The future world under the name of “4th Industrial Revolution” or “Digital Transformation” can be characterized by the keywords, ‘Data’, ‘Smart’, and ‘Connected’, where ‘Spatial’ (Map) is considered the core infrastructure and the realization of the three key words.
Spatial Computing for Sustainable Infrastructure (SCSI) Lab, at Yonsei University has strived to contribute to the future from two perspectives: (1) 3D reconstruction of indoor/outdoor and (2) expansion of spatial data science. This presentation will focus on the second part—the efforts of widening the horizon of spatial data science in new fields of applications such as “Education”.
Higher Education is facing disruptive innovation that requires provision of a more effective and customized education service to individual student. In the field of Learning Analytics (LA), there has been much effort, in the form of the collection and thorough analysis of a variety of student-related datasets, to optimize learning performance and environments by means of personalization. The datasets include traditional questionnaire surveys, student information, and, more recently in the wake of the big-data-analytics trend, unstructured datasets such as SNS activities, text data, and learning management system (LMS) log data of learner activities. Spatial data, however, is rarely considered as a key dataset, despite its high potential for characterization of students and prediction of their performances and conditions. As a new field of application, the speaker has proposed “spatial-data-driven student-characterization”, in which spatial data play a pivotal role of improving modeling quality. Based on two and half years’ data acquisition (Fall 2015 - Fall 2017) with respect to 4,000+ freshman students at residential college, SCSI lab conducted preliminary implementation of descriptive and predictive modeling for students’ achievements, satisfaction, and mental health dynamics. The outcomes were promising enough to substantiate the value of spatial data for educational applications.
Joon Heo is a professor at the department of civil and environmental engineering at Yonsei University. Until spring 2018, he was the first director of Open and Smart Education (OSE) Center, which was formed in 2014 and in charge of MOOC production, Yonsei Learning Management System (YSCEC), and other educational issues. He also served as an associate director of Yonsei Enterprise Support (YES) Foundation from 2009 to 2017, which is in charge of incubating and accelerating start-ups at Yonsei University.
He obtained his B.S. in the Department of Civil Engineering (Urban Engineering Major) from the Seoul National University in 1993, and his M.S. and Ph.D. in Civil and Environmental Engineering from University of Wisconsin-Madison in 1997 and 2001 respectively. In 2000, he joined a start-up company, Forest One Inc., a value-added geospatial information provider and IT consulting company, located in Evanston, IL. For the following five years, he lead technology developments as CTO and provided technical services to Fortune 500 companies. He joined the Department of Civil and Environmental Engineering at Yonsei University in 2005 as a faculty member and has taught Geographic Information System (GIS), photogrammetry, and remote sensing. His areas of research interests include (1) mapping science of outdoor and indoor 3D reconstruction for As-Built BIM and civil infrastructure management; (2) spatial data science covering data collection, management, and analytics with domain specific applications; (3) image processing and remote sensing for natural resource management and construction. He has published over 100 refereed journal papers and over 150 conference papers. He is currently running a MOOC, “Spatial Data Science and Applications” Leave geography site on Coursera.
With the advent of Internet of Things, social media, wearable devices, mobile phones, and planetary-scale sensing there is an ample opportunity to transform big geospatial data into actionable information. The talk focuses on emergency management which is fundamentally a spatio-temporally distributed heterogeneous data assimilation problem for situation recognition. This talk illustrates examples from related projects in our research group and presents key challenges for managing big data.
Rajendra Akerkar is a Professor and Head of Big Data Research Group at Western Norway Research Institute. He has 27 years of experience in knowledge representation and reasoning, data analytics, intelligent systems and requirement engineering. He is actively involved in several international research & innovation initiatives for more than 20 years. Currently he coordinates four major research projects funded by European Commission (Horizon 2020 programme) and the Research Council of Norway on two different topics: ubiquitous data-driven mobility and emergency management. He is a member of IEEE Task Force on Disaster Resilient Smart World. He is serving as an Associate Editor of International Journal of Metadata, Semantics and Ontologies, and Knowledge Management Track Editor of Web Intelligence, an international journal. He is also serving as the scientific committee member of many reputed international conferences. Rajendra has authored 16 books and 145 research papers.
