),박진영 ( Jinyoung Park ),문호석 ( Hoseok Moon ) 국방대학교 안보문제연구소 2021 국방연구 Vol.64 No.4

본 연구에서는 여단급 과학화전투(Korea Combat Training Center, KCTC) 훈련결과 빅데이터를 이용하여 전투승리요인을 분석하기 위한 방법론을 제안하였고, 보병대대 공격작전 시 전투승리요인을 분석하는 과정을 제시하였다. KCTC 훈련결과 데이터 분석과 관련된 기존 연구들은 연구의 대상이 주로 대대급 KCTC이었고, 분석 데이터도 훈련결과의 일부만 이용하였으며, 군사전문가의 전술적 평가가 연구에 반영되지 못했다는 제한점이 있었다. 본 연구에서는 이러한 기존 연구의 제한점을 극복하기 위해서 여단급 KCTC훈련 실시 후 2년간의 모든 훈련결과 데이터를 분석대상으로 하였고, 군사전문가의 평가를 훈련결과 분석에 반영하는 방법을 제안하였다. 군사전문가의 평가에 대한 분석은 교리와 KCTC 사후검토자료를 이용하였고, 이러한 분석을 술(術)적분석이라고 하였다. 술적분석은 훈련결과에 대한 과학적 분석 전에 선행되도록 하였고, 술적분석과 과학적분석을 결합하여 전투승패결과에 영향을 주는 전투승리요인을 제시하였다. KCTC 훈련결과 빅데이터를 이용하여 다양한 제대와 작전형태에 따른 훈련결과를 분석하는 데, 본 연구에서 제안하는 방법론이 군사전문가의 통찰력과 데이터에 의한 과학적 분석을 융합하여 훈련결과를 평가하는데 활용될 수 있을 것이다. This study proposed a methodology to analyze combat victory factors using big data as a result of the Korea Combat Training Center (KCTC) training and presented the case as analyzing combat victory factors during infantry battalion offensive operations. Existing studies related to KCTC training result data analysis mainly focused on the battalion-level KCTC, and the analysis data also used only a part of the training results, and there was a limitation that the tactical evaluation of military experts could not be reflected in the study. In this study, in order to overcome the limitations of the existing studies, all the training results data of the two years of the brigade-level KCTC training were analyzed as the subject of analysis, and a method of reflecting the evaluation of military experts in the analysis of the training results was proposed. For the analysis of the evaluation of military experts, the doctrine and the KCTC after action review data were used, and this analysis was called a tactical analysis. The tactical analysis was preceded by the scientific analysis of the training results, and the battle victory factors that affect the outcome of the battle were presented by combining the tactical analysis and scientific analysis. The methodology proposed in this study can be used to evaluate the training results in which the insights of military experts and scientific analysis based on data are fused to analyze the training results according to various types of troops and operations using KCTC training results big data.

