Joint Feature Selection and Parameter Tuning for Short-Term Traffic Flow Forecasting Based on Heuristically Optimized Multi-layer Neural Networks

Short-term traffic flow forecasting is a vibrant research topic that has been growing in interest since the late 70’s. In the last decade this vibrant field has shifted its focus towards machine learning methods. These techniques often require fine-grained parameter tuning to obtain satisfactory performance scores, a process that usually relies on manual trial-and-error adjustment. This paper explores the use of Harmony Search optimization for tuning the parameters of neural network jointly with the selection of the input features from the dataset at hand. Results are discussed and compared to other tuning methods, from which it is concluded that neural predictors optimized via the proposed heuristic wrapper outperform those tuned by means of naive parametrized algorithms, thus allowing for longer-term predictions. These promising results unfold potential applications of this technique in multi-location neighbor-aware traffic prediction.

[1]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[2]  Zong Woo Geem,et al.  A New Heuristic Optimization Algorithm: Harmony Search , 2001, Simul..

[3]  Tharam S. Dillon,et al.  Evaluation of Recent Computational Approaches in Short-Term Traffic Forecasting , 2015, IFIP AI.

[4]  Michael J Demetsky,et al.  SHORT-TERM TRAFFIC FLOW PREDICTION: NEURAL NETWORK APPROACH , 1994 .

[5]  Wei Zhang,et al.  Research of Traffic Flow Forecasting Based on the Information Fusion of BP Network Sequence , 2015, IScIDE.

[6]  Javier Del Ser,et al.  Understanding daily mobility patterns in urban road networks using traffic flow analytics , 2016, NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium.

[7]  Shalini Bhatia,et al.  Traffic Flow Control using Neural Network , 2012 .

[8]  Eleni I. Vlahogianni,et al.  Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach , 2005 .

[9]  Sherif Ishak,et al.  OPTIMIZATION OF DYNAMIC NEURAL NETWORKS PERFORMANCE FOR SHORT-TERM TRAFFIC PREDICTION , 2003 .

[10]  Eleni I. Vlahogianni,et al.  Short-term traffic forecasting: Where we are and where we’re going , 2014 .

[11]  Baher Abdulhai,et al.  Short Term Freeway Traffic Flow Prediction Using Genetically-Optimized Time-Delay-Based Neural Networks , 1999 .

[12]  J. W. C. van Lint,et al.  Short Term Traffic Prediction Models , 2007 .

[13]  Eleni I. Vlahogianni,et al.  Spatio‐Temporal Short‐Term Urban Traffic Volume Forecasting Using Genetically Optimized Modular Networks , 2007, Comput. Aided Civ. Infrastructure Eng..

[14]  Ming Zhong,et al.  Refining Genetically Designed Models for Improved Traffic Prediction on Rural Roads , 2005 .

[15]  Meng Meng,et al.  A two-stage short-term traffic flow prediction method based on AVL and AKNN techniques , 2015 .

[16]  Fang Liu,et al.  Travel Time Estimation Using Freeway Point Detector Data Based on Evolving Fuzzy Neural Inference System , 2016, PloS one.

[17]  Stephen Dunne,et al.  Regime-Based Short-Term Multivariate Traffic Condition Forecasting Algorithm , 2012 .

[18]  Li Li,et al.  The short-term traffic flow prediction based on neural network , 2010, 2010 2nd International Conference on Future Computer and Communication.

[19]  Dewei Li,et al.  A short-term traffic flow forecasting method and its applications , 2015 .

[20]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.