ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Extension of Rule-based SLICE Platform With Deep Learning Model
Cited 1 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
김현학, 서영호, 우성필, 박동환
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1893-1895
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289576
협약과제
20IR1300, 초대규모(Massive) 실시간 IoT 인프라 및 네트워크 기술 개발 , 박태준
초록
The meaning of intelligent systems has changed over time. Traditionally, it refers to an intelligent ruled-based context aware system, but nowadays, it is more often referred to as a deep learning intelligent system. Since these two intelligent systems are still insufficient to be used separately, this paper try to integrate the intelligent module of deep learning on SLICE, which was introduced as a rule-based intelligent IoT platform that easily provides intelligent services. First, in this paper, the pros and cons of the existing rule-based engine and the deep learning-based intelligence model are examined. After that, how to combine the advantages of each is discussed. Finally, this paper shows that the proposed intelligent system integration can be used to design and implement a service more easily and quickly through a feasibility test and simple performance check with a low-cost general-purpose Raspberry Pi.
KSP 제안 키워드
Context aware system, Feasibility test, Intelligent IoT, Intelligent module, Intelligent systems, IoT Platform, Learning model, Learning-based, Low-cost, Over time, Rule-based