Title :
A NEW METHOD FOR SPREAD VALUE ESTIMATION IN MULTI-SPREAD PNN AND ITS APPLICATION IN SHIP NOISE CLASSIFICATION
Author :
Farrokhrooz, M. ; Karimi, M.
Author_Institution :
Dept. of Electr. Eng., Shiraz Univ.
Abstract :
The use of probabilistic neural network (PNN) is very common in supervised pattern recognition applications. PNN is based on Bayes decision rule and it uses Gaussian Parzen windows for estimating the probability density functions (pdf) required in Bayes rule. The conventional PNN needs a single spread value for pdf estimation which is proportional to Gaussian window width. In this paper we suggest the use of a multi-spread PNN structure whose spread values are estimated using the training data. In addition, we introduce several new discriminating features of acoustic radiated noise which can be used for ship noise classification. These features are used as discriminating features in the conventional and multi-spread PNN. Finally, the performance of the conventional PNN and the suggested multi-spread PNN in classifying real ship noise data are compared. Results of this comparison show that the performance of the multi-spread PNN is better than the conventional PNN
Keywords :
Bayes methods; Gaussian processes; acoustic noise; acoustic signal processing; neural nets; signal classification; Bayes decision rule; Gaussian Parzen windows; acoustic radiated noise; multi-spread PNN structure; probabilistic neural network; probability density function estimation; ship noise classification; spread value estimation; supervised pattern recognition; Acoustic noise; Artificial intelligence; Boats; Convergence; Electronic mail; Marine vehicles; Neural networks; Parameter estimation; Smoothing methods; