• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.103-114
• /
• 2021

This study explores research methodologies of design and data science, and applies data science paradigm on design process. Design research methodologies would have benefits of productivity and efficiency by using data driven design methodology. From insights of former studies, a new methodology of data driven design is suggested that design problem is transformed to data set attributes, such as variables, values and data patterns. The fine dust information app design is conducted as a case study to prove this methodology.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.3
• /
• pp.73-85
• /
• 2014

As the importance of big data analysis increases to improve the competitiveness of a corporate, a unified big data project development methodology is required in order to study the problem of a corporate in a systematic way and evaluate the problem w.r.t. a business value after solving the problem. This paper propose Scientific Data Anslysis and Development methodology(SDAD) which are integrated methodology of software development and project management for easier application into a field project. SDAD consisits of 6 stages(problem definition stage, data preparation stage, model design stage, model development stage, result extraction stage, service development state), each stages has detailed processes(47) and productions(93). SDAD, furthermore, unified previous ISP, DW, SW development methodologies in terms of the data analysis and can easily interchange the productions with them. This paper, lastly, introduces a way to assign responsible persons for each process and provide communication procedures in RACI chart to improves the efficiency of the interaction among professionals from different subjects. SDAD is applied to a Bigdata project in Korea Employment Information Services institution and the result turned out to be acceptable when evaluated by the supervision.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.655-662
• /
• 2023

Big data research plays a role of supplementing existing social science research methods. If the survey and experimental methods are somewhat inaccurate because they mainly rely on recall memories, big data are more accurate because they are real-time records. Social science research so far, which mainly conducts sample research for reasons such as time and cost, but big data research analyzes almost total data. However, it is not easy to repeat and reproduce social research because the social atmosphere can change and the subjects of research are not the same. While social science research has a strong triangular structure of 'theory-method-data', big data analysis shows a weak theory, which is a serious problem. Because, without the theory as a scientific explanation logic, even if the research results are obtained, they cannot be properly interpreted or fully utilized. Therefore, in order for big data research to become a methodological innovation, I proposed big thinking along with researchers' efforts to create new theories(black boxes).

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.563-567
• /
• 2023

본 연구는 한국 통계청이 수행하는 가계동향조사와 생활시간조사에서 자료처리 과정 및 방법을 혁신하려는 시도로, 기존의 통계 생산 방법론의 한계를 극복하고, 대규모 데이터의 효과적인 관리와 분석을 가능하게 하는 인공지능 기반의 통계 생산을 목표로 한다. 본 연구는 데이터 과학과 통계학의 교차점에서 진행되며, 인공지능 기술, 특히 자연어 처리와 딥러닝을 활용하여 비정형 텍스트 분류 방법의 성능을 검증하며, 인공지능 기반 통계분류 방법론의 확장성과 추가적인 조사 확대 적용의 가능성을 탐구한다. 이 연구의 결과는 통계 데이터의 품질 향상과 신뢰성 증가에 기여하며, 국민의 생활 패턴과 행동에 대한 더 깊고 정확한 이해를 제공한다.

• Korea Science and Art Forum
• /
• v.34
• /
• pp.133-148
• /
• 2018

Korea's housing structure is predicted that one-person housing will be the most common type of housing in Korea. Therefore, this study intends to derive contents for designing a one-person housing space considering the life of a rapidly increasing one-person householder. For this purpose, this study objectively derives the social, economic and cultural influencing factors of one-person households through big data analysis, and analyzed the correlation between contents using social network analysis methodology. In this paper, 60 core contents related to one person housing space were derived by applying big data analysis methodology. And through social network analysis, the most influential contents were derived from the space editing and space composition categories. This means that the residential space is an important part of the design idea that can flexibly respond to changes in the user's life. Based on this study, future research will focus on the concept and design methodology of one-person housing space.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2020.11a
• /
• pp.52-53
• /
• 2020

