ThinkSpatial: Gengchen Mai

thinkspatial_log<strong></strong>oThe UCSB forum on spatial technologies presents

Space2Vec: Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells

Gengchen Mai

STKO Lab

University of California, Santa Barbara

11:30 a.m. (PT)

Tuesday, Dec 1, 2020

Zoom:  https://ucsb.zoom.us/meeting/register/tZUtcu6rrzosE9VEnfMGptAxbxe4zhNILoHY

Upon registration, you will receive access to this link

Abstract. Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations (embeddings) based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks. We see a strikingly similar situation in spatial analysis, which focuses on incorporating both absolute positions and spatial contexts of geographic objects such as POIs into models. A general-purpose representation model for space is valuable for a multitude of tasks. However, no such general model exists to date beyond simply applying discretization or feed-forward nets to coordinates, and little effort has been put into jointly modeling distributions with vastly different characteristics, which commonly emerges from GIS data. Meanwhile, Nobel Prize-winning Neuroscience research shows that grid cells in mammals provide a multi-scale periodic representation that functions as a metric for location encoding and is critical for recognizing places and for path-integration. Therefore, we propose a representation learning model called Space2Vec to encode the absolute positions and spatial relationships of places. We conduct experiments on two real-world geographic data for two different tasks: (1) predicting types of POIs given their positions and context, (2) image classification leveraging their geo-locations. Results show that because of its multi-scale representations, Space2Vec outperforms well-established ML approaches such as RBF kernels, multi-layer feed-forward nets, and tile embedding approaches for location modeling and image classification tasks. Detailed analysis shows that all baselines can at most well handle distribution at one scale but show poor performances in other scales. In contrast, Space2Vec ’s multi-scale representation can handle distributions at different scales.

 

Bio. Gengchen Mai is a Ph.D. candidate at the Space and Time for Knowledge Organization Lab in the Department of Geography, University of California, Santa Barbara. His Ph.D. adviser is Prof. Krzysztof Janowicz. His research interests include Machine Learning/Deep Learning, GIScience, Geographic Question Answering, NLP, Geographic Information Retrieval, Knowledge Graph, and Semantic Web. Currently, Mai’s research is highly focused on Geographic Question Answering and Spatially-Explicit Machine Learning models. He received his B.S. Degree in Geographic Information System from Wuhan University. Thus far, he has completed four AI/ML research-based internships at Esri Inc., SayMosaic Inc., Apple Map, and Google X. He now serves as a machine learning consultant/advisor for Google X.

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Marcela Suarez (amsuarez@ucsb.edu), or Karen Doehner (kdoehner@spatial.ucsb.edu)), to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Patricia Murrieta-Flores

thinkspatial_logo
On Tuesday, November 24, 2020, the UCSB forum on spatial thinking presents

Subaltern Spatial Thinking: Towards a decolonial approach to spatial technologies

 

Patricia Murrieta-Flores

Lancaster University

11:30 a.m. Tuesday, November 24, 2020 | Zoom*

Abstract:

The quick emergence of digital technologies and the rise of the use of computational approaches and tools in all disciplines have substantially changed the ways that we do research, expediting and placing at our fingertips datasets and information at a scale that was impossible before. While our societies have enthusiastically embraced this change, technologies are neither unbiased nor innocent. In the wake of Geographic Information Systems (GIS), a now-ubiquitous tool, disciplines such as history and archaeology have adopted this technology for the study of the past. This is well represented in the creation of the field called the Spatial Humanities. Rooted in a modern, western and Cartesian conception of space, while GIS has proved invaluable to advance both research and discussions related to geography, space and place in these fields, there is the need for critical reflection regarding its use, and to work towards the development of more inclusive spatial tools. Given GIS’ increasing popularity in Humanities research worldwide, and especially its emergence in the Global South, I will present a case study from research produced in the project “Digging into Early Colonial Mexico: A large-scale computational analysis of 16th century historical sources”, aiming to showcase how through the analysis of Mesoamerican spatial thinking, we can highlight the need of carefully considering the use of particular technologies in historical research, and discuss a decolonial approach to technology.

