3DGeo Research Group PhD Graduate School: CrowdAnalyser

• Project: Joint Graduate School between Computer Science and Geoinformatics Research Group, Department of Geography, University of Heidelberg
• Funding: Landesgraduiertenförderung Baden-Württemberg
• Duration: 2012–2015
• Principal Investigators:  Prof. Dr. Alexander Zipf (Speaker), Prof. Dr. Michael Gertz, Jun. Prof. Björn Ommer, Jun. Prof. Bernhard Höfle
• Associated PostDocs: Dr. Hongchao Fan, Dr. Mohamed Bakhilla, Dr. Jamal Jokar Arsanjani, Dr. Stefan Hahmann, Dr. Maxim Rylov, Dr. Adam Rousell, Dr. Joao Porto
• Associated PhD students: Enrico Steiger, René Westerholt, Nicolas Billen, Martin Hämmerle, Katarina Gavrić, Nima Sedaghat Alvar, Helen Dorn, Yeran Sun, Amin Mobasheri, Ming Li, Maxim Rylov, Johannes Lauer, Clemens Jacobs

A key characteristic feature of the Web 2.0 is that data is voluntarily provided by users on the Internet through portals such as Wikipedia, YouTube, Flickr, Twitter, Blogs, OpenStreetMap, and various social networks at an unprecedented scale and staggering rate. In today’s information society and knowledge economy these portals provide a valuable resource for diverse application domains. The enormous potential of this voluntarily generated (crowdsourced) data through the masses of volunteers (crowd) is increasingly recognized, but in many areas, especially in science, it is not utilized to its full potential. There are several unsolved issues that arise from these rapidly increasing, very dynamic and highly heterogeneous data streams of content created by users. Addressing these issues has the goal to automatically assess and develop this new type of poorly structured data for different application domains, in particular, to infer new information. The participating research groups in Heidelberg have done pioneering work in these directions, especially in the context of utilizing geographic data. The objective of the college is to develop novel methods and approaches towards the quality-oriented analysis and exploration of crowdsourced Web 2.0 data as well to further improve and scale existing methods. In comparison to existing efforts, especially the following two key points are considered as new aspects towards such approaches:

a.) The temporal aspect of dynamically changing data – in addition to the more typical geospatial and semantic aspects – needs to be a fully integrated into these approaches.

b.) In order to significantly improve analytical approaches, it is essential to combine heterogeneous streams of data (text, video, images, geospatial data). So far, such data streams have only been studied in isolation. By considering possible relationships between data streams the quality of information extraction approaches and enrichment of the base data can be improved significantly.

The reference frame considered in this research is composed of space, time, and semantics. By combining these axes we expect major improvements of data analysis techniques and novel insights into the exploration processes. By joining the expertise of the research groups participating in this college, research on above topics and problem settings can be conducted effectively.

• Extraction and Enrichment of Event-Data
• Real-time prediction and finding of alternative routes
• Extending visual object recognition with textual metadata
• Improving OpenStreetMap through machine learning
• Crowdsourcing 3D: Fusion of 3D and dynamic geodata from technical and human sensors

Martin Hämmerle:

My fascination of working with 3D geodata started with the first time I turned a self-captured point cloud on the screen and was thus catapulted into the third dimension (for own flying lessons see, e.g., the point cloud of the Dechen Cave). 3D geodata are increasingly used for capturing and modelling natural objects and spatial processes. With a growing toolbox of sensors and methods, there are more and more possibilities of working with data from different sources. My PhD project aims at exploring the value and usage of crowdsourced 3D geodata with respect to different applications in various thematic domains.

Enrico Steiger:

Real-time social sensor data could be used directly or indirectly to derive spatiotemporal human mobility- and motion patterns on a city scale level. My research objective is to develop novel methods and approaches towards the quality-oriented analysis and exploration of crowd-sourced social-media data. I'm focused on the overall question how spatiotemporal patterns in ubiquitous sensor networks and heterogeneous data streams can be explored, extracted, validated and aggregated in order to be able to sense urban geo-processes and to gain knowledge about urban dynamics. The identification of mobility hubs and the extraction of movement trajectories could be used to understand, enrich and improve mobility and intelligent transportation systems (ITS).

René Westerholt:

My research deals with investigating scale-driven effects that affect the analysis of social media data. Social media captures a variety of real-world phenomena. Each of the captured phenomena takes place on a certain spatial scale range. Therefore, these data are particularly susceptible to scale effects, due to their mixed-scale nature. The goal of my research is to discover new geostatistical methods for scale-sensitive dealing with social media data. A specific focus of this research is on the investigation of Twitter Tweets.

