• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.12
• /
• pp.716-722
• /
• 2016

In the recent rapidly changing IT environment, the amount of smart digital data is growing exponentially. As a result, in many areas, utilizing big data research and development services and related technologies is becoming more popular. In SMART learning, big data is used by students, teachers, parents, etc., from a perspective of the potential for many. In this paper, we describe big data and can utilize it to identify scenarios. Big data, obtained through customized learning services that can take advantage of the scheme, is proposed. To analyze educational big data processing technology for this purpose, we designed a system for big data processing. Education services offer the measures necessary to take advantage of educational big data. These measures were implemented on a test platform that operates in a cloud-based operations section for a pilot training program that can be applied properly. Teachers try using it directly, and in the interest of business and education, a survey was conducted based on enjoyment, the tools, and users' feelings (e.g., tense, worried, confident). We analyzed the results to lay the groundwork for educational use of big data.

• Electronics and Telecommunications Trends
• /
• v.28 no.1
• /
• pp.33-41
• /
• 2013

64bit 범용 서버의 활용 확산, 메모리 가격의 하락 등 하드웨어의 발전과 실시간성을 요구하는 응응 분야의 확대로 인해 인-메모리 컴퓨팅 기술에 대한 관심이 높아지고 있다. 인-메모리 컴퓨팅 기술은 응용 서비스의 클라우드화, 모바일화, 글로벌화로 인해 발생하는 익스트림 트랜잭션의 고성능 처리를 지원하기 위한 기반 기술로 활용이 확대되고 있다. 또한 빅데이터를 효과적으로 활용하기 위해서 빅데이터라는 원석을 보석으로 가공하는 데 있어서 실시간성을 제공하기 위한 기반 플랫폼으로서 활용이 시도되고 있다. 본고에서는 고성능 트랜잭션 처리를 필요로 하는 통신, 금융 등 특정 분야에서 주로 활용되던 인-메모리 DBMS(Datbase Management System) 기술이 익스트림 트랜잭션 서비스 환경, 빅데이터 실시간 분석 환경 등 새로운 서비스 환경을 지원하기 위한 기술 발전 동향에 대해 조사한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.66-67
• /
• 2016

최근 수많은 국 내외 글로벌 기업들이 클라우드 자원의 제공자 겸 소비자 역할을 하는 프라이빗 IaaS 클라우드 환경을 구축하고 있는 추세이며 이를 위해 오픈소스 클라우드 플랫폼인 오픈스택(OpenStack)이 많이 사용되고 있다. 이 논문에서는 대규모 빅데이터 처리를 위해 오픈스택 클라우드 환경의 가상머신 라이브 마이그레이션 기법을 사용할 경우 발생할 수 있는 문제점을 분석한다. 이러한 문제점에 대하여 가상머신에서 빅데이터 연산 처리 시 스토리지 병목현상을 해결하기 위한 마이그레이션 기법을 제시한다.

• The Journal of Small Business Innovation
• /
• v.20 no.3
• /
• pp.49-68
• /
• 2017

Platform finance is emerging as an alternative finance for SMEs by suggesting a new funding source based on a new technology named FinTech. The essence of this business is the adapting ICT challenges to the financial industry that can adequately reflect risk assessment using Big Data and effectively meet individual risk-return preference. Thus, this is evolving as an alternative to existing finance in the form of P2P loans for Micro Enterprises and supply-chain finance for SMEs that need more working capital. Platform finance in Korea, however, is still at an infant stage and requires policy support. This can be summarized as follows: "Participation of institutional investors and the public sector," meaning that public investors provide seed money for the private investors to crowd in for platform finance. "Negative system in financial regulations," with current regulations to be deferred for new projects, such as Sandbox in the UK. In addition, "Environment for generous use of data," allowing discretionary data sharing for new products," and "Spreading alternative investments," fostering platform finance products as alternative investments in the low interest-rate era.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.125-140
• /
• 2018