Bio:

Patricia Murrieta-Flores is Senior Lecturer and Co-Director of Digital Humanities at Lancaster University. Her interest lies in the application of technologies for Humanities and her primary research area is the Spatial Humanities. Her main focus is the investigation of different aspects of space, place and time using a range of technologies including GIS, NLP, Machine Learning and Corpus Linguistics approaches. Patricia is the PI on the Transatlantic Platform (T-AP) funded project ‘Digging into Early Colonial Mexico: A large-scale computational analysis of 16th century historical sources’, and also collaborator and Co-I in multiple projects funded by the ERC, ESRC, AHRC, HERA, and the Paul Mellon Centre among others. She has edited and contributed to multiple books on Digital Humanities, Cultural Heritage, the use of GIS and other technologies in Archaeology, History, and Literature, and she has published multiple articles exploring theories and methodologies related to space and place. She is currently Executive Board Secretary Elect of the Alliance of Digital Humanities Organizations (ADHO).

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Marcela Suarez (amsuarez@ucsb.edu), Karen Doehner (kdoehner@spatial.ucsb.edu), or Emmanuel Papadakis (epd@ucsb.edu), to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

*This talk is a part of the spatial series Knowledge Representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Karl Grossner

thinkspatial_logo
On Tuesday, October 27, 2020, the UCSB forum on spatial thinking presents

Representing Place for World Historical Gazetteer

 

Karl Grossner

University of Pittsburgh World History Center

11:30 a.m. Tuesday, October 27, 2020 | Zoom*

Abstract:

The recently launched World Historical Gazetteer (WHG) web platform aggregates contributions of information about named places drawn from historical source material by researchers studying the past in numerous humanities and social science fields. There are no constraints upon spatial or temporal extents, nor on scale of features, however, the project focus to date is on populated places, administrative units, natural geographic features, and regions of all kinds. Contributed datasets can be of any size.

To date, the WHG data stores hold records for about 1.8 million places having over 3 million name variants. Of these, only 60,000 have explicit temporal attributes; the remainder have been accessioned from the Getty Thesaurus of Geographic Names (TGN) and have unspecified temporal scope. We anticipate that the temporally scoped portion of WHG data will eventually grow to upwards of 10 million records. The project’s overarching goal is a free global resource useful for:

  1. geocoding of historical source materials, enabling mapping and spatial analysis of individual texts, corpora, and datasets
  2. linking historical research datasets and projects via shared references to places
  3. teaching, particularly geospatial perspectives in History
  4. via APIs, support for digital historical atlases and story maps

Linked Places format
As a data aggregation platform, WHG requires a standard contribution format. Researchers model data to suit their purposes, impacted by the nature of the source material and their conceptual model(s) of the phenomena being studied. We have developed the Linked Places format jointly with the Pelagios project, for use in both systems. Linked Places format is a hybrid: it is valid GeoJSON which has been extended with “when” objects for temporal scoping (GeoJSON-T), and it is valid JSON-LD v1.1, an RDF syntax.

Linked Places format enables relatively rich descriptions of places, including the temporal scoping of names, types, geometries, and relations with other places. We also developed a simpler and less expressive delimited text format, LP-TSV, and an automated transform is performed on ingest to WHG.

Toward Knowledge Representation
In this talk, Grossner will give an overview of Linked Places format, and the somewhat unorthodox path taken in development of its conceptual model, syntax, and supporting ontology. That path reflects the way that ontologies can emerge as working systems are developed, not as an afterthought, but as a product of investigating the entities and relations of a domain as the many variations of entities and properties “in the wild” present themselves.

Bio:

Karl Grossner is an independent GIScience researcher working to develop novel models, standard formats, and semantically-enabled software and systems supporting the emerging genre of digital historical atlases. Broadly, his research interest concern “computing place.” A co-founder of the GeoHumanities SIG within the Alliance for Digital Humanities Organizations (2013), Grossner is an active member of that global and trans-disciplinary community. From 2017 to the present, Grossner has served as Technical Director of the World Historical Gazetteer project at the University of Pittsburgh’s World History Center (whgazetteer.org).

After earning his Ph.D. in Geography at Santa Barbara in 2010, Grossner remained at the Center for Spatial Studies for a year, co-leading the NSF-funded TeachSpatial project (teachspatial.org) with Donald Janelle, the Center’s Program Director at the time. Following that, he worked for five years as a digital humanities research developer at Stanford University, building several significant interactive scholarly web applications in partnership with faculty members. Grossner’s side projects in recent years include GeoJSON-T, a temporal extension to the GeoJSON standard, and Linked Paths, experimental web software for representing, sharing, and analyzing data about historical geographic movement, including journeys, flows, and named routes.