Invited Talks

Prof. Paul Longley: The provenance and use of geospatial Big Data, 10-11am s.t., Seminar room (room 104)

This presentation reports on the research activities of the Consumer Data Research Centre (CDRC), which is one of the UK’s current ‘Big Data’ investments funded by the Economic and Social Research Council (ESRC). Established in 2014, the CDRC’s mission is to bring sharper focus to the deployment and use of business and social media data, in support of decision-making across a widening spectrum of applications. After describing the three tier service structure of the CDRC, this presentation sets out the range of applications that are under development, the researcher and user interfaces that have been devised, and the ways in which business data may be evaluated and linked to conventional social survey sources. The presentation then focuses upon issues of establishing the provenance of business and social media data, and the wider implications of Big Data for the practice of social science. It also discusses some practical ways in which the value of new data sources may be reliably assessed.

Prof. Paul Longley is a lead scientist at University College of London (UCL).

Guy Lansley: Small area profiling through geodemographics, 11-12am s.t., Seminar room (room 104)

Guy Lansley will present research results from an extended case study of the use of address register and Twitter geo-temporal demographics to understand the activity patterns of different ethnic groups in London. These patterns are linked to the geography of residence as depicted using conventional data sources such as the UK Census of Population.

Guy Lansley is a research associate at University College of London (UCL).

Guy Lansley: Geodemographic analysis using R: Hands-on workshop, 1-3pm s.t., CIP Pool (room 003)

Guy Lansley will hold a workshop which provides attendees with the basic theoretical and practical knowledge necessary to produce a valid geodemographic segmentation from small area population data. The lecture will provide an introduction to geodemographic classifications as a useful tool for neighbourhood insight. It will then give an overview of the key analytical steps necessary to build a geodemographic segmentation from large data sets on the population. Focusing on Census data from the UK, the following computer practical will provide an opportunity for attendees to develop their own skills by building and then visualising a geodemographic classification from population data using open software (namely R and QGIS).

Prerequisite: basic experience in R

Friday, 27th of November 2015 (talks & workshop)

• Berliner Straße 48, Seminar Room (Room 104), 1st floor
• Schedule:
  • 1st talk: 10-11am s.t.
  • 2nd talk: 11-12am s.t.
  • Lunch break: 12-1pm s.t.
  • Hands on workshop: 1-3pm s.t.
  • Coffee break & talk: 3-5pm s.t.
  • Social Event Christmas market: 6pm s.t.
  • Pre-Christmas Dinner Kulturbrauerei Heidelberg: 8pm s.t.
• From the main trainstation: Tramlines 21 (direction 'Hans-Thoma-Platz') or 24 (direction 'Handschuhsheim Nord'), stop 'Technologiepark'
• From Bismarckplatz: Bus 31 (direction 'Kopfklinik'), stop 'Technologiepark'

Invited Talks

Dr. Gennady Andrienko: Space, Time, and Visual Analytics

Visual analytics aims to combine the strengths of human and electronic data processing. Visualization, whereby humans and computers cooperate through graphics, is the means through which this is achieved. Seamless and sophisticated synergies are required for analyzing spatio-temporal data and solving spatio-temporal problems. In modern society, spatio-temporal analysis is not solely the business of professional analysts. Many citizens need or would be interested in undertaking analysis of information in time and space. Researchers should find approaches to deal with the complexities of the current data and problems and find ways to make analytical tools accessible and usable for the broad community of potential users to support spatio-temporal thinking and contribute to solving a large range of problems.

Dr. G. Andrienko is a lead scientist at Fraunhofer Institute IAIS and professor (part-time) at City University London.

Dr. Daniel Kondermann: Can we crowdsource low-level vision?

Dr. D. Kondermann will present several approaches to crowdsourcing in computer vision and the key factors for determining whether crowdsourcing is feasible for a given project or not. To underline the ideas, he will present three recent publications for crowdsourced object contour and feature correspondence estimation and subsequent optical flow estimation. Results indicate that even for low-level vision crowdsourcing can be used, but that the design of the user interfaces has tremendous influence on the quality of the results.

Leaflet

Download the workshop leaflet with information about the talks, schedule, etc. here. (A printer-friendly version you can find here. It is also provided in print at the workshop.)

Venues

Thursday, 8th of May 2014 (talks)

• Speyrer Straße 6, room H2.22, 2nd floor
• The nearest Bus stops are Speyerer Straße (Lines 717, 720, 721) and Montpellierbrücke (HSB 26, 33, 96), both located directly across the street.
• The HCI is within walking distance of the Main Train Station (Heidelberg Hauptbahnhof). For detailed walking instructions, click 

  here

  .

Friday, 9th of May 2014 (hands-on workshop)

• Berliner Straße 48, room 003, ground floor
• From the main trainstation: Tramlines 21 (direction 'Hans-Thoma-Platz') or 24 (direction 'Handschuhsheim Nord'), stop 'Technologiepark'
• From Bismarckplatz: Bus 31 (direction 'Kopfklinik'), stop 'Technologiepark'