As one of the processes in the manufacturing industry, quality inspection inspects the intermediate products or final products to separate the good-quality goods that meet the quality management standard and the defective goods that do not. The manual inspection of quality in a mass production system may result in low consistency and efficiency. Therefore, the quality inspection of mass-produced products involves automatic checking and classifying by the machines in many processes. Although there are many preceding studies on improving or optimizing the process using the data generated in the production process, there have been many constraints with regard to actual implementation due to the technical limitations of processing a large volume of data in real time. The recent research studies on big data have improved the data processing technology and enabled collecting, processing, and analyzing process data in real time. This paper aims to propose the process and details of applying big data for quality inspection and examine the applicability of the proposed method to the dairy industry. We review the previous studies and propose a big data analysis procedure that is applicable to the manufacturing sector. To assess the feasibility of the proposed method, we applied two methods to one of the quality inspection processes in the dairy industry: convolutional neural network and random forest. We collected, processed, and analyzed the images of caps and straws in real time, and then determined whether the products were defective or not. The result confirmed that there was a drastic increase in classification accuracy compared to the quality inspection performed in the past.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.443-444
• /
• 2019

공유경제 시대의 다양한 전기구동플랫폼 운용에 유효한 새로운 유지보수 가이드라인을 도출하고자, 본 연구는 하이브리드자동차와 전기자동차의 특성을 모두 갖는 PHEV의 장기간 주행 데이터를 분석하여, 주요 부품의 상태 변화를 파악하였다. PHEV의 모터, 인버터, 2차전지 등 주요 부품의 주행 데이터 변화를 관찰하여 마일리지 누적에 따른 상태변화가 큰 부품을 파악하였다. 분석결과 1만Km 이상 주행 시 보조 배터리의 온도와 5만Km 이상 주행 시 2차전지의 온도 변화가 유의미하게 발생함을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.115-117
• /
• 2017

R has become a popular analytics platform as it provides powerful analytic functions as well as visualizations. However, it has a weakness in which scalability is limited. As an alternative, the RHadoop package facilitates distributed processing of R programs under the Hadoop platform. This paper investigates usefulness of the RHadoop package when analyzing healthcare big data that is widely open in the internet space. To do this, this paper has compared analytic performances of R and RHadoop using the medical treatment records of year 2015 provided by National Health Insurance Service. The result shows that RHadoop effectively enhances processing performance of healthcare big data compared with R.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.667-668
• /
• 2023

IT 기술의 발달로 인해 뉴스를 제공하는 플랫폼들이 다양해 졌고 최근 해외 인터뷰 영상, 해외 뉴스를 Youtube Shorts형태로 제작하여 화자의 의도와는 다른 자막을 달며 가짜 뉴스가 생성되는 문제가 대두되고 있다. 이에 본 논문에서는 Sentence-BERT를 활용한 YouTube 가짜 뉴스 탐지 시스템을 제안한다. 제안하는 시스템은 Python 라이브러리를 사용해 유튜브 영상에서 음성과 영상 데이터를 분류하고 분류된 영상 데이터는 EasyOCR을 사용해 자막 데이터를 텍스트로 추출 후 Sentence-BERT를 활용해 문자 유사도를 분석한다. 분석결과 음성 데이터와 영상 자막 데이터가 일치한 경우 일치하지 않은 경우보다 약 62% 더 높은 문장 유사도를 보였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.29-36
• /
• 2021

The amount of data generated has been growing exponentially, and the complexity of data has been increasing owing to the advancement of information technology (IT). Big data analysts and engineers have therefore been actively conducting research to minimize the analysis targets for faster processing and analysis of big data. Hadoop, which is widely used as a big data platform, provides various processing and analysis functions, including minimization of analysis targets through Hive, which is a subproject of Hadoop. However, Hive uses a vast amount of memory for data deduplication because it is implemented without considering the complexity of data. Therefore, an efficient algorithm has been proposed for data deduplication of complex structures. The performance evaluation results demonstrated that the proposed algorithm reduces the memory usage and data deduplication time by approximately 79% and 0.677%, respectively, compared to Hive. In the future, performance evaluation based on a large number of data nodes is required for a realistic verification of the proposed algorithm.

• Journal of Digital Convergence
• /
• v.11 no.4
• /
• pp.267-271
• /
• 2013

Our society has two prospective properties because of IT technology. Firstly, it is accelerated a degree of convergence. And convergence regions are expanded. For example, smart healthcare region was created by IT technology and medical industry. The efforts to convergence will be continued. Because of these properties, A number of data are made in our life. Through many devices such as smart phone, camera, game machine, tablet pc, various data types are produced. In this paper, we described utilization of Big Data. And we analysed Big Data processing process.