The short description of the MASTER H2020 RISE Project

1. Multiple Aspect Trajectory Management and Analysis
1
This project has received funding from the European Union's Horizon 2020 research and
innovation programme under Marie-Slodowska Curie grant agreement No 777695

2. 2Consortium
10 partners (6 EU, 1 Canada, 3 Brazil) in blue the
overlapping partners with SEEK
European academic
CNR, Consiglio Nazionale delle Ricerche, IT
UNIVE, Ca’ Foscari University Venice, IT
UPRC, University of Pireaus Research Center, GR
UVSQ, University of Versailles Saint-Quentin , FR
HUA, Harokopio University of Athens, GR
European non academic
Thira, Municipality of Thira, GR
International academic
UFSC, Federal University of Santa Catarina BR
UFC, Federal University of Cearà , BR
PUC, Pontificial University of Rio de Janeiro, BR
DAL, Dalhouise University , CA

3. 3

4. MASTER Budget
4
EU funded 112 secondment months:
 A) Secondments: 2000 * 112 = 224.000
 B1) Research and Training: 1800 * 112 = 201.600
 B2) Management: 700 * 112 = 78.400
Total funded by EU: 504.000
Funded by partner organizations 16 secondment
months equivalent to 16*4500= 72.000 euro
Total project budget 576.000 euro.

5. Research Program
5

6. From raw trajectories to holistic
trajectories
Spatio-temporal trajectories do not properly represent the richness and
complexity of the data.
Many different contextual aspects can be exploited to enrich the spatio-
temporal data.
Holistic trajectories: enrichment of the application-dependent
aspects of trajectories from heterogeneous and multidimensional
data.
Credits to Vania Bogorny (UFSC)
6
Raw trajectory Holistic trajectory

7. Research questions Challenges
How can we create and manage
holistic trajectories?
We need methods for building semantically rich trajectories
from heterogeneous and multidimensional data.
How can we infer interesting
knowledge?
We need data analysis methods capable of taking into account
the different aspects of holistic trajectories. Specifically:
similarity analysis, clustering, graph analysis, prediction and
recommendation.
Which applications may benefit
from the analysis of holistic
trajectories?
We study the impact of the holistic trajectories analysis methods
into the tourism, sea monitoring and public transportation
domains.
How to preserve the privacy of the
individuals?
We need methods based on the privacy-by-design principle
How can we deal with the Big Data
characteristics?
Storage and analysis methods with emphasis on efficiency and
large scale data management.
Research challenges in holistic trajectories
7

8. MASTER - The Concept 8

9. WP1 Management
Leader: CNR
M1-M48
 Task 1.1 Administrative and Financial Management
(CNR)
 Task 1.2 Technical Management (CNR)
Deliverables
D1.1 Project Web site [M3, CNR]
D1.2 First Progress report [M12, CNR]
D1.3 Second Progress report [M36, CNR]
D1.4 Mid Term Meeting [M14, CNR]
9
Milestones
MS2 Mid Term Meeting [M14]

10. WP2: Training Dissemination
and Communication
Leader: CNR
M1-M48
 Task 2.1 Training (UNIVE)
 Task 2.2 Dissemination and Communication (CNR)
Deliverables
D2.1 Training, Dissemination and Communication plans [M4, UNIVE]
D2.2 Dissemination and Communication report [M48, CNR]
D2.3 Training and Networking activities report and material [M48, UNIVE].
10
Milestones
MS6 Final Prototype and final workshop [M48]

11. WP3: Holistic Trajectories
construction and Management
Leader: UNIVE
M1-M36
 Task 3.1 Holistic Trajectories enrichment methods (CNR)
 Task 3.2 Holistic Trajectories Data Management (UNIVE)
 Task 3.3 Privacy issues in holistic trajectories (UVSQ)
 Task 3.4 Big Data solutions for holistic trajectories (HUA)
 Task 3.5 Training (CNR)
Deliverables
D3.1 Data management and enrichment methods for holistic trajectories [M24, UNIVE].
D3.2 Privacy and Big Data issues in holistic trajectory construction and management [M36, UVSQ].
D3.3 Final version of data management and enrichment methods for holistic trajectories [M36, UNIVE].
11
Milestones
MS3 Holistic Trajectory construction and similarity methods [M24]

12. WP4: Holistic trajectories analysis
methods
Leader: HUA
M8-M48
 Task 4.1 Computing Similarity of holistic trajectories (CNR)
 Task 4.2 Machine Learning and Data mining Methods (UVSQ)
 Task 4.3 Privacy issues (UPRC)
 Task 4.4 Big Data solutions (HUA)
 Task 4.5 Future challenges (CNR)
 Task 4.6 Training (UNIVE)
Deliverables
D4.1 First version of similarity measures and analysis methods for holistic trajectories [M24, UVSQ].
D4.2 Final version of similarity measures and analysis methods for holistic trajectories [M42, UVSQ].
D4.3 Future challenges for holistic trajectories [M48, CNR].
D4.4 Big Data and Privacy Issues in holistic trajectory analysis[M48,HUA].
12
Milestones
MS3 Holistic Trajectory construction and similarity methods [M24]
MS5 Holistic trajectories analysis methods [M42]

13. WP5: Application Scenario
Leader: UPRC
M1-M48
 Task 5.1 Tourism (CNR)
 Task 5.2 Sea monitoring (UPRC)
 Task 5.3 Transportation (UNIVE)
Deliverables
D5.1 Requirements for application scenarios [M12, UPRC]
D5.2 Revision of the application scenarios [M24, UPRC]
D5.3 Preliminary software prototypes [M36, CNR]
D5.4 Final report on the application scenarios and software prototypes [M48, CNR].
13
Milestones
MS1 Requirements and Application scenarios for holistic trajectories [M12]
MS4 First Prototype for application scenarios [M36]
MS6 Final Prototype and final workshop [M48]

14. Web site and Social Media
 http://www.master-project-h2020.eu
 Facebook: Master Project H2020
 Twitter: Master Project H2020
14