빅데이터 분석의 기술마케팅 활용에 관한 연구 : 잠재 수요기업 발굴을 중심으로

전채남,서일원 한국전략마케팅학회 2013 마케팅논집 Vol.21 No.2

최근 빅데이터에 대한 연구가 늘어나고 있지만 대부분 빅데이터의 개념, 동향, 기술 현황, 활용 가능성 등의 연구에 국한되어 있다. 본 연구는 빅데이터 연구를 확대하고 실용성을 높이기 위해 마케팅 분야의 빅데이터 활용을 연구 주제로 선정하였다. 빅데이터의 활용 분야로 기술마케팅을 선택한 것은 기술시장에서 마케팅의 필요성이 높아지고 특히 기술시장의 특성 때문에 잠재 수요자 발굴이 중요하기 때문이다. 이를 위해 신기술 빅데이터의 분석을 통해 확인된 주요기술은 무엇인가?, 신기술 빅데이터의 분석을 통해 발굴된 잠재 수요기업은 어디인가?, 잠재 수요기업과 연관되어 있는 핵심어들은 무엇인가? 등을 연구문제로 설정하였다. 한국표준과학연구원(KRISS)의 2가지 신기술을 선정하고 3명의 코더들이 협의를 통해 4개의 분석단어를 정하였다. 빅데이터는 인터넷에서 수집하고 정제 한 후에 텍스트마이닝과 시맨틱네트워크분석을 실시하였다. 기업의 스키마와 홈페이지 통해 재검증하는 과정을 거쳤다. 빅데이터 분석을 실시한 결과, 첫 번째 연구문제는 연결정도, 연결정도중심성, 빈도 등을 통해 2개의 기술마다 상위 20개의 주요기술을 확인하였다. 두 번째 연구문제는 공동출현 연결망, 연결 강도, 코사인 유사계수 등을 통해 2개 기술의 잠재 수요기업을 발굴하였다. ‘배열검출기형 분광복사계 성능평가 기술’은 17개의 기업을 발굴하였고, ‘초음파를 이용한 진공압력 측정센서 및 모듈’은 10개의 기업을 발굴하였다. 세 번째 연구문제는 잠재 수요기업의 에고네트워크분석을 통해 기업명과 의미 있게 연관되어 있는 단어들을 확인하였다. 본 연구는 기존의 개념적 빅데이터 연구에서 빅데이터 분석을 통해 기술마케팅의 잠재 수요기업을 발굴하는 실용적인 빅데이터 연구로 나아간 점이 의의가 있다. 빅데이터의 구체적인 활용 분야로 기술마케팅을 선택하여 실증함으로써 연구의 범위를 확대하고 향후 빅데이터 분석 연구의 발전에 기여하고 있다. Even though the study of the Bigdata is getting advanced, the topics are limited fundamental concept, trend, technical situation or the practical possibility of the Bigdata. The purposes of this research are to expand the study of the Bigdata and to use it in technology marketing practically. Also we found a few buyers which have potential possibility of technology marketing by using Bigdata. One reasons that we choose Bigdata for technology marketing is the necessity of marketing in the technical business area is getting higher. The other reason is that finding potential buyers is getting more important because of the nature of technical business. For these, we set-up the research problems like “What are the verified main techniques through the Bigdata analyzing?, Where are the extracted potential buyers through the Bigdata analyzing?” and “What are the keywords which are connected to the potential buyers?” We choose two at the new techniques of Korea Research Institution of Standards and Science(KRISS) and three coders discussed to choose four analyzing words. We collected the Bigdata on the internet, and executed textmining and semantic network analysis with it. After that, we reexamined them by confirming the schema of the potential buyer and the homepage. First, we checked 20 main techniques per the two techniques by degree, degree centrality, and frequency. Second, we found the answer of this study by finding the potential buyers which has the two techniques through co-occurrence frequency, network intensity and cosine similarity coefficient. Extract 17 buyers at ‘Performance characterization of array-type spectroradiometers’ and 10 buyers were extracted at ‘Pressure measuring system for vacuum chamber using ultrasonic wave’. Finally, we need to check the keywords related to the corporate name through analyzing ego-network of potential buyers. Therefore the results are proved completely through analyzing the Bigdata. This study is full of significance in the way that conceptual study of analyzing Bigdata goes a step further to the application of practical use to find potential buyers. This research contributes to the Bigdata study by expanding the range of the study through offering practical way of using in technology marketing area.