Material:
ThinkSpatial-Grossner

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Marcela Suarez (amsuarez@ucsb.edu), Karen Doehner (kdoehner@spatial.ucsb.edu), or Emmanuel Papadakis (epd@ucsb.edu), to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

*This talk is a part of the spatial series Knowledge Representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Nicola Guarino

thinkspatial_logo
On Tuesday, October 13, 2020, The UCSB forum on spatial thinking presents

Events and their (Spatial) Context: On the Semantics of Locative Modifiers

 

Nicola Guarino

ISTC-CNR Laboratory for Applied Ontology, Trento

9:00 a.m. Tuesday, October 13, 2020 | Zoom*

Abstract:

The notion of event is intimately connected to that of context. Describing an event means not just saying what happened, but also specifying how it happened, by adding details (generically called modifiers) that often involve the broader context where the event occurred. These modifiers often express locative information. But what are we referring to, when we add a locative modifier? This is an issue that has been investigated in the literature on linguistic semantics (especially by Claudia Maienborn), and is still rather open. Consider for instance “Maradona signed the contract in Argentina” versus “Maradona signed the contract on the last page.” While in the first case the modifier clearly denotes the location of the signature event, in the second case it refers to the location of something else. Similarly, in “John kissed Mary on the boat” the semantics of the locative modifier is clear, but in “John kissed Mary on the cheek” the semantics is different. In this talk, I will present a novel theory of events that explains these phenomena in terms of relationships between the modifier and the event’s context. It is a sort of microscopic approach based on the Aristotelian theory of change, according to which the actual subjects of change are individual qualities inhering in the participants, and not the participants themselves. In this view, an event (in its simplest form) is a single quality manifestation, i.e., the occurrence of a change (or unchanged) with respect to one of its qualities. More generally, ordinary events are clusters of quality manifestations, consisting of a focus accounting for what happens, and an internal context accounting for how it happens. Event kinds provide criteria to carve up events from the broader context by determining their focus and their internal context.

Bio:

Nicola Guarino is a retired research associate at the Institute of Cognitive Sciences and Technologies of the Italian National Research Council (ISTC-CNR), and former director of the ISTC-CNR Laboratory for Applied Ontology (LOA) based in Trento. Since 1991 he has been playing a leading role in the ontology field, developing a strongly interdisciplinary approach that combines together Computer Science, Philosophy, and Linguistics. The impact of such an approach is testified by a long list of widely cited papers and many keynote talks and tutorials in major conferences involving different communities. Among the most well-known results of his lab, the OntoClean methodology and the DOLCE foundational ontology. Guarino has been the founder and editor-in-chief (with Mark Musen, Stanford University) of the Applied Ontology journal, founder and former president of the International Association for Ontology and its Applications (IAOA), and editorial board member of Int. Journal of Semantic Web and Information Systems and Journal of Data Semantics. He is also a founding member of the Italian Association for Artificial Intelligence and fellow of the European Association for Artificial Intelligence (EurAI).

On the theoretical side, Guarino’s current research interests are focusing on the ontological foundations of knowledge representation and conceptual modeling and specifically the ontology of events and relationships (collaborating with Giancarlo Guizzardi to the new version of the UFO ontology), while on the application side his research is focusing on enterprise modeling and the ontology of economics. He is also interested in leveraging ontological analysis and semantic technologies to improve cognitive transparency, social accountability, and the participatory governance of artificial intelligence artifacts.

Material:
ThinkSpatial-Nicola-Guarino

The objectives of the ThinkSpatial presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

*This talk is a part of the spatial series Knowledge representation and GeoHumanities; upon registration, you can access all the talks of the series using the provided link.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Martin Doerr

thinkspatial_logo
On Thursday, September 17, 2020, The UCSB forum on spatial thinking presents

Identifiable Individuals and Reality
What Do We Describe and Why

 

Dr. Martin Doerr

Foundation for Research and Technology – Hellas (FORTH)

10:00 a.m. Thursday, September 17, 2020 | Zoom link*

Abstract:

Data of empirical-descriptive sciences, such as cultural heritage studies, geography, geology, biodiversity are usually kept in predicate-logic based information systems that refer to things in reality by unique identifiers. This can only work, if the referred features or phenomena, in reality, are distinct and can diachronically be identified in the same way by independent observers without a dialogue between them. In this presentation, we argue that only a smaller part of the features in our environment is sufficiently distinct over a useful time-span to form “identifiable individuals.” Different ontological categories can provide specific criteria about how parts of reality can be subdivided into “identifiable individuals” that turn out to be useful for modeling the behavior of reality as a result of observation, rather than convention, the so-called ontological individuation. We demonstrate (1) that there are always cases in which individuality is undecidable basically within all such categories, (2) that multiple individuals may overlap in substance in characteristic ways, and (3) that no such individual has precise spatiotemporal boundaries due to a variety of causes.