자율운항선박의 효과적인 운영을 위해서는 자선 주변 해상 환경의 장애물 및 자선, 타선에 대한 통합적인 상황인식 정보가 요구된다. 상황인식은 현재의 시점에서 관측되는 정보를 바탕으로 운항 해역에 대한 종합적인 인식과 함께 가까운 미래에서 발생할 수 있는 위험 상황 및 비정상 상황에 대한 추론까지를 포함한다. 본 연구에서는 이러한 자율운항선박의 원격 상황인식을 위한 기초연구로써, 선박자동식별시스템 AIS의 항적 정보 분석에 대한 내용을 수행한다. AIS에서 얻어지는 항적 정보를 이용한 해상 상황인식을 수행하기 위한 전처리 과정으로써, 손실 데이터에 대한 보간 방법에 대한 연구를 수행한다. 구체적인 방법론은, 추적필터를 이용한 보간 방법과 항적 정보 학습 기반의 보간 방법을 적용하였으며, AIS에서 얻어지는 실제 항적 데이터를 이용하여 초기 결과를 검증하였다.

• Journal of the Korean Society for information Management
• /
• v.28 no.4
• /
• pp.85-97
• /
• 2011

The purpose of this study was to develop a methodology of user participation evaluation of a scholarly information site in the field of science and technology and to enhance the site by applying a set of testing protocols. Experiments were conducted in a laboratory setting. Data from multiple sources, including eyetracking, search logs and post surveys, were collected and analyzed quantitatively. Based on the results of eyetracking, the contents and images were reorganized after removing unessential elements in the site. The resulting data from the search logs showed that the users were able to finish the tasks more quickly with the revised user interface. The results of the data analysis of post surveys indicated an overall improvement in the revised website compared to the original one.

• Journal of Korea Technology Innovation Society
• /
• v.2 no.3
• /
• pp.48-60
• /
• 1999

과학기술지표는 전통적으로 R&D 투입 데이터와 특허자료가 사용되었지만 본 연구에서는 이들의 단점을 극복할 대안으로 기업의 혁신활동 지표를 제시하고자 한다 먼저 한국의 CIS 데이터가 소개되고 계량분석을 이용한 방법론이 소개된다. 한편 이를 이용하여 산업별 혁신 능력지수를 제시한다

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.935-940
• /
• 2023

Most text data collected through web scraping for artificial intelligence and big data analysis is generally large and unstructured, so a purification process is required for big data analysis. The process becomes structured data that can be analyzed through a heuristic pre-processing refining step and a post-processing machine refining step. Therefore, in this study, in the post-processing machine refining process, the Korean dictionary and the stopword dictionary are used to extract vocabularies for frequency analysis for word cloud analysis. In this process, "user-defined stopwords" are used to efficiently remove stopwords that were not removed. We propose a methodology for applying the "thesaurus" and examine the pros and cons of the proposed refining method through a case analysis using the "user-defined stop word thesaurus" technique proposed to complement the problems of the existing "stop word dictionary" method with R's word cloud technique. We present comparative verification and suggest the effectiveness of practical application of the proposed methodology.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.905-907
• /
• 2022

악성코드를 분석하는 기존 기법인 정적분석은 빠르고 효율적으로 악성코드를 탐지할 수 있지만 난독화된 파일에 취약한 반면,, 동적분석은 난독화된 파일에 적합하지만 느리고 비용이 많이 든다는 단점을 가진다. 본 연구에서는 두 분석 기법의 단점을 해결하기 위해 딥러닝 모델을 활용한 난독화에 강한 정적분석 모델을 제안하였다. 본 연구에서 제안한 방법은 원본 코드 및 난독화된 파일을 grayscale 이미지로 변환하여 데이터셋을 구축하고 AutoEncoder 를 사전학습시켜 encoder 가 원본 파일과 난독화된 파일로부터 원본 파일의 특징을 추출할 수 있도록 한 이후, encoder 의 output 을 fully connected layer 의 입력으로 넣고 전이학습시켜 악성코드를 탐지하도록 하였다. 본 연구에서는 제안한 방법론은 난독화된 파일에서 악성코드를 탐지하는 성능을 F1 score 기준 14.17% 포인트 향상시켰고, 난독화된 파일과 원본 파일을 전체를 합친 데이터셋에서도 악성코드 탐지 성능을 F1 score 기준 7.22% 포인트 향상시켰다.