Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS
Anonymous Analyses of Mobility Data? Yes we can!
Mobility Minings most recent paper Privacy-preserving Distributed Monitoring of Visit Quantities describes a new approach of processing movement data locally. The idea behind the concept is that several spatially distributed sensors collect movement data and automatically transmit their data anonymously to a central coordinator, which generates the global movement statistics. The poster was presented during the 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2012) by Dr. Christine Kopp.
Abstract: "The organization and planning of services (e.g. shopping facilities, infrastructure) requires quantitative information about the number of customers and their frequency of visiting. In this paper we present a framework which enables the collection of quantitative visit information for arbitrary sets of locations in a distributed and privacy-preserving way. While trajectory analysis is typically performed on a central database requiring the transmission of sensitive personal movement information, the main principle of our approach is the local processing of movement data. Only aggregated statistics are transmitted anonymously to a central coordinator, which generates the global statistics. In this paper we present our approach including the methodical background that enables distributed data processing as well as the architecture of the framework."
Authors: Dr. Christine Kopp, Dr. Michael Mock & Dr. Michael May
Link to poster.
Link to paper.
Finding Movement Patterns in Spatiotemporal Data
Mobility Mining has been working on a new approach to analyze spatiotemporal data from mobile phones in a privacy-preserving way in order to find and extract movement patterns of objects.
The results were presented at the 20th European Conference on Artificial Intelligence (ECAI 2012)" during the the workshop "Ubiquitous Data Mining 2012".
Abstract: "The increasing amount of mobile phones that are equipped with localization technology offers a great opportunity for the collection of mobility data. This data can be used for detecting mobility patterns. Matching mobility patterns in streams of spatiotemporal events implies a trade-off between efficiency and pattern complexity. Existing work deals either with low expressive patterns, which can be evaluated efficiently, or with very complex patterns on powerful machines. We propose an approach which solves the trade-off and is able to match flexible and sufficiently complex patterns while delivering a good performance on a resource-constrained mobile device. The supported patterns include full regular expressions as well as relative and absolute time constraints. We present the definition of our pattern language and the implementation and performance evaluation of the pattern matching on a mobile device, using a hierarchy of filters which continuously process the GPS input stream."
Authors: Simona Florescu, Michael Mock, Christine Körner & Michael May
Movements at major events
In cooperation with the Zoo Duisburg Mobility Mining installed several Bluetooth-Sensors in the microcosm to analyze a) how visitors actually move through the area and b) how long people stay at certain points of interest. A selection of very interesting results from the Duisburg Zoo project were presented during the 24th Applied Geoinformatics (AGIT 2012) Conference in Salzburg, Austria.
Analyse von raum-zeitlichen Bewegungsmustern auf Basis von Bluetooth-Sensoren, Abstract (in german): "Informationen über das Kundenverhalten sind ein wesentlicher Forschungsbestandteil im Bereich des Marketings. Dabei hilft das Verstehen von Entscheidungsfindungsprozessen des potentiellen Kunden - in einem raum-zeitlichen Wechselspiel mit seiner Umgebung - dem Anbieter die Qualität seines Produktes aufzuwerten. Bis vor kurzem wurden Veränderungen am Produkt häufig durch Trial-and-Error-Methoden vorgenommen; heute jedoch erlauben neuartige Technologien - wie beispielsweise Bluetooth, GPS oder Video – neue Möglichkeiten dem Anbieter zielgenaue Qualitäts-Validierungen seiner Produkte durchzuführen. In dem vorliegenden Beispiel wird der vorangehende Sachverhalt auf die Mobilität im Duisburger Zoo übertragen. Repräsentative Daten über das Bewegungsverhalten der Besucher werden unter Wahrung der Privatsphäre in einem langen Versuchszeitraum anhand von Bluetooth-Tracking erfasst, anschließend problemspezifisch aufbereitet, analysiert und interpretiert."
Authors: Timothy Ellersiek, Thomas Liebig, Dirk Hecker & Christine Körner
Link to paper.
MODAP & Mobility Mining launch their second workshop
Within the framework of MODAP (Mobility, Data Mining and Privacy) we are launching our second workshop with the topic Mobile Analytics Meets Social Media. The workshop presents new ways to collect mobility data based on existing technologies (e.g. GPS, Bluetooth or GSM). In addition, it introduces successful mobility-based business models and application scenarios. Furthermore, the workshop gives insight into innovative analysis methods and applications combining mobility and social media data. The workshop consists of invited talks, a panel discussion as well as a demonstration and poster session. The latter provides the opportunity of a vivid exchange of information and thoughts between the participants.
Human Mobility from GSM Data - A Valid Alternative to GPS?
Characteristics of human mobility are a valuable source of information in many applications. Within the frame of the Mobile Data Challenge (MDC) 2012 Mobility Mining evaluates the usability of call detail records for the extraction of mobility quantities and shows that GSM activity data underestimates average daily travel distance and radius of gyration when derived straightforward from the data.
"The Mobile Data Challenge (MDC) releases the Lausanne data for the research community. The challenge provides an opportunity to analyze a comprehensive and relatively unexplored data set including rich social and geographic information. "
Abstract: "Characteristics of human mobility are a valuable source of information in many applications. In this paper we evaluate the usability of call detail records for the extraction of mobility quantities. We derive several quantities from the simul-taneously collected GPS and GSM mobility data of the Nokia Mobile Data Challenge. Our analyses show that GSM activity data underestimates average daily travel distance and radius of gyration when derived straightforward from the data. In addition, they indicate that the correlation between mobile phone usage and movement quantities is biased when using GSM activity data. Finally, our analyses conrm that long-term GSM activity data is well suited to detect frequent stop locations."
Authors: Daniel Schulz, Sebastian Bothe & Christine Körner
Reality Monitoring – Be Ahead with Real Time Data
Mobility Mining will be present at this years CeBIT contributing hot topics all around Reality Monitoring. We are looking forward to see you there!
Detecting critical events or events related to damage require a swift reaction, respectively. Novel methods for analyzing mobile data and Twitter messages create a headstart of knowledge, as events can not only be detected in real time, but can also be monitored. With "Reality Monitoring", the Fraunhofer IAIS presents intelligent methods to support the process of decision-making and visual preparation of data. Making mobile data accessible for not only methods of analysis, but also for visualisation purposes, offers novel and innovative insights for location planning or traffic forecasting.
Reality Monitoring - Fields of Competence
- How can large critical incidents be detected in near real time?
- How can semantics be detected in huge quantities of twitter data?
- Which data are suitable for monitoring mobility behaviour after critical incidents?
- How can decision-makers be supported by visual analytics?