Joint research project

Where you go is who you are: advanced analysis techniques on mobility data

Project leaders
Chiara Renso, Jose Antonio Fernandes Macedo
BRASILE - CNPq - Conselho Nacional Desenvolvimento Cientifico y Tecnologico
CNR/CNPq 2012-2013
Thematic area
Engineering, ICT and technologies for energy and transportation
Status of the project

Research proposal

A flood of data pertinent to moving objects is available today, and will be more in the near future, particularly due to the automated collection of data from personal location-aware devices. Such wealth of positioning data may enable novel classes of applications of high societal and economic impact, provided that the discovery of consumable and concise knowledge out of these raw data is made possible.

Behavioral patterns can be extracted from the traces of past human activities through a semantic-enriched knowledge discovery process. Here, positioning data are first transformed in semantically enriched trajectory data stored in a database. Then, mobility patterns, the most common movements emerging from data, are computed with data mining algorithms. A further semantic enrichment step is needed to give context-dependent meaning to the discovered patterns. New challenging research topics result from this work. Among them, we believe that studying mobility form a complex network point of view may offer a complementary approach to the human mobility understanding in such complex form of data.
Several application domain may benefit from the results of this research, as mobility management institutions.

Work is organized into Working Packages:

WP1: Semantic Trajectory definitions and storage representation.
The traditional representation of a trajectory only takes into account the geometric aspect in terms of geographic coordinates. But discovering the important places visited, for how long, and the behavior represented by such movement needs an adequate data model for semantic trajectory. An interesting direction is to study trajectory database in connection with the Linked Data paradigm, in particular GeoLinked Data thus allowing interoperability.
WP 1 will be developed during the first year of the project.
WP1 deliverable is planned at the end of the first year.

WP2: Semantic Data Mining and patterns interpretation. The objective of this work package is to investigate knowledge discovery methods that take into account the meaning of the movement data based on the notion of semantic trajectory. This can be done by (1) studying methods that use the contextual information - for example from Linked Data - to mine different properties of a trajectory and (2) proposing post-processing methods to give a context-dependent meaning to the extracted patterns. The new methods will be experimented in trajectory datasets provided to the partners. Brazilian partner will provide case study on Fifa World cup and emergency planning, while Italian partner provide case study on traffic management.
Privacy data mining will also be investigated to preserve individual privacy.

WP2 is the core activity thus the effort will span the two years.
WP2 deliverable is planned at the end of the project.

WP3: New challenges: complex network on mobility data. The objective of this task is to investigate how the complex network paradigm (often used to represent social networks like facebook or twitter) may be employed for analyzing mobility data. Here the challenge is twofold: (1) find an appropriate mapping from mobility data to complex network structures based on nodes and edges, and (2) find novel analysis questions which can be answered by complex network analysis.
WP3: The major effort for this WP is during the second year of the project. WP3 deliverable is planned to be delivered at the end of the project.

WP4: Project management.
The project coordinator is responsible for the management of the project providing the entire infrastructure for administrative and communication needs, such as a web site and repository. A kick-off meeting will be held with remote video conference tools at the project start date in order to plan the project activities. Regular meetings will be held by the two project coordinators to monitor and discuss the project activities. Minutes of each meeting will be stored in the project repository to be available for partners, along with all internal documents, deliverables, datasets and software.
WP4 effort will span the two years.

Project results and diffusion of research
The results of the project will be disseminated to the research community through joint publications. The CVs of the involved researchers prove an existing fruitful collaboration. The scientific excellence of the joint publication also prove the potential for a broad diffusion of the research result.
Another result of the project is training. During the visit we plan to held courses or seminars on our respective expertise. This will help in having a ground terminology and asses the bases for collaboration, besides being an educational training activity for PhD students and young researchers.

The two coordinators and they respective research groups have a long lasting collaboration - since 2008 as witnessed by joint publications and events - and they are currently involved in a FP7 PEOPLE - Marie Curie Action IRSES project called SEEK to be start in march 2012 coordinated by Chiara Renso. The broad topic of SEEK overlaps the present research proposal and this witnesses the fact that there is a strong interest from the EU on mobility knowledge discovery. Moreover, SEEK proves that the know how of the european researchers on data mining needs to be complemented by the brazilian expertize on semantics. However, the present proposal, besides being tailored on semantic trajectory representation and mining, introduces the investigation on complex network with mobility data, an innovative and challenging issue where the synergies and complementariness of the two partners play a crucial role.
In the last few years Brazil has shown an unprecedented increase in the economic development. This is witnessed also by the organization of two big worldwide events: Football cup in 2014 and Olympic games in 2016. We believe that the outcome of the project in understanding human mobility could consistently improve the study of mobility in the context of these two events.

Research goals

The goal of the project is to investigate methods to extract meaningful knowledge from large amount of movement data by defining techniques for an advanced semantic-rich knowledge discovery process. 
We intend to reach the objectives of the project by exchanging staff of the two institutions. During the exchange the staff of the two institutions will collaborate to reach the objectives of the defined WP. The scientific research result will be consolidated into 3  final deliverables corresponding to the Scientific Working Packages:
WP1:  Semantic trajectory definition and representation - Due YEAR 1
WP2: Trajectory Semantic Data mining and Pattern Understanding- Due: YEAR 2
WP3: New challenges in Trajectory knowledge discovery - Due YEAR 2

Last update: 27/11/2021