ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 A Study on the Virtuous Circle Self-Learning Methods for Knowledge Enhancement
Cited 0 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
유재학, 김영민, 권순현, 김귀훈, 김내수, 김선진, 표철식
발행일
201702
출처
International Conference on Platform Technology and Service (PlatCon) 2017, pp.46-51
DOI
https://dx.doi.org/10.1109/PlatCon.2017.7883683
초록
Recently, along with the development of ICT technology, there is a significant increase in Internet of Everything (IoE) more advanced than Internet of Things (IoT) is one of the technologies that not only connects people and things, data and services, but also provides users with more intelligent and smart services However, it is difficult to efficiently process data generated from various kinds of things and services in this IoT environment. Also, it is difficult to provide objective analysis and knowledge-based services in an adaptive manner in response to IoE environment changes. In this paper, we propose a virtuous circle based knowledge convergence and extension model to accommodate the above intrinsic requirements. The proposed model exploits 1) the advanced information during preprocessing phase got by analyzing the high volume data of various IoE devices on real-time and 2) gives machine learning based learning models and their results during learning model phase to support the decision making accurately. These self-learning and learning results can be generated, converged, inferenced, and expanded with new knowledge of data processing and learning. Finally, our system has the added advantage of providing knowledge and understanding of physical things, virtual things, domains and services, and analysis information so that the user can easily understand them.
KSP 제안 키워드
Advanced information, Data processing, High volume, Internet of Everything, Internet of thing(IoT), IoT environment, Knowledge Enhancement, Knowledge convergence, Knowledge-based, Learning methods, Learning model