빅데이터 분석을 이용한 코로나 19 이후 경호 관련 학과의 사회적 인식 분석

김건희,황성용 학습자중심교과교육학회 2023 학습자중심교과교육연구 Vol.23 No.16

Objectives The purpose of this study is to analyze society's overall perception of universities' security-related departments through big data, provide basic data for the development of security-related departme. Methods Under the keyword “University + Security,” data from major domestic portal sites were collected and refined from January 20, 2020 to March 31, 2023, when the first COVID-19 confirmed case in Korea was found, and word cloud analysis, network analysis and centrality analysis, and CONCOR analysis were conducted. Results First, through word cloud analysis of the top 30 keywords of frequency, ‘police’ was found to be an overwhelmingly frequent keyword. Second, in network analysis, “police” was confirmed to be the most important keyword, and words such as “police”, “security”, “administration”, “major”, and “sports” showed high connectivity in connection centrality analysis. In the mediation centrality analysis, it was confirmed that most keywords serve as bridges between nodes and are actively connected. Third, in the CONCOR analysis, it was confirmed that it was clustered into six groups, and the cluster name was determined as ‘public security and After Graduation’, ‘Curriculum and Employment’, ‘University Promotion’, ‘physical education’, ‘Daegu’, and ‘Other’. Conclusions It was confirmed that the police and security have a close relationship in people's perceptions, and it is believed that it would be a desirable direction to properly utilize them and reflect them in security-related departments. IIt is necessary to develop and apply a curriculum that can strengthen the systematicity of education and enhance expertise to induce students' interest. It is necessary to use it as an advantage of security-related departments by increasing positive awareness and interest in bodyguards, and it will be helpful to prepare and present specific plans for students' careers and post-graduation plans, and to find and advance to public security.

텍스트마이닝 분석을 활용한 디카페인 커피에 대한 소비자 인식 분석 연구

박병현,김준형,남장현 (사)한국조리학회 2024 한국조리학회지 Vol.30 No.4

. This study aims to understand consumer perception and trends related to decaffeinated coffee through text mining text analytics), identifying key keywords connected to decaffeinated coffee. From March 14, 2019, to March 13, 2023, text documents on the network were collected, and the collected data underwent refining processes using Textom. A total of 14,204 pieces of data were collected, and after preprocessing to remove unnecessary data, a refined dataset of 7.7 MB was obtained. The collected and refined data were analyzed using natural language processing for frequency analysis, co-occurrence frequency analysis, revealing key keywords. The relationships between keywords were analyzed through connection structure and centrality analysis. Based on this, cluster analysis was conducted, identifying four core keyword clusters with structural similarity. Sentiment analysis on consumer emotions regarding decaffeinated coffee was conducted using the sentiment dictionary provided by Textom. The results of text mining analysis are as follows. Firstly, it was observed that ‘franchises’ are prominently discussed in decaffeinated-related documents. Secondly, centrality analysis for network connection structure revealed a close association between decaffeinated and coffee, followed by a strong connection to franchises. Centrality analysis was used to understand the network structure of keywords related to decaffeinated coffee, which were primarily associated with the attributes, taste, and purchase intentions of decaffeinated coffee. Thirdly, through CONCOR analysis, four key groups were identified, focusing on consumer experiences with decaffeinated coffee, health-related concerns, interest in new products, and personal transactions. Particularly, health-related keywords significantly influenced consumer concerns regarding caffeine's adverse effects and their interest in decaffeinated coffee. Given the steady growth of the decaffeinated coffee market, the importance of utilizing these research findings for marketing strategy analysis and further research on decaffeinated coffee is evident.

