• 한국빅데이터학회지
• /
• 제4권1호
• /
• pp.29-38
• /
• 2019

본 연구에서는 판매량 증대와 효율적인 재고 관리를 위해 지난 5년간 온라인 쇼핑몰 'A'에서 누적된 빅데이터를 활용하여 기온 변화에 따른 반팔 티셔츠와 아우터웨어(outer wear)의 판매량을 예측하는 판매 예측 모델을 제안한다. 제안한 모델은 2014년부터 2017년도까지 기온 변화에 따른 반팔 티셔츠와 아우터웨어의 판매량을 분석하여 2018년 기온 변화에 따른 반팔티셔츠와 아우터웨어의 판매량을 예측한다. 제안한 판매 예측 모델을 사용하여 반팔티셔츠와 아우터웨어의 판매량 예측값과 실제 2018년 판매량을 비교 분석한 결과 반팔티셔츠와 아우터웨어의 예측 오차율은 각각 ±1.5%와 ±8%를 나타내었다.

• 한국빅데이터학회지
• /
• 제3권1호
• /
• pp.63-71
• /
• 2018

최근 5년(2013~2017년) 연속 영화 총 관객 수가 2억 명이 넘는 국내 영화 산업에서 천만 관객을 돌파한 한국 영화 간에는 어떤 요인이 영향을 미쳤는지 분석해 보았다. 일반적으로 천만 관객 돌파에 영향을 주는 요인으로는 스크린 수와 평점을 중요하게 보는 시각이 많았다. 본 연구에서는 스크린 수, 평점을 포함하고 추가적으로 4가지 요인을 설정하여 가설을 수립하고 빅데이터 분석을 통해 천만 관객 돌파 유무와의 상관관계를 분석했다. 이를 통해 천만 관객 돌파 예측 정확도는 91%, 누적 관객 수 예측 정확도는 99.4%까지 맞추는 유의미한 결과를 얻었다.

• 대한산업공학회지
• /
• 제42권4호
• /
• pp.296-303
• /
• 2016

In public transportation, smart cards have been introduced for the purpose of convenient payment systems. The smart card transaction data can be utilized not only for the exact and convenient payment but also for civil planning based on travel tracking of citizens. This paper focuses on the analysis of the transportation convenience using the smart card big data. To this end, a new index is developed to measure the transit convenience of each region by considering how passengers actually experience the transportation network in their travels. The movement data such as movement distance, time and amount between regions are utilized to access the public transportation convenience of each region. A smart card data of five working days in March is used to evaluate the transit convenience of each region in Seoul city. The contribution of this study is that a new transit convenience measure was developed based on the reality data. It is expected that this measure can be used as a means of quantitative analysis in civil planning such as a traffic policy or local policy.

• 한국식생활문화학회지
• /
• 제36권2호
• /
• pp.168-183
• /
• 2021

Using the big data analysis of the Choseonwangjosilrok, this research aimed to figure out the fruits' types, prevalence, seasonal appearances as well as the royalty's perspective on fruits during Choseon period. Choseonwangjosilrok included nineteen kinds of fruits and five kinds of nuts, totaling 1,601 cases at 72.8% and 533 cases at 24.2% respectively. The text recorded fruits being used as: tributes for kings, gifts from kings to palace officials, tomb offerings, county specialties, trade goods or gifts to the foreign ambassadors, and medicine ingredients in oriental pharmacy. Seasonally the fruits appeared demonstrating an even distribution. Periodic characteristics were observed in decreasing quantity chronologically. From fifteenth century to nineteenth century, the fruits with timely features were seen: 804 times at 36.6%, 578 times at 26.3%, 490 times at 22.3%, 248 times at 11.3%, and 78 times at 3.5% respectively. In fifteenth century: citrons, quinces, pomegranates, cherries, permissions, watermelons, Korean melons, omija, walnuts, chestnuts, and pine nuts appeared most frequently. In sixteenth century: pears, grapes, apricots, peaches, and hazelnuts appeared most frequently. In seventeenth century: tangerines and dates appeared most frequently. In eighteenth century, trifoliate orange was the most frequently mentioned fruit.

• 국토계획
• /
• 제54권3호
• /
• pp.75-90
• /
• 2019

As the 24-hour society arrives, human activities in daytime and nighttime urban spaces are changing drastically, and the need for new urban management policies is steadily increasing. This study analyzes the types and characteristics of Seoul's human dynamics using location-based big data and the results are summarized as follows. First, the pattern of human dynamics in Seoul repeats itself every 7 days. Second, the types of human dynamics in Seoul can be classified into five types, and each of type has its own unique time-series and local characteristics. Third, the degree of match between human dynamics and zoning system in urban planning legislation was highest in 'Type 1' residence pattern and low in other types. The following implications can be drawn from these results. First, This paper examined the methodology of analyzing the regional characteristics of Seoul through the human dynamics and obtained meaningful results. Second, This paper can derive reliable and objective pattern analysis results using Big data that reflect the overall population characteristics. Third, the scale of night-time activity in the urban space of Seoul was understood, and its distribution, patterns and characteristics identified.

