Learn about how the Transforming Transport Lighthouse Project is helping to transform the Transport and Logistics domains using big data technologies. Lessons learned, pitfalls, innovation potential and business insights.
4. About TT
EU Horizon 2020 Big Data Value PPP Large Scale Pilot Action
• Demonstrates transformations big data has on mobility and logistics
• Part of
• 48 members - 18.7 MEUR budget - 30 months duration
4
6. TT Methodology
Rationale
• Each data set, domain, use case is different
• Diversity of data sources and infrastructures
• “No free lunch”
Each pilot
• Analytics solutions best suited for requirements and data
• Infrastructure best linked to data sources
• Big data pipelines and tools fit for purpose
Cross-cutting sharing of
• best practices, architecture patterns, KPIs, lessons learned, …
6
7. TT Methodology
3-Stage validation
and scale-up
Stage Embedding Scale of Data
Technology
Validation
Problem understanding and
validation of key solution ideas
(Historic) data pinpointing
problems and opportunities
Large-scale
Experiments
Controlled environment (not
productive environment)
Large historic and real-time data,
possibly anonymized / simulated
In-situ (on site)
trials
Trials in the field, involving actual
end-users
Real-time, live production data
complementing historic data
7
8. Transport Innovation via
Big Data
8
(IconSource:DHL/DETECON)
Efficiency
Customer
Experience
Business
Models
Smart Highways ++ ++ o
Sustainable Connected Vehicles ++ ++ o
Proactive Rail Infrastructures ++ + o
Ports as Intelligent Logistics Hubs ++ + o
Smart Airport Turnaround ++ + +
Integrated Urban Mobility ++ ++ o
Dynamic Supply Networks + + +
New
Business
Models
Improved
Operational
Efficiency
Better
Customer
Experience
Transport Domains
9. Transport Innovation via
Big Data
9
Run-time
visualization of
operations to
increase terminal
productivity
Deep Learning for
proactive transport
management
Enhanced decision
support for terminal
operators (risk and
reliability of
warnings)
Predictive analytics for proactive terminal process
management
@ duisport inland port terminal
10. Transport Innovation via
Big Data
10
Deep learning for proactive terminal management
Integrated data of container moves
(10,000 moves / month)
Data Integration
and Aggregation
(GPS / XYZ mapping;
from states to moves)
Data streams from terminal equipment
(1.3 mio states / month)
11. Transport Innovation via
Big Data
11
Deep learning for proactive terminal management
0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0 10 20 30 40 50 60 70 80 90
Diagrammtitel
nums2enoplannednopath mlp
Checkpoint [sequence prefix]
Accuracy[MCC]
RNN
MLP
Predicting Delays in Container Transport
(Recurrent Neural Networks)
+42%
Prediction Reliablity for Decision Support
(Ensemble Neural Networks / Bagging)
Cost Savings
Frequency
Cost savings of
14% on average
[Metzger & Föcker, “Predictive business process monitoring
considering reliability estimates”, CAiSE 2017]
[Metzger & Neubauer, “Considering non-sequential control flows for
process prediction with recurrent neural networks”, SEAA 2018]
12. Transport Innovation via
Big Data
12
Advanced analytics
solutions (Indra
HORUS) for improved
traffic distribution
along road corridor
Better information
and decision tools for
road users
Real-time incident
warnings based on
novel sensor
technology
Improved driving and travel experience
@ CINTRA/Ferrovial-managed highways
13. Transport Innovation via
Big Data
13
Real-time road incident warnings using novel sensor technology
Optical fiber-based sensor
(0.88 GB/sec)
Time
Distance
Filtered data
(1-5 GB/day)
Isolating Signals from Noise
(classification, adaptive
thresholds, clustering etc.)
= 3,500 virtual sensors
14. Transport Innovation via
Big Data
14
Real-time road incident warnings using novel sensor technology
Individual Mobility Pattern Detection
(trucks)
Aggregate Mobility Pattern Detection
(traffic jams)
15. Transport Innovation via
Big Data
Data-driven decision making in retailing
@ Athens International Airport
15
Advanced big data
analytics solutions
(Indra INPLAN) to
anticipate
passenger flow and
preferences
Adapt marketing to
expected passenger
typology per time
slot
Use data insights to
exploit market
niches
16. Conclusions
Opportunities
Deep learning
e.g., RNNs
Cross-sector data sharing
e.g., TT Data Portal
Challenges
Data protection
e.g., GDPR vs. IPR
Lack of skills
e.g., lack of up ½ million data
professionals in 2020 [IDC]
16
0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0 10 20 30 40 50 60 70 80 90
Diagrammtitel
nums2enoplannednopath mlp
Checkpoint
Accuracy
„deep“
„classical“
Commercial data: 68%
Personal data: 1%
17. Thank You!
17
This project received funding from the European Union’s Horizon 2020
research and innovation programme under grant agreement no. 731932
Contact:
Andreas Metzger
paluno
andreas.metzger@paluno.uni-due.de
Skype: ammetzger
http://www.transformingtransport.eu