We argue that the kinds of conditions allowing for ontological individuation have widely not been studied, as well as what properties make phenomena not suited for individuation, such as clouds, stages of growth, flowing matter, and so forth. We further propose that the description of delimited situations in such systems, be it after observation or in prediction, needs to relate to identifiable individuals as reference. This epistemic individuation inherits the indeterminacy of the individuals of reference. We further propose that many kinds of scientific description of reality are an approximation that can be better processed via outer bounds. As a practical application, we show how adequate individuation criteria can substantially reduce the ambiguity of spatiotemporal gazetteers.

Bio:

Dr. Martin Doerr is a Research Director at the Information Systems Laboratory and honorary head of the Centre for Cultural Informatics of the Institute of Computer Science, FORTH. He has been leading the development of systems for knowledge representation and terminology, metadata, and content management. He has been leading or participating in a series of national and international projects for cultural information systems. His long-standing interdisciplinary work and collaboration with the International Council of Museums on modeling cultural-historical information have resulted besides others in an ISO Standard, ISO21127:2006, a core ontology for the purpose of schema integration across institutions.

Material:
ThinkSpatial2020-MartinDoerr

The objectives of the ThinkSpatial presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

* Please contact Karen Doehner, kdoehner@spatial.ucsb.edu or Emmanuel Papadakis epd@ucsb.edu, to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking. If you are participating from outside the UCSB community, please also ask for access credentials.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Liz Ackert

thinkspatial_logo

On Tuesday, June 2, 2020, The UCSB forum on spatial thinking presents

Latinx Destinations and Health

 

Liz Ackert

Department of Geography
University of California, Santa Barbara

11:30 a.m. (PST) Tuesday, June 2, 2020

Zoom* : https://ucsb.zoom.us/j/98445704485

Abstract:

The geography of Latinx areas of residence in the U.S. has shifted dramatically in the past three decades, with the Latinx population increasingly living in urban, suburban, and rural areas outside of established immigrant gateways such as California and Texas. This project addresses the consequences of the geographic diversification of Latinx settlement in the U.S. for patterns of health and well-being among the Latinx population. Amidst the changing geography of Latinx settlement, one question of interest is whether emerging areas of Latinx settlement, including “new” and “other” areas of settlement, have more positive or negative contextual resources and intergroup relations related to health and well-being than established gateways. In this ThinkSpatial talk, I present initial exploratory results from an assessment of variation in health care resources and immigration enforcement policies across three types of Latinx counties: (1) Established Destinations; (2) New Destinations, and; (3) Other Destinations. I draw from an array of publicly-available data sources, including the U.S. decennial censuses, the Health Resources and Services Administration (Area Health Resource Files, Health Professional Shortage Areas data, and Medically Underserved Areas data), the Robert Wood Johnson Foundation (County Health Rankings and Roadmaps), and the Migration Policy Institute and Immigrant Legal Resource Center (287g program participation information). This work has important implications for the current COVID19 pandemic, as it reveals the types of communities where Latinx populations may be lacking health care resources and where they may face contextual barriers to accessing health care.

Bio:

Liz Ackert is an Assistant Professor in the Department of Geography at the University of California, Santa Barbara. Her research interests include racial/ethnic inequality, immigration, education, health disparities, urban geography, and quantitative methods. Her work examines explanations for why racial/ethnic and immigrant-origin groups are unequally distributed across contexts—including schools, neighborhoods, and immigrant destinations—and evaluates the consequences of this contextual inequality for disparities in outcomes in domains such as education, residential mobility, and health. Ackert is particularly interested in understanding how the attributes of immigrant-receiving contexts, including states, communities, neighborhoods, and schools, influence the health and well-being of Latinx  children and youth.

Material:

Ackert_ThinkSpatial_Talk_Web_June2_2020

* Note, if you are participating from outside the UCSB community, please contact epd@ucsb.edu to get access to the credentials.

