Kyoungsook's Homepage

産総研
last updated 2023.9.9
写真
Profile
金 京淑 (KIM, Kyoungsook)
国立研究開発法人産業技術総合研究所 (AIST)
人工知能研究センター(Artificial Intelligence Research Center (AIRC)
副研究センター長 (Deputy director)
〒135-0064 東京都江東区青海2-4-7
E-mail:ks.kim*aist.go.jp(*を@に変更して使用してください。)
Education
  • 1994.2 Pusan National University, Korea, BS
  • 2001.2 Pusan National University, Korea, MS (Computer Science)
  • 2007.8 Pusan National University, Korea, PhD (Computer Science)
Experience
  • 2007.09 ~ 2007.10 Pusan National Univeristy, PostDoc
  • 2007.11 ~ 2014.03 National Institute of Information and Communications Technology (NICT), Researcher
  • 2014.04 ~ 2016.09 National Institute of Advanced Industrial Science and Technology (AIST), Researcher
  • 2016.10 ~ 2017.08 National Institute of Advanced Industrial Science and Technology (AIST), Senior Researcher
  • 2017.09 ~ 2020.12 National Institute of Advanced Industrial Science and Technology (AIST), Team Leader
  • 2021.01 ~ 2022.03 National Institute of Advanced Industrial Science and Technology (AIST), Planning Officer
  • 2022.04 ~ present National Institute of Advanced Industrial Science and Technology (AIST), Deputy Director
Interests
Geo-enabled Computing Framework based on GIS, Location-based Services, Spatiotemporal databases, Big data analysis, Cyber-Physical Cloud Computing, etc.
Research Projects

AI Data Platforms

I am working on the research and development of an AI data platform to collect, store, manage, and use big data captured from various IoT devices for AI applications. Comparing to traditional data platforms, our AI data platform will allow users to easily and quickly clean, intergrate, and analyze data with machine learning techniques.

Moving Object Analysis

I have designed a new data format (MF-JSON) and interactive visualization tool (Stinuum) for handling moving-object data, such as pedestrians, vehicles, drones, and hurricanes, not only spatiotemporal geometries but also dynamic thematic properties. First, MF-JSON provides an alternative JSON format for encoding moving objects based on OGC Moving Features Encoding standards. In particular, MF-JSON covers the movements of 0-dimensional Point, 1-dimensional curve LineString, and 2-dimensional surface Polygon based on the application requirements such as disaster risk management, traffic information services, and geo-fencing services. Second, the Stinuum (Spatio-temporal continua on Cesium) visualization tool customizes the perspective view of Cesium for the continuum representation of spatiotemporal geometries in a space-time 3D cube whose x-axis and y-axis represent a geographic space and orthogonal z-axis (height) represents time. Comparing with a static 2D map with timelines and animated maps, the space-time cube visualization technique has advantages on the analysis of topological relationships among multiple moving objects. We will show how Stinuum can support a holistic analysis to reduce the cognitive workload needed to understand space, time, and thematic properties of moving objects. More information

Radiation Risk Assessment

After the nuclear power plant accident in Fukushima, significant amount of radioactive materials released into the environment. Five years later, some of evacuees have been allowed to return home permanently, following the enormous decontamination effort. However, many refugees are still suffering from uncertainty as to their prospect of return and fear of radiation. In order to effectively and appropriately manage external radiation doses in the affected areas, it is important to identify the radiation exposure for each person based on his/her life patterns. We have developed a risk assessment tool for Fukushima residents to estimate external doses by using an offline map and airborne survey data. In particular, some local areas still cannot allow the Internet connection. The tool provides an offline map with Leaflet, an open JavaScropt library for integrative maps and open tile maps developed by Geospatial Information Authority of Japan (GSI). This work is a good example how open source software and open data can contribute to our safety and society. More information(Japanese)

