ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Brain-inspired Method for Hyper-connected and Distributed Intelligence
Cited 2 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Sang Ki Kim, Sunme Kim
Issue Date
2020-02
Citation
International Conference on Artificial Intelligence in Information and Communication (ICAIIC) 2020, pp.1-4
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICAIIC48513.2020.9065226
Abstract
In a large-scale IoT environment such as a future smart city, various sensors and autonomous cars/drones/robots collect and process a wide variety of data. However existing monolithic or silo style operation of smart city makes hard to solve the problem when an unseen complex event occurs. In this paper, we suggest a structure and method of distributed intelligence processing which mimics the function and network structure of the brain in order to efficiently control the complex situations. Our approach utilizes local and rapid processing in parallel as well as global and exploratory processing through cooperation and competition between local intelligence. It will give us an opportunity to realize the autonomous problem solving on a large scale hyper-connected network infrastructure, by finding an emergence structure of distributed intelligence that mimics human consciousness process.
KSP Keywords
Autonomous car, Brain-inspired, Complex situations, Cooperation and competition, Distributed Intelligence, Hyper-connected, IoT environment, Smart city, large-scale, network infrastructure, network structure