Analysis of Research Trends of NRF’s Humanities City Support Project

최에스더,정진경,이규태 한국비교정부학회 2023 한국비교정부학보 Vol.27 No.4

(Purpose) Through the analysis of unstructured big data, this study analyzes the research trends in the field of the Humanities Popularization Project of the Korea Research Foundation over the past 10 years to examine whether the purpose of the Humanities City Support Project is being effectively promoted and to explore the way forward. (Design/methodology/approach) After collecting data related to keywords, research goals, expected effects, and research summaries of the research project, we connected the data to the data held by Textom, a big data analysis solution program, to perform data purification and preprocessing. The frequency and matrix files generated by Textom were connected to the UciNet program to perform semantic linkage network and centrality analysis. CONCOR analysis, a technique that clusters keywords in structural positions by analyzing the relationship between co-occurring keywords, was performed. (Findings) The results of the TF-IDF analysis were presented in the order of 'healing', 'humanities', 'culture', 'happiness', 'city', 'community', 'region', 'citizen', 'art', and 'resident'. The results of the connection centrality analysis show that 'humanities' and 'humanities' 'culture', 'city', 'region', 'citizen', 'course', 'business', 'history', 'experience', 'society', and 'program' are highly active, which is similar to the results of the frequency and TF-IDF analysis. In addition, the results of the dominance centrality analysis are similar to the results of the connection centrality analysis. The CONCOR analysis shows that the first group is highly related to keywords related to the understanding of humanities such as 'humanities', 'humanities', 'culture', 'humanities-based', 'tradition', and 'human'. The second group shows high keyword relevance for humanities subjects such as "city," "region," "citizen," "community," "communication," "participation," "residents," and "youth. The third group includes humanities programs such as "history," "courses," "programs," "topics," "education," "composition," "literature," "art," and "content," and the fourth group includes humanities directions such as "life," "values," "healing," "spirit," "meaning," "proliferation," "stagnation," "future," "opportunity," and "contribution. (Research implications or Originality) Based on these findings, we believe that the way forward is to develop humanities programs that directly involve local community members in order to meet the goals of the HRF's Humanities Popularization Project. To this end, we summarize our policy suggestions as follows. First, budgetary support is needed to increase the value of the humanities through the Humanities City Support Project and to share and spread humanities programs with the public. Second, the Humanities City Support Project should be renamed the 'Humanities and Arts City Support Project' by including the arts in its scope, and should be made more public-friendly by adding experiences and performances to humanities-centered lectures. Third, as the times are changing rapidly and the channels for listening to theoretical humanities lectures through online media are diversifying and popularizing, it is necessary to specialize in programs that can generate experience and interest and activate community resources instead of focusing on lectures. If the project so far has been mainly a case of mobilizing audiences artificially, we should avoid this and ask for a way to actively engage basic local governments in lifelong education.

인구의 서울 쏠림과 지방 쇠퇴의 원인 및 해결방안 : 감성분석을 중심으로

정수빈 ( Su-been Jeong ),김재원 ( Jae-won Kim ),박서윤 ( Seo-yun Park ),곽인상 ( In-sang Kwak ),주다영 ( Da-young Joo ) 한국감성과학회 2023 춘계학술대회 Vol.2023 No.-

South Korea, which has developed around Seoul, has gradually widened the gap between Seoul and the provinces. This caused overcrowding in Seoul and the decline of the provinces, and emerged as a national problem along with a decrease in population. This study studies the causes and solutions of the population's concentration in Seoul and local decline: focusing on big data and emotional analysis. Previous studies derive solutions through statistical-based numerical surveys. However, statistical-based surveys estimate the results by investigating based on what has already happened. Induction methods that infer results based on statistical facts have high accuracy, but there are emotional areas that cannot be investigated only by statistical techniques. In particular, people's perceptions of social problems and psychological factors for individual factors can be seen as emotional areas. To this end, emotional analysis and big data analysis, which were not well used in previous studies, were used. Through emotional analysis, people's interest and public opinion are analyzed to infer the cause of the problem, and big data is used to provide a basis for the inference results. In the case of the subject of this study, upper factors such as medical care, transportation, and culture and various lower factors are intertwined. Behind these factors lies the psychological elements of positivity and denial. Through emotional analysis, the relationship between these keywords is analyzed and the psychology of the public hidden therein is grasped. In particular, since psychology has a strong subjective tendency, there is a limit to investigating it only with statistical techniques and refining it to meaningful values that can be used for reasoning results. Therefore, problem analysis using emotional analysis techniques is necessary. Emotional analysis technology is a technology that extracts positive, negative, and neutral emotions from natural language data such as text and sentences, and text data is used for this. This study used these emotional analysis technologies to analyze positive and negative factors about Seoul's population growth and local population decline, which are considered the main causes, and to identify the characteristics and problems of each region.Through this, we would like to suggest ways to help policy alternatives to solve the problem of leaning toward Seoul and local decline.

