Project Summary
The three-year 1.98
Million Euro FP7 ADVANCE project started in October 2010 with the
kick-off meeting at Aston University. The project is lead by the
Computer and Automation Research Institute of the Hungarian Academy of
Sciences, Hungary, has academic partners Aston University and University
of Groningen, the Netherlands and industrial partners Technology
Transfer Systems, Italy and Palletways, United Kingdom.
The Aston team consists of Anikó Ekárt, Christopher Buckingham, and
Philip Welch, all from Computer Science, School of Engineering and
Applied Science. Philip joined the group in October as a full time
research fellow on the project, after previously working in the
logistics industry, which is the focus of the Advance project.
The launch had fourteen participants from the five partner institutions
in Hungary, the Netherlands, Italy and UK and was followed by the two
user workshops at Palletways, UK.
One of the main aims of the project is to
increase efficiency of lorry usage by reducing the "delivery of air":
transport industry parlance for lorries running with less than full
capacity.
Logistics networks typically accumulate OVER 1 BILLION new items of
information each month (customer orders, pallets, trailer images,
postcodes, depot data, GPS tracking of vehicles, etc.), generated every
minute of every day by thousands of pallets travelling on hundreds of
trailers for more than one million customers scattered across hundreds
of thousands of postcodes, each with multiple different service
requirements. Every second, thousands of data items come on stream at
any point of the network and need analysis to guide short-term decisions
about lorry deployment (within minutes) as well as longer term plans
for carrying capacity.
We are developing a decision support system to help make management,
operations and planning decisions that may be rapidly changing and not
easily specified in advance. The ADVANCE decision-support engine will
enable strategic planning coupled with instant decision making to
provide vision in a blizzard of data.
Predictive analysis will predict future trends and events based on
current and historical facts.
The patterns and dependencies that exist in the 50 million or more data
elements created daily in logistics networks can only be meaningfully
processed by intelligent data mining approaches linked to strategic
decision making based on longer term analyses of billions of pieces of
information.
The ADVANCE software will have the capacity to analyse massive data sets
for long term planning as well as rapidly processing huge amounts of
new data in real time. It will provide a dual perspective on transport
requirements and decision making dependent on the latest snapshot
information and the best higher-level intelligence.
See the ADVANCE
project website for
more details.
Main University navigation links
