A neural network architecture for noise prediction

Abstract This paper presents application of neural networks (NNs) to the problem of prediction of noise caused by urban traffic. The most representative physical variable quantifying noise emissions is the equivalent sound pressure level. Up to now it has been identified on the basis of semi-empirical models, typically regression analysis, which generally do not provide very accurate approximations of the trend followed by sound pressure level. The authors have attempted to overcome this difficulty by adopting a neural approach based on a Backpropagation Network (BPN). Results obtained by the comparison of the BPN approach with those provided by selected relationships found in relevant literature, show how good is the approach proposed. The neural solution to the problem has shown the necessity, in certain phases, of a set of acoustic measurements which is as free as possible of error. The complexity of error identification by means of classical approaches has led the authors to explore the possibility of a neural solution to this problem as well. The authors therefore propose use of a neural architecture made up of two cascading levels. At the first level a supervised classifying network, the learning vector quantization (LVQ) network, filters the data discarding all the wrong measurements, while at the second level the BPN predicts the sound pressure level.

[1]  Jorma Laaksonen,et al.  LVQPAK: A software package for the correct application of Learning Vector Quantization algorithms , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[3]  T. Kohonen,et al.  Appendix 2.4 Stopping Rule 2.3 Fine Tuning Using the Basic Lvq1 or Lvq2.1 Lvq Pak: a Program Package for the Correct Application of Learning Vector Quantization Algorithms , 1992 .

[4]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[5]  Teuvo Kohonen,et al.  Statistical pattern recognition with neural networks , 1988, Neural Networks.

[6]  Duane DeSieno,et al.  Adding a conscience to competitive learning , 1988, IEEE 1988 International Conference on Neural Networks.

[7]  Anthony Kuh,et al.  A combined self-organizing feature map and multilayer perceptron for isolated word recognition , 1992, IEEE Trans. Signal Process..

[8]  Salvatore Cavalieri,et al.  Noise Prediction in Urban Traffic by a Neural Approach , 1993, IWANN.

[9]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[10]  James L. McClelland Explorations In Parallel Distributed Processing , 1988 .

[11]  Javier Tuya,et al.  Combination of Self-Organizing Maps and Multilayer Perceptrons for Speaker Independent Isolated Word Recognition , 1993, IWANN.

[12]  Patrick Gallinari,et al.  Learning vector quantization, multi layer perceptron and dynamic programming: comparison and cooperation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[13]  Salvatore Cavalieri,et al.  Self-organizing map to filter acoustic mapping survey in noise pollution analysis , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[14]  R. Perfetti,et al.  Shear velocity estimation by the combined use of supervised and unsupervised neural networks , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[15]  Luigi Marletta,et al.  Acoustic survey and statistical analysis of Messina noise levels , 1991 .

[16]  Umit Dağitan,et al.  Connected Word Recognition Using Neural Networks , 1989, NATO Neurocomputing.