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Emmanuel Papadakis (epd@ucsb.edu) to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Alina Ristea

thinkspatial_logo

On Tuesday, May 5, 2020, the UCSB forum on spatial thinking presents

Spatial Crime Patterns vs. Safety Perception: Mixed Experiments

 

Alina Ristea

Boston Area Research Initiative (BARI)
School of Public Policy and Urban Affairs
Northeastern University, Boston

11:30 a.m. (PST) Tuesday, May 5, 2020

Zoom* : https://ucsb.zoom.us/j/98445704485

Abstract:
The occurrence of crime depends on a multitude of factors, namely crime attractors or generators, and it shows high spatiotemporal complexity. This presentation is targeting two opposite crime perspectives: (1) objective crime, and (2) subjective crime—perceived crime safety—fear of crime. This work contributes to the research on environmental crime analysis and prediction by pursuing two objectives. The first goal is to uncover spatial relationships between crime occurrences and nearby social media activity, whereas the second goal is to estimate the possible influence of social media posts on crime prediction models. The focus of this part of the presentation is on sporting events, suggesting that spatial crime patterns and people’s social posts are similar on event days and more dissimilar on non-event days. The subjectivity in crime is captured through the lenses of fear of crime. This project is an approach to amalgamate the knowledge about safety features already studied in the urban environment. The primary goal of this work is in using a fusion methodology for integrating a systematic video data acquisition, geographical storytelling, and human physiological measurements to build upon the analysis of the urban environment through a GIS-based platform. The three main objectives of this project are: (1) to test the compatibility of data acquisition through mixed technologies; (2) to extract safety information from the data acquired using mixed methods and to implement it in a GIS-based model; (3) to compare official crime data reported to the police, urban blight indicators, and people’s perceived safety, extracted from the mixed-method approach.

Bio:
Alina Ristea
is a Postdoctoral Research Associate at the Boston Area Research Initiative (BARI), part of the School of Public Policy and Urban Affairs, Northeastern University. She has a Ph.D. in Applied Geoinformatics from the University of Salzburg, Austria (2019), entitled Integration and Evaluation of Social Media in Crime Prediction Models. Her background studies are in the domains of geography, cartography, and Geographic Information Systems (GIS). Ristea’s research interests are highly interdisciplinary, and include interdisciplinary level, focusing among others on combining elements of GIScience, urban informatics, neighborhood effects, spatiotemporal crime analysis, social media mining, predictive analytics, and safety perception. She is a guest editor for the International Journal of Geo-Information (IJGI), by MDPI: Special Issue Urban Crime Mapping and Analysis Using GIS. In addition, she is a member of the International Association of Crime Analysts (IACA) and the American Association of Geographers (AAG). Among others, Ristea won a Marshall Plan Scholarship (February–May 2019), from the Austrian Marshall Plan Foundation, for a research stay at Louisiana State University (LSU).

Material:

ThinkSpatial - Alina Ristea

 

* Note, if you are participating from outside the UCSB community, please contact epd@ucsb.edu to get access to the credentials.

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Emmanuel Papadakis (epd@ucsb.edu) to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Konstadinos Goulias

thinkspatial_logo

On Tuesday, April 28, 2020, the UCSB forum on spatial thinking presents

Life Cycle Stages, Daily Contacts, and Activity—Travel Time Allocation for the Benefit of Self and Others

 

Konstadinos G. Goulias

Department of Geography
University of California, Santa Barbara

11:30 a.m. (PST) Tuesday, April 28, 2020

Zoom: https://ucsb.zoom.us/j/96140245863

Abstract:

In this research, we study the correlation between life cycle stages and time allocation for the benefit of self and others. Life cycle stages are defined based on age, employment, family status, and disabilities. Time allocation is classified based on the people with whom each respondent came into contact and for whom he or she performed activities and travel. Based on a two-day time use diary, daily time allocation is classified in social fields that we define as family, friends, schoolmates, co-workers, clubmates, among others. We also include time for sleeping and activities and personal travel. The data analysis creates a taxonomy using cluster analysis of time-of-day activity sequences, complexity of time schedules, and uncovers its correlation with life cycle stages.

Bio:
Since 2004, Konstadinos (Kostas) G. Goulias has been a Professor of Transportation at the Department of Geography at the University of California, Santa Barbara. From 1991 to 2004 he was Professor of Transportation in the Department of Civil and Environmental Engineering of PennState University, where he also directed research centers. His research is on large-scale transportation systems modeling and simulation, travel behavior dynamics, sustainable transportation, smart cities, economic geography, travel survey methods, geocomputation, and geoinformation. He chairs the International Association for Travel Behaviour Research and he is the co-editor-in-chief of Transportation Letters an international peer-reviewed journal published by Taylor and Francis. He received a Laurea (5 years and a thesis equivalent to M.S.) in Engineering from the University of Calabria (Italy) in 1986, an M.S. in Engineering from the University of Michigan, Ann Arbor, in 1987, and a Ph.D. in Engineering from University of California Davis, in 1991.

