• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.85-91
• /
• 2019

Since online shopping has become common, people can easily buy fashion goods anytime, anywhere. Therefore, consumers quickly respond to various environmental variables such as weather and sales prices. Thus, utilizing big data for efficient inventory management has become very important in the fashion industry. In this paper, the changes in sales volume of fashion goods due to changes in temperature is analyzed via the proposed big data analysis algorithm by utilizing actual big data from Korean fashion company 'B'. According to the analytic results, the proposed big data analysis algorithm found both expected and unexpected changes in sales volume depending on the characteristics of the fashion goods.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.105-114
• /
• 2019

Missing value replacement is one of the big issues in data analysis. If you ignore the occurrence of the missing value and proceed with the analysis, a bias can occur and give incorrect results for the estimate. In this paper, we need to find and apply an appropriate alternative to missing data from weather data. Through this, we attempted to clarify and compare the simulations for various situations using existing methods such as MICE and MissForest based on R and time series-based models. When comparing these results with each variable, it was determined that the kalman filter of the auto arima model using the ImputeTS package and the MissForest model gave good results in the weather data.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.175-183
• /
• 2019

Drop-out issue is one of the challenges of cyber university. There are about 130,000 students enrolled in cyber universities, but the dropout rate is also very high. To lower the dropout rate, cyber universities invest heavily in learning analytics. Some cyber universities analyze the possibility of dropout and actively support students who are more likely to drop out. The purpose of this paper is to identify the learning data affecting the dropout prediction index. As a result of the analysis, it is confirmed that number of lessons(progress), credits, achievement and leave of absence have a significant effect on dropout rate. It is necessary to increase the accuracy of the prediction model through post-test on the student dropout prediction index.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.185-194
• /
• 2019

In the 100-year history of Korean films, Korean films have grown to more than 100 million viewers every year since 2012, and their total sales are estimated at 1 trillion. It is assumed that the influence on the popularity of Korean movies is related to 2012, when 60% of smartphone penetration rate and 30 million subscribers exceeded. As a result, before and after 2012, changes in movie boxing factor variables were needed, and the prediction model trained as a new independent variable was applied to actual data.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.3
• /
• pp.13-19
• /
• 2016

Spark, an in-memory big-data processing framework is popular to use for real-time processing workload. Spark can store all intermediate data in the cluster memory so that Spark can minimize I/O access. However, when the resident memory of workload is larger that the physical memory amount of the cluster, the total performance can drop dramatically. In this paper, we analyse the factors of bottleneck on PageRank Application that needs many memory through experiment, and cluster the Spark with Tachyon File System for using memory to solve the factor of bottleneck and then we improve the performance about 18%.

• Journal of Information Technology Applications and Management
• /
• v.24 no.4
• /
• pp.57-69
• /
• 2017

Due to the development of technology even in learning and education area, many studies have begun to make a new attempts to research by using SNS, breaking away from traditional learning methods. However, the limitations of these studies are restricted only to the use of wireless Internet and writing on Web sites. This study aims to conduct a research on English learning activities that utilize various technologies such as Bigdata, Facebook, Social Network Services (SNS) and English applications. In addition, this study looks into how these modern technologies can be integrated in the classrooms and which activities can be applied in the English classroom. This research is to suggest effective English learning methods through a thorough investigation on the effectivity of various technologies based on the Web 2.0 such as Flickr, blogs, MySpace, and online discussion board within the context of the English learning. To verify the effect of the study, the subjects are divided into experimental and control group. The experiment is proceeded with pre- and post-test. The experimental group is designed to verify the effects using SNS tools such as Facebook, Bigdata, and Online Massive Learning. A survey is conducted to determine the preference of utilizing social networking sites and to analyze the effects in class. The result is that the average scores for experimental group have improved more than the average of control group. The comparison of pre and post-test of the experimental group shows that the significance of the higher and median group was statistically significant at the p<0.01.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2017.11a
• /
• pp.969-988
• /
• 2017

4차 산업혁명에 대한 국가적 관심이 높아짐에 따라 ICT산업 분야의 연구개발(R&D)는 앞으로의 국가 성장에 핵심적인 역할을 할 가능성이 크다. 우리나라의 경우도 빠르게 변화하는 ICT 산업에 대응하기 위해, 국가차원에서는 중장기 전략을 수립하고 있으며, 민간차원에서는 관련 인력풀(pool)을 늘리는 등 다각화된 대처를 하고 있다. 하지만 미국과 중국 등 선진국들의 기술수준과 가격 경쟁력을 결코 무시할 수 없어, 우리나라의 ICT산업은 낙관할 수만은 없는 상황이다. 그러므로 지금은 오히려 우리나라 ICT산업에 대한 명확한 진단을 통해 효율적이고 효과적으로 기술기회와 R&D기회를 발굴하는 것이 보다 실효성 있는 정책 수립에 도움을 줄 수 있다. 본 논문에서는 한국과학기술정보연구원(KISTI)에서 개발한 교역활동 프로파일 분석 시스템을 통해 ICT산업에 관련된 상품들 전체를 거시적인 관점에서 확인함으로써 우리나라의 ICT산업 전반을 진단하고 분석하고자 한다. 이로 인해, 증거기반(evidence-based)의 과학적인 방법으로 연구개발 기회를 파악하여 효율적이고 효과적인 정책수립에 기여하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.323-325
• /
• 2016

Computing loud arrival times were, important data Clouding and, without being limited to the device, may process the information. Recently, work environment and improved access to Cloud and Mobile, this decision has been made to take effect immediately. However, when such important decisions of the government, the security is required. In this paper, we study the network access and control in IoT, Cloud, Bigdata, Smartwork System applied to Mobile. Study the authentication, authorization, and security for each security level Level of Service to connect to the DB information. Research of this paper will be used as the basis for the information processing and decision-making system design and construction of public institutions and agencies as important information for the protection Smartwork System.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.23-32
• /
• 2016

With the rapid development of information technology, we can manage not only structured data but also unstructured data. Big data environments drive new business values. This study examines the effect of analytic resources to business performance under big data environments. Recent worldwide reports showed empirical performance results of big data applications. Compared to these reports, we attempt to analyze resources of big data applications to companies in Korea. This study results in current status of big data use in Korea. and will help to develop a maturity model of big data applications.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.33-39
• /
• 2016

Recently, predicting personality with the help of smartphone usage becomes very interesting and attention grabbing topic in the field of research. At present there are some approaches towards detecting a user's personality which uses the smartphones usage data, such as call detail records (CDRs), the usage of short message services (SMSs) and the usage of social networking services application. In this paper, we focus on the assessing the correlation between MBTI based user personality and the smartphone usage data. We used $Na{\ddot{i}}ve$ Bayes and SVM classifier for classifying user personalities by extracting some features from smartphone usage data. From analysis it is observed that, among all extracted features facebook usage log working as the best feature for classification of introverts and extraverts; and SVM classifier works well as compared to $Na{\ddot{i}}ve$ Bayes.