An evolving wavelet-based de-noising method for the weigh-in-motion system

  • Authors:

  • Xie Chao;Huang Jie;Wei Chengjian;Xu Jun

  • Affiliations:

  • College of Information Science and Engineering, Nanjing University of Technology, Nanjing, Jiangsu, P.R. China;Research Center of Information Security, Dept. of Radio Engineering, Southeast University, Nanjing, Jiangsu, P.R. China;College of Information Science and Engineering, Nanjing University of Technology, Nanjing, Jiangsu, P.R. China;College of Information Science and Engineering, Nanjing University of Technology, Nanjing, Jiangsu, P.R. China

  • Venue:
  • ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In order to enhance the roads maintenance, a number of weigh-in-motion (WIM) systems are used in the high way to collect the weight of every vehicle pass by, but normally the outcome is rough. The one important reason of this problem is that lots of complex low-frequency noises exist in the weighing signal, which can not be filtered by the Fourier series analysis. In this paper, firstly we apply the de-noising method via thresholding of wavelet coefficients to purify the signal, and then we propose an evolving wavelet thresholding method for the WIM system using evolutionary programming (EP), further we evolves the best threshold by this method and improve the weighing signal processing. Finally, we use our thoughts to model a simulated WIM signal de-nosing system and experimental results shows that this novel system provides more accurate data compared to other existing analyzing measures for weighing signal.