The objectives of the ThinkSpatial presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Emmanuel Papadakis (epd@ucsb.edu) to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: George Baryannis

thinkspatial_logo

On Tuesday, April 21, 2020, the UCSB forum on spatial thinking presents

Qualitative Spatial Reasoning Using Answer Set Programming

 

George Baryannis

Department of Computer Science
University of Huddersfield, UK

11:30 a.m. Tuesday, April 21, 2020 | Zoom meeting room:

https://ucsb.zoom.us/j/96140245863

Abstract:

Spatial (and temporal) information is often expressed using qualitative terms such as natural language expressions instead of coordinates; reasoning over such terms has several practical applications, such as naval traffic monitoring, warehouse process optimization, and robot manipulation. Well over 40 qualitative calculi have been proposed so far, including Allen’s interval algebra and the Region Connection Calculus. Reasoning with such calculi has been the focus of extensive research within the wider AI community, with a number of specialized reasoning tools developed. One barrier to the wide adoption of these tools is that only qualitative reasoning is supported natively when real-world problems most often require a combination of qualitative and other forms of reasoning.

I will discuss research to overcome this barrier (conducted at the University of Huddersfield, UK, and the University of Calabria, Italy), focusing on using Answer Set Programming (ASP) as a unified formalism to tackle problems that require qualitative reasoning in addition to non-qualitative reasoning. ASP is a logic-based knowledge representation and reasoning approach that includes a rich but simple modeling language and is capable of handling search problems of high complexity. Research is motivated by two case studies: reasoning about the relations among large numbers of trajectories and determining optimal coverage of telecommunication antennas.

Bio:
George Baryannis is Senior Lecturer (Associate Professor) at the Department of Computer Science of the University of Huddersfield, UK. He received his Dipl.Eng. in Electronic and Computer Engineering from the Technical University of Crete, Greece, and his M.Sc. and Ph.D. in Computer Science from the University of Crete, Greece. His teaching and research interests lie within Artificial Intelligence, mainly focusing on knowledge representation and reasoning, machine learning, and interpretability, as well as applications in supply chain risk management, smart homes, and service-oriented computing.

Material:

ThinkSpatial-QSRASP

 

The objectives of the ThinkSpatial presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Emmanuel Papadakis (epd@ucsb.edu) to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar

ThinkSpatial: Claudio Fogu

thinkspatial_logo

On Tuesday, March 10 June 9, 2020, The UCSB brown-bag forum on spatial thinking presents

The Fishing Net and the Spider Web—

Making Italians Making Southerners

 

Claudio Fogu

Department of French and Italian
University of California, Santa Barbara

12:00 p.m. Tuesday, March 10 June 9, 2020 | 3512 Phelps Hall (map)

 

Abstract:

This talk will discuss the network-theory approach of Grad Malkin’s study of the Archaic Mediterranean and its extension to the history of the modern Mediterranean. Fogu will focus in particular on the role played by the Italian peninsula, coastal communities, and islands in the oscillation among distributed, centralized, and decentralized patterns of connectivity in the Mediterranean.

Bio:

Claudio Fogu moved to Los Angeles in 1983 to study film at UCLA, and later pursued a Ph.D. in History. He taught at Ohio State University and then at USC. Since moving to UCSB in 2005 he has been an Associate Professor of Italian Studies and teaches courses on Italian cultural history and memory, with an emphasis on film and visual culture. He is author of multiple books and is current President of the California Chapters of the American Association of University Professors (CA-AAUP), President of the UC Santa Barbara Faculty Association (UCSB), and Vice-President for External Affairs of the Consortium of UC Faculty Associations (CUCFA).

 

The objectives of the ThinkSpatial brown-bag presentations are to exchange ideas about spatial perspectives in research and teaching, to broaden communication and cooperation across disciplines among faculty and graduate students, and to encourage the sharing of tools and concepts.

Please contact Werner Kuhn (werner@ucsb.edu) to review and schedule possible discussion topics or presentations that share your disciplinary interest in spatial thinking.

Follow spatial@ucsb on Twitter | Google+ | Google Calendar