A Data Science Central Community
Over half of the thousand researchers tried to solve the problem of traffic in big agglomerations. The result? Even 60% improvement in accuracy, an algorithm that can be used in GPS navigation devices to skipthe traffic jams and much more.
Over the last century, number of cars engaged in vehicular traffic in cities has increased rapidly, causing many difficulties for all citizens: traffic jams, large and unpredictable communication delays,
pollution etc. Excessive traffic became a civilization problem that affects everyone who lives in a city of 50,000 or larger, anywhere in the world. Complexity of processes that stand behind traffic flow is so large, that only data mining algorithms - from the domains of structure mining, graph mining, data streams, large-scale and temporal data mining - may bring efficient solutions for these problems. The competitions aim was to devise the best possible algorithms that tackle problems of traffic flow prediction, for the purpose of intelligent driver navigation and improved city planning.
Over half of the thousand of participants tried to solve the problem and took part in the competitions three tasks:
1. Participants tried to predict traffic congestion basing on series of measurements from 10
selected road segments. The goal was to make short-term predictions of future values based on historical ones. The author of the winning solution Alexander Groznetsky fom Ukraine designed an algorithm with only 23% level of mistake which is almost two times better than a basic algorithm used in this task.
2. Modeling the process of traffic jams formation during morning peak in the presence of
roadworks, would be much useful for commuters. Researchers submitted 1298 solutions trying to predict the process basing on the data containing identifiers of road segments closed due to roadworks, accompanied by a sequence of segments where the first jams occurred. The winning algorithm created by Warsaw University Student Łukasz Romaszko
predicts a sequence of segments where next jams will occur in the nearest future. The winning algorithm describes the process more than 30% better than the existing one.
3. Benjamin Hamner a graduate from Duke University was the most successful of
all participants who tried to reconstruct and predict traffic basing on real-time information from individual drivers. Input data consisted of a stream of notifications from 1% of vehicles
about their current GPS locations in the city road network, sent every 10 seconds. The algorithm receives this stream and predicts traffic congestion on selected road segments for the next 30 minutes with accuracy improved by 60% over the baseline. The method used to the creation of the algorithm and the solution itself creates a new opportunity for improvement in the GPS navigation systems. The algorithm works in the exact same way as those used in GPS car navigation system like TomTom Traffic. The algorithm is much useful in choosing the
optimal way to the destination place.
For more details visit: http://tunedit.org/challenge/IEEE-ICDM-2010