기능성 화장품 마케팅의 소셜 빅데이터 분석 활용 : H사 사례를 중심으로

황신해,구동영,김정군 한국디지털정책학회 2019 디지털융복합연구 Vol.17 No.7

This study aims to analyze the cosmedical cosmetics market and the nature of customer through the social big data analysis. More than 80,000 posts were analyzed using R program. After data cleansing, keyword frequency analysis and association analysis were performed to understand customer needs and competitor positioning, formulated several implications for marketing strategy sophistication and implementation. Analysis results show that “prevention” is a new and essential attribute for appealing target customers. The expansion of the product line for the gift market is also suggested. It has been shown that there is a high correlation with products that can be complementary to each other. In addition to the traditional marketing technique, the social big data analysis based on evidence was useful in deriving the characteristics of the customers and the market that had not been identified before. Word2vec algorithm will be beneficial to find additional 본 연구는 소셜 빅데이터 분석을 통해 튼살 기능성 화장품 시장과 고객 분석을 수행하고 중소화장품제조 기업의 마케팅 활용 후 시사점을 도출하기 위해 수행되었다. 20만개 이상의 네이버 블로그, 네이버 까페, 인스타그램, 네이버스토어 게시글을 대상으로 R을 활용한 빅데이터 분석을 수행하였다. 키워드 빈도분석, 연관관계 분석을 통해 고객 니즈와 경쟁사 포지셔닝을 이해하고 마케팅 전략 수립을 위한 시사점을 도출하였다. 분석 결과 튼살 완화와 함께 예방이 핵심 소구점으로 파악되었고 선물용 시장을 위한 제품 라인의 확장이 주요 시사점으로 나타났고 제품에 대해 상호 보완할 수 있는 제품과의 연관성이 높은 것으로 나타났다. 전통적인 마케팅 기법과 함께 사용 시 소셜 빅데이터 분석은 증거 기반의 의사 결정과 기존에 파악하지 못했던 고객과 시장의 특성 도출에 유용함을 확인하였다. 향후 연구에서는 word2vec과 같은 자동화된 문장 분류를 통해 추가적인 마케팅 인사이트를 얻을 수 있을 것으로 판단된다.

빅데이터를 활용한 정책분석의 방법론적 함의

이영주(Young-Joo Lee),김도훈(Dhohoon Kim) 한국IT서비스학회 2016 한국IT서비스학회지 Vol.15 No.1

In the creative economy paradigm, motivation of the opportunity based startup is a continuous concern to policymakers. Recently, bigdata anlalytics challenge traditional methods by providing efficient ways to identify social trend and hidden issues in the public sector. In this study the authors introduce a case study using social bigdata analytics for conducting policy analysis. A semantic network analysis was employed using textual data from social media including online news, blog, and private bulletin board which create buzz on the startup business. Results indicates that each media has been forming different discourses regarding government’s policy on the startup business. Furthermore, semantic network structures from private bulletin board reveal unexpected social burden that hiders opening a startup, which has not been found in the traditional survey nor experts interview. Based on these results, the authors found the feasibility of using social bigdata analysis for policy-making. Methodological and practical implications are discussed.