In his important recent essay “Colonial Object Relations,” literary theorist David L. Eng scrutinizes a disturbing and profoundly geographical colonial analogy in the work of Austrian-British psychoanalyst Melanie Klein. Klein compared the process of psychic “reparation,” whereby children repair hateful feelings toward their primary caregivers with feelings of gratitude, to European political reparation for colonial atrocities. Yet in Klein’s political scenario, colonists “make repair” for indigenous genocides by repopulating a territory, not with Indigenous people, but with their own European countrymen. This relay of violence followed by atonement through replacement, Eng argues, lies at the core of “bad faith liberal white guilt.” This talk builds on Eng’s work by examining how phantasies about refugees from the global South can impede meaningful reparation for colonial violence and solidarity with migrants. I illustrate this argument at length with two examples. The first draws on empirical fieldwork I conducted for my first book project with LGBT refugees at a church refugee program in Toronto, Canada from 2011 to 2016. The second previews a new research project on the literary character Paddington Bear, hailed by the International Rescue Committee as “the most famous Refugee in Britain.”
David K. Seitz is a cultural geographer with interests in questions of difference, desire, and citizenship, broadly conceived. He is Assistant Professor of Cultural Geography in the Department of Humanities, Social Sciences and the Arts at Harvey Mudd College. His first book, A House of Prayer for All People: Contesting Citizenship in a Queer Church (2017, Minnesota) examines the affective and spatial dimensions of belonging at a large, predominantly LGBT church in Toronto, Canada. His articles have appeared in Society and Space, Antipode, The International Journal of Regional Research, and Emotion, Space and Society.
The HWISE Network fosters the development of new analytics and theoretical advances, as well as research protocols and standardized assessments to document, benchmark, and understand the causes and consequences of water insecurity at the household level. HWISE partners have completed standardized water insecurity assessments at 28 sites across 4 continents, comprising data from over 8,000 households. Dr. Stoler presents the highlights of ongoing cross-cultural studies using HWISE data, prospects for high-resolution monitoring and evaluation of water insecurity, and implications for the Sustainable Development Goals.
Dr. Stoler is co-PI of the NSF-funded Household Water Insecurity Experiences (HWISE) Research Coordination Network (RCN), a collaborative of 50+ water researchers and practitioners that study household water insecurity in relation to broader socio-environmental challenges.
The Deepwater Horizon oil spill, which occurred from April to July of 2010, was the largest spill in U.S. history. Oil washed onto and damaged thousands of square kilometers of intertidal marsh that had been experiencing elevated rates of erosion for decades. Documenting subsequent change in the spatial distribution marsh plant communities is critical to assess ecosystem impacts and to establish future coastal management priorities. This research investigates the effects of marsh oiling on community dominant plant species distributions and land loss rates and, simultaneously, further validate the use of advanced remote sensing and GIS techniques to address landscape-scale ecological disturbances. The findings suggest that the most important impact of oiling along marsh boundaries is the acceleration of shoreline retreat and land loss. Further, the results imply that marsh responses to oil contamination are highly variable, and wave action is a significant factor in determining marsh recovery trajectories. Without high wave energy, marsh plant communities show signs of recovery within 3 years of oil contamination. Conversely, oiled shorelines that are exposed to high wave energy can accelerate land loss exponentially. Finally, the results demonstrate the value of employing advanced remote sensing and GIS techniques in examining landscape-scale ecosystem changes that are impractical to assess using traditional, field-based quantitative methods.
Dr. Beland (SDSU/UCSB 2018) is an environmental geographer with a specific interest in applying a combination of remote sensing and geospatial tools along with on-the-ground sampling to investigate disturbance and evolution in coastal landscapes with the broad intent of gaining a better understanding of the linkages between natural processes, human activities and coastal ecosystem responses. He is currently a lecturer at California State University, Los Angeles, where he teaches courses in Environmental Science, Global Climate Change and Environmental Applications of GIS.
American Society of Photogrammetry and Remote Sensing
San Diego State University Student Chapter