Social Media Mining

The role of location-embedded social media is being emphasized to monitor surrounding situations and predict future effects by the geography of data shadows. However, it brings big challenges to find meaningful information about dynamic social phenomena from the mountains of fragmented, noisy data flooding. I have proposed a data model to represent local flock phenomena as collective interests in geosocial streams and present an interactive visual analysis process. Also I have developed a new visualization tool, called RendezView, composed of a three-dimensional map, word cloud, and Sankey flow diagram. RendezView allows a user to discern spatio-temporal and semantic contexts of local social flock phenomena and their co-occurrence relationships. An explanatory visual analysis of the proposed model is simulated by the experiments on a set of daily Twitter streams and shows the local patterns of social flocks with several visual results.
Publications

International

DBLP - Google Scholar - ACM Digital Library(1,2)

Presentations

  • Another Perspective View of Cesium for OGC Moving Features, Kyoung-Sook Kim, Hyemi Jeong, Dongmin Kim, FOSS4G, Boston, USA, Aug. 18, 2017
  • Personal Radiation Exposure Management by using an Offline Map for Fukushima Residents, Kyoung-Sook Kim, Wataru Naito, Hirotaka Ogawa, FOSS4G, Boston, USA, Aug. 18, 2017
  • オフラインのマップを利用した個人の生活パターンによる外部被ばく線量評価支援ツール, 金 京淑、内藤 航、小川 宏高, 第7回地理院地図パートナーネットワーク会議, Jun. 8, 2017
  • Geocognitive Computing Platforms for Smart City Applications, Smart Data Forum and AIST Joint Workshop "Industrie 4.0, Big Data and Artificial Intelligence in Germany and Japan", May 19, 2017
  • RendezView: An Interactive Visual Mining Tool for Discerning Flock Relationships in Social Media Data, Melissa Bica, Kyoung-Sook Kim, The International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2015), Austin, TX, USA, Nov. 17, 2015
  • External Radiation Exposure Estimation by OGC-based Sensor Information Platforms, Kyoung-Sook Kim, Isao Kojima, Hirotaka Ogawa, FOSS4G, Seoul, Korea, Sept. 18, 2015
  • RALFIE: Reduce Potential Radiation Exposure by OGC-based Sensor Information Platforms”, OGC TC – Health Domain Working Group, Barcelona, Spain, Mar. 10, 2015
  • Migration From Grid To Cloud: Case Study from GEO Grid, Geospatial World Forum 2014, Geneve. May 9, 2014
  • Challenges and Opportunities for Cyber-Physical Cloud Computing, クラウド協議会第38 回ワークショップ「インタークラウドとオープン化」, Mar. 2013
  • Cyber Physical Data Cloud: An Event Processing System for Real-World Awareness, AAAS Annual Meeting 2013 (USA), Feb. 16, 2013
  • Cyber-Physical Cloud Computing as a Future Cloud, NIST Joint Cloud and Big Data Workshop (NIST), Gaithersburg, MD, USA, Jan. 15-17, 2013
  • Cyber-Physical Data Cloud Computing for Real-World Awareness, Cloud Computing Forum & Workshop V (NIST), Washington, DC, USA, Jun. 5-7, 2012
  • Towards Information Service-Controlled Networking, Korean-Japan APII Workshop, BEXCO, Busan, South Korea, Sept. 30, 2011

Awards

  • Best Paper Award, LBSN 2014: Sophy: a Morphological Framework for Structuring Geo-referenced Social Media
  • Best Demonstration Award Runners up, ACM SIGSPATIAL 2011: mTrend: Discovery of Topic Movements on Geo-microblogging Messages
  • Best Paper Award, W2GIS 2009: Moving Phenomenon: Aggregation and Analysis of Geotime-Tagged Contents on the Web

Others(Not Listed)