A Study on Korean Emotion Index Using Cluster Analysis

Jong-Hwa Lee,Hoanh-Su Le,Hyun-Kyu Lee 한국인터넷전자상거래학회 2019 인터넷전자상거래연구 Vol.19 No.5

Based on a study of the wheel of emotions of American psychologist Plutchik (1980). The emotional wheel of Plutchik’s has seven adjectives: surprised, sad, happy, fearful, disgusted, bad, angry. And the emotions were grouped in a hierarchical manner. We have reconstructed the English - based emotional wheel with Korean language processing and use it for the analysis of the emotion of the netizen in various media based on text. Media on the web environment was collected from textual informal data such as Internet news, article comments, blogs, and social network services (SNS) content (Facebook, Twitter, Instagram, YouTube, etc.). We collected the emotion words from the hash tags of SNS and constructed the Korean emotion dictionary based on the seven emotion sets of Flickr. In this study, we have obtained over 150,000 Korean emotional words in seven dimensions then calculated the weight of emotional words in each dimension. In other words, we want to find emotion index through cluster analysis. PVClust is an R package for evaluating uncertainty in hierarchical cluster analysis. For each cluster of hierarchical clustering, the quantity called p-value is computed through multi-scale bootstrap resampling. The p-value is a value between 0 and 1, and it is possible to check how strong the data is supported in the cluster, and it is expected to be utilized as a basic research on building three-dimensional emotional DNA through emotional word ranking in each emotional dimension.

빅데이터 분석 시장 활성화를 위한 기술적, 제도적 요인에 관한 연구: 전문가 심층인터뷰 방법을 중심으로

배재권 사단법인 인문사회과학기술융합학회 2017 예술인문사회융합멀티미디어논문지 Vol.7 No.5

Interest in big data is growing throughout the industries and companies are developing profit models that create and optimize business value using big data analysis solutions. The governments and industries of leading countries are using big data as an important tool to solve various problems and issues as well as for establishing future strategies and making strategic decisions. The Korean government has a clear determination to stimulate the big data market and is increasing its budget for big data, but big data related companies are not making high profits due to the lack of business models. Furthermore, private companies are assuming a conservative position toward investments in big data due to insufficient success stories of big data use in various areas. In this study, therefore, the delphi survey and in-depth interview methodologies were used to identify the resistance factors of the big data market activation and elucidate the technical and institutional factors required to stimulate big data analysis. The results of this study revealed that big data experts suggested five technical and institutional factors required to stimulate the big data analysis market including: (1) improvement of technologies for machine learning and artificial intelligence techniques, (2) personal information protection act revision for activating the use of de-identification of personal information and big data industry promotion act legislation, (3) the need to nurture specialists such as data scientists and big data analysis, (4) the need to actively open public data, and (5) developing and refining components in data governance framework. 전 산업에 걸쳐 빅데이터(BigData)에 대한 관심이 날로 증대되고 있고, 기업들은 빅데이터 분석 솔루션을 활용한 비즈니스 가치 창출과 이를 최적화하려는 수익모델을 개발하고 있다. 주요 국가 정부와 산업계에서는 빅데이터를 각종 문제 해결 및 이슈 대응과 더불어 미래 전략과 수반되는 전략적 의사결정의 중요한 도구로 활용하고자 한다. 한국 정부 또한 빅데이터 시장 활성화를 위한 의지가 명확하고 매년 빅데이터 관련 예산을 증액하고 있으나 빅데이터 관련 기업들은 비즈니스 모델 부재로 높은 수익성을 내지 못하고 있는 실정이다. 또한 다양한 영역에서의 빅데이터 활용 성공사례가 부족한 점으로 인해 민간기업의 경우 빅데이터 투자에 보수적으로 접근하고 있다. 따라서 본 연구는 빅데이터 시장 활성화의 저항요인 규명과 빅데이터 분석 활성화에 필요한 기술적, 제도적 요인을 도출하기 위해 전문가 심층면접조사(In-depth Interview)를 수행하였다. 연구결과, 빅데이터 전문가들은 빅데이터 분석 시장 활성화에 필요한 기술적, 제도적 요소로 (1) 기계학습(machine learning) 및 인공지능기법(artificial intelligence techniques)의 기술력 향상, (2) 비식별 정보이용 활성화를 위한 개인정보보호법 제도 개선과 빅데이터 진흥법 제정, (3) 데이터 과학자, 빅데이터 분석가 등의 전문 인력 양성 필요, (4) 정부의 공공데이터 개방과 민간 빅데이터와의 통합 필요, (5) 데이터 거버넌스(data governance) 프레임워크의 구성요소 개발 및 상세화 등을 제시하였다.