I am the team leader of Data Platform Research Team at the Artificial Intelligence Research Center (AIRC) of AIST in Japan. I served as a researcher of National Institute of Information and Communications Technology (NICT) in Japan from Nov. 2007 to Mar. 2014. I received my B.S., M.S., and Ph.D. Degrees in Computer Science from Pusan National University in Korea in 1998, 2001, and 2007, respectively.
My research interests are in Geo-enabled Computing Framework based on GIS, Location-based Services, Spatiotemporal databases, Big data analysis, Cyber-Physical Cloud Computing, etc.
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.
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
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)
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.