Short-term prediction of traffic flow using a binary neural network

TY - JOUR

T1 - Short-term prediction of traffic flow using a binary neural network

AU - Hodge, Victoria J.

AU - Krishnan, Rajesh

AU - Austin, Jim

AU - Polak, John

AU - Jackson, Tom

N1 - © Natural Computing Applications Forum 2014. This is an author produced version of a paper accepted for publication in Neural Computing and Applications. Uploaded in accordance with the publisher's self-archiving policy.

PY - 2014/12

Y1 - 2014/12

N2 - This paper introduces a binary neural network-based prediction algorithm incorporating both spatial and temporal characteristics into the prediction process. The algorithm is used to predict short-term traffic flow by combining information from multiple traffic sensors (spatial lag) and time-series prediction (temporal lag). It extends previously developed Advanced Uncertain Reasoning Architecture (AURA) k-nearest neighbour (k-NN) techniques. Our task was to produce a fast and accurate traffic flow predictor. The AURA k-NN predictor is comparable to other machine learning techniques with respect to recall accuracy but is able to train and predict rapidly. We incorporated consistency evaluations to determine if the AURA k-NN has an ideal algorithmic configuration or an ideal data configuration or whether the settings needed to be varied for each data set. The results agree with previous research in that settings must be bespoke for each data set. This configuration process requires rapid and scalable learning to allow the predictor to be setup for new data. The fast processing abilities of the AURA k-NN ensure this combinatorial optimisation will be computationally feasible for real-world applications. We intend to use the predictor to proactively manage traffic by predicting traffic volumes to anticipate traffic network problems.

AB - This paper introduces a binary neural network-based prediction algorithm incorporating both spatial and temporal characteristics into the prediction process. The algorithm is used to predict short-term traffic flow by combining information from multiple traffic sensors (spatial lag) and time-series prediction (temporal lag). It extends previously developed Advanced Uncertain Reasoning Architecture (AURA) k-nearest neighbour (k-NN) techniques. Our task was to produce a fast and accurate traffic flow predictor. The AURA k-NN predictor is comparable to other machine learning techniques with respect to recall accuracy but is able to train and predict rapidly. We incorporated consistency evaluations to determine if the AURA k-NN has an ideal algorithmic configuration or an ideal data configuration or whether the settings needed to be varied for each data set. The results agree with previous research in that settings must be bespoke for each data set. This configuration process requires rapid and scalable learning to allow the predictor to be setup for new data. The fast processing abilities of the AURA k-NN ensure this combinatorial optimisation will be computationally feasible for real-world applications. We intend to use the predictor to proactively manage traffic by predicting traffic volumes to anticipate traffic network problems.

KW - Associative memory

KW - Binary neural network

KW - k-nearest neighbour

KW - Prediction

KW - Spatiotemporal

KW - Time series

U2 - 10.1007/s00521-014-1646-5

DO - 10.1007/s00521-014-1646-5

M3 - Article

SN - 0941-0643

VL - 25

SP - 1639

EP - 1655

JO - Neural computing & applications

JF - Neural computing & applications

IS - 7

ER -