  • "Stinuum: A Holistic Visual Analysis of Moving Objects with Open Source Software", Kyoung-Sook Kim, Dongmin Kim, Hyemi Jeong, Hirotaka Ogawa: 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2017), Redondo Beach, California, USA, Nov. 7-10, 2017, (to appear)
  • "OGC Moving Features Encoding Extension - JSON" OGC. Best Practice OGC 16-140r1, 2017.
  • "MixedWalk: Explore Ahead Before Stepping in Mobile Augmented Reality Services", Jun Lee, Kyoung-Sook Kim(ca), Hirotaka Ogawa, Yongjin Kwon: 6th IEEE International Conference on AI & Mobile Services (AIMS 2017), Hawaii, USA, June 25-30, 2017, pp. 62-69, doi: 10.1109/AIMS.2017.17
  • "Towards Open Interfaces of Smart IoT Cloud Services", Kyoung-Sook Kim, Hirotaka Ogawa: Conference of Korea Institute of Information and Communication Engineering, 20(01), pp. 0235 ~ 0238, 2016 (Korea Domestic/English)
  • "A Vision of Cyber-Physical Cloud Computing for Smart Networked Systems", Eric D Simmon, Kyoung-Sook Kim, Eswaran Subrahmanian, Ryong Lee, Frederic Jean Marie de Vaulx, Yohei Murakami, Koji Zettsu, Ram D Sriram: NIST Interagency/Internal Report (NISTIR) 7951, 2013
  • "Complementary Integration of Heterogeneous Crowd-sourced Datasets for Enhanced Social Analytics", Ryong Lee, Kyoung-Sook Kim, Komei Sugiura, Koji Zettsu and Yutaka Kidawara: Proc. of Workshop on Field Speech and Mobile Data, Milan, Italy, pp. 234-243, 2013.6.3 (International/English)
  • "Service-Controlled Networkingに基づくネットワークフローの動的制御手法", 木全 崇, 豊村 鉄男, 金 京淑, 是津 耕司: 電子情報通信学会技術研究報告, Vol.112, SC2012-2, pp.7-12 ((Japan Domestic/Japanese))
  • "Spatiotemporal Analysis of Geoweb Media", Kyoung-Sook Kim: 情報通信研究機構季報 58(3・4), pp.165-176, 2012.9 (Japan Domestic/Japanese)
  • "Towards Open Sharing and Universal Access to Heterogeneous Natural and Social Sensing Data", Ryong Lee, Eloy Gonzales, Kyoung-Sook Kim, Koji Zettsu: 電子情報通信学会技術研究報告, Vol.111, No.173, DE2011-29, pp.13-18 (Japan Domestic/Japanese)
  • "Path Query Processing for Moving Objects on Road Networks", Kyoung-Sook Kim, Koji Zettsu, Yutaka Kidawara, Yasushi Kiyoki: The Workshop on Mobile Information Retrieval, 2008.7 (International/English)
  • "A New Indexing Method for Trajectories of Moving Objects on Road Networks", Kyoung-Sook Kim, Ki-Joune Li: The KIPS transactions Part D, 13(7), pp. 879-888, 2006.12 (Korea Domestic/Korean)
  • "Query Routing in Road-based Mobile Ad-hoc Networks", So-Young Hwang, Kyoung-Sook Kim, Ki-Joune Li: The KIPS transactions Part D, 12(2), pp. 259-266, 2005.4 (Korea Domestic/Korean)
  • "Analysis of Outlier Effects on Spatial Indices", Si-Wan Kim, Kyoung-Sook Kim, Ki-Joune Li: The Journal of GIS Association of Korea, 12(4), pp. 333-349, 2004.12 (Korea Domestic/English)
  • "Design and Implementation of Query Processor for Moving Objects", Kyoung-Sook Kim, O-je Kwon, Hee-Young Byun, Dea-Soo Jo, Tae-Wan Kim, Ki-Joune Li: Journal of the Korea open GIS association, 6(1), pp. 31-50, 2004.6 (Korea Domestic/Korean)