Information Technology Reference
In-Depth Information
Predicting Road Accidents Based on Current
and Historical Spatio-temporal Traffic Flow Data
Rupa Jagannathan
1
, Sanja Petrovic
1
, Gavin Powell
2
, and Matthew Roberts
2
1
Division of Operations Management and Information Systems, Nottingham University
Business School, Nottingham, UK
{rupa.jagannathan,sanja.petrovic}@nottingham.ac.uk
2
Innovation Works, EADS, UK
{gavin.Powell,matthew.roberts}@eads.com
Abstract.
This paper presents research work towards a novel decision support
system that predicts in real time when current traffic flow conditions, measured
by induction loop sensors, could cause road accidents. If flow conditions that
make an accident more likely can be reliably predicted in real time, it would be
possible to use this information to take preventive measures, such as changing
variable speed limits before an accident happens. The system uses case-based
reasoning, an artificial intelligence methodology, which predicts the outcome of
current traffic flow conditions based on historical flow data cases that led to ac-
cidents. This study focusses on investigating if case-based reasoning using spa-
tio-temporal flow data is a viable method to differentiate between accidents and
non-accidents by evaluating the capability of the retrieval mechanism, the first
stage in a case-based reasoning system, to retrieve a traffic flow case from the
case base with the same outcome as the target case. Preliminary results from
experiments using real-world spatio-temporal traffic flow data and accident data
are promising.
Keywords:
Traffic flow, road accidents, spatio-temporal data, case-based
reasoning.
1
Introduction
The aim of this research work is to predict when current traffic conditions make the
occurrence of road accidents more likely. If traffic conditions can be analysed in real-
time and assessed for their safety with respect to road accidents, preventive measures
can be taken, such as changing variable speed limits, to avoid accidents. According to
the Department of Transport, out of 151474 road accidents in the UK in 2011, 75708
accidents happened on major roads, i.e. motorways and 'A' roads [1]. Apart from the
human loss, the total national financial cost of road accidents has been estimated to
amount up to 2.5% of the gross national product [2].
There are many factors that can influence the risk of road accidents such as human
error, weather and visibility conditions, vehicle conditions, etc. Another major factor
is traffic flow. Traffic flow refers to interactions between vehicles, drivers, and
