• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.2
• /
• pp.86-97
• /
• 2016

This study aims to analyze the characteristics of the smart city governance through the multi-layer governance model, which includes administrative governance(AG), technological governance(TG), and global governance(GG). The results of the smart city governance are as follows. Multi-layered governance was modeled to enable cross-checking of each element of the propelling process and types of governance. AG has transitioned from a public partnership to a public-private people partnership(pppp) through a public-private partnership(ppp). TG has the characteristics of information communication technologies(ICTs) - eco technologies(EcoTs) - Spatial technology convergence including physical center, information software platforms such as the CCTV convergence center, and virtualization such as the cloud data center. GG aims at developing killer applications and ICTs-embedded space with intelligent buildings such as a smart city special zone to enable overseas exports. The smart city roadshow and forum have been developed as a platform for overseas exports with competition as well as cooperation.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.157-171
• /
• 2021

The purpose of this study is to assess the smart city for major cities in Korea. The assessment indicators are based on the STIM structure (Service, Technology, Infrastructure, and Management Layer Architecture) of the Multi-Layered Smart City Model. Assessment indicators are established through smart city concepts, case analysis, big data analysis, as well as weighted through expert AHP survey. For the assessment, seven major metropolitan cities are selected, including Seoul, and their data such as KOSIS, KISDISTAT from 2017 to 2019 is utilized for the smart city level assessment. The smart city level results show that the service, technology, infrastructure, and management levels were relatively high in Seoul and Incheon, which are metropolitan areas. Whereas, Busan, Daegu, and Ulsan, the Gyeongsang provinces are relatively moderate, while Daejeon and Gwangju, the South Chungcheong region and the Jeolla provinces, were relatively low. The overall STIM ranking shows a similar pattern, as the Seoul metropolitan area smart city level outperforms the rest of the analyzed areas with a large difference. Accordingly, balanced development strategies are needed to reduce gaps in the level of smart cities in South Korea, and respective smart city plans are needed considering the characteristics of each region. This paper will follow the literature review, assessment index establishment, weight analysis of assessment index, major cities assessment and result in analysis, and conclusion.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.383-386
• /
• 2019

4 차산업혁명의 발달은 전 세계가 건강한 삶에 관련된 스마트시티 및 맞춤형 치료에 큰 관심을 갖게 하였고, 특히 기계학습 기술은 암을 극복하기 위한 유전체 기반의 정밀 의학 연구에 널리 활용되고 있어 암환자의 예후 예측 및 예후에 따른 맞춤형 치료 전략 수립 등을 가능케하였다. 하지만 암 예후 예측 연구에 주로 사용되는 유전자 발현량 데이터는 약 17,000 개의 유전자를 갖는 반면에 샘플의 수가 200 여개 밖에 없는 문제를 안고 있어, 예후 예측을 위한 신경망 모델의 일반화를 어렵게 한다. 이러한 문제를 해결하기 위해 본 연구에서는 고차원의 유전자 발현량 데이터를 신경망 모델이 효과적으로 학습할 수 있도록 2D 이미지로 표현하는 기법을 제안한다. 길이 17,000 인 1 차원 유전자 벡터를 64×64 크기의 2 차원 이미지로 사상하여 입력크기를 압축하였다. 2 차원 평면 상의 유전자 좌표를 구하기 위해 유전자 네트워크 데이터와 Node2Vec 이 활용되었고, 이미지 기반의 암 예후 예측을 수행하기 위해 합성곱 신경망 모델을 사용하였다. 제안하는 기법을 정확하게 평가하기 위해 이중 교차 검증 및 무작위 탐색 기법으로 모델 선택 및 평가 작업을 수행하였고, 그 결과로 베이스라인 모델인 고차원의 유전자 벡터를 입력 받는 다층 퍼셉트론 모델보다 더 높은 예측 정확도를 보여주는 것을 확인하였다.