• 동아시아경상학회지
• /
• 제10권1호
• /
• pp.109-121
• /
• 2022

Purpose - This study attempted to analyze news big data in order to examine the trend of change in housework due to technological innovation and family changes. Research design, data, and methodology - News big data was collected from Bigkinds for the purpose of trend analysis. A total of 8,270 articles containing 'housework' were extracted from news articles between January 1, 1990 and December 31, 2021. 11 general daily newspapers and 8 business newspapers were selected and were analyzed by dividing them into five-year units. Result - The change of trends in housework that appeared through news big data analysis can be summarized as below. First, the tendency to regard housework as work of women or housewives is gradually weakening. Instead, the centrality of connection with double income is increasing. Second, there is a tendency to strengthen the institutional approach to evaluation of the productivity of housework. Third, the possibility of market substitution for housework is expanding. Conclusion - In the era of the 4th industrial revolution, examining the impact of technological innovation and family change on housework not only enables the prospect of an industry, but also provides implications for policies related to housework. In addition, this study is differentiated in that it contributed to expand the field of housework research previously limited to analyzing survey data.

• 대한전기학회논문지:전력기술부문A
• /
• 제55권3호
• /
• pp.133-138
• /
• 2006

This paper presents an Optimal Power Flow (OPF) algorithm using Interior Point Method (IPM) to swiftly and precisely perform the five minute dispatch. This newly suggested methodology is based on Affine Scaling Interior Point Method which is favorable for large-scale problems involving many constraints. It is also eligible for OPF problems in order to improve the calculation speed and the preciseness of its resultant solutions. Big-M Method is also used to improve the solution stability. Finally, this paper provides relevant case studies to confirm the efficiency of the proposed methodology.

• 한국산업융합학회 논문집
• /
• 제27권3호
• /
• pp.581-590
• /
• 2024

This study aims to extract key topics through text mining of incident records (incident history, post-incident measures, preventive measures) from construction safety accident case data available on the public data portal. It also seeks to provide fundamental insights contributing to the establishment of manuals for disaster prevention by identifying correlations between these topics. After pre-processing the input data, we used the LDA-based topic modeling technique to derive the main topics. Consequently, we obtained five topics related to incident history, and four topics each related to post-incident measures and preventive measures. Although no dominant patterns emerged from the topic pattern analysis, the study holds significance as it provides quantitative information on the follow-up actions related to the incident history, thereby suggesting practical implications for the establishment of a preventive decision-making system through the linkage between accident history and subsequent measures for reccurrence prevention.

• 한국전자거래학회지
• /
• 제19권4호
• /
• pp.73-99
• /
• 2014

최근 다양한 분야에서 빅데이터 활용방안을 연구 중이다. 빅데이터는 기존의 방법으로는 다룰 수 없었던 방대한 분량의 데이터를 말한다. 빅데이터는 의사결정의 정확도 제고, 가까운 미래예측 그리고 새로운 비즈니스 창출가능이라는 점에서 주목을 받고 있다. 본 연구는 기술사업화분야에서의 빅데이터 활용방안 제안을 그 목적으로 하였다. 그리고 이를 위해서 문헌연구와 사례연구 그리고 그룹인터뷰를 진행하였으며, 이들을 바탕으로 기술사업화분야에서의 빅데이터 활용방안을 도출하였다. 빅데이터 활용방안은 기술사업화 프로세스의 5단계(착상, 보육, 시연, 촉진, 지속)별로 제시하였다. 본 연구는 기술사업화분야에서의 빅데이터 활용의 가능성을 제시했다는 점에서 의의가 있으며, 연구 방법상 일반적 해석에는 한계가 있을 수 있다고 생각한다. 그리고 본 연구가 기술사업화 정보 분석의 영역 확대에 기여할 수 있을 것으로 기대한다.

• 통상정보연구
• /
• 제13권3호
• /
• pp.543-564
• /
• 2011

기업경영에 있어 전략적 의사결정과 기업성과는 독립적이지 않고 상호 밀접한 관계가 있다. 본 연구는 한국 5대 무역기업집단 (Big Five Trading Conglomerates)의 전략적 의사결정과 기업성과간의 상관관계를 실증적으로 고찰 하였다. 비록 외환위기 이후 한국기업체들의 전반적 경영변화에 대한 많은 연구가 있었지만 전략적 의사결정을 주제로 한 주목할 만한 연구는 없었다. 연구결과 첫째, 한국 5대 무역기업집단의 의사결정 과정에는, 예전과 비교 해 봤을 때, 주목할 만한 변화가 없었다. 둘째, 의사결정과정에서 최고경영진의 과도한 개업은 기업성과를 방해 하지 않는 것으로 나타났다. 위를 바탕으로 볼 때 한국 무역기업집단 내에서 의사결정권한이 지금도 일부 최고경영진에 집중되어 있음을 시사하며, 이는 조직 전반에 걸쳐 내재된 오랜 유교적 전통과 문화 때문인 것으로 판단된다. 셋째, 그러나 의사결정과정에 있어 이사회의 권한이 점점 더 중요해짐을 알 수 있었다. 마지막으로, 의사결정권자들은 자신들의 정치적 위치나 권력을 개인적 목적을 위해 오용 및 남용하지 않는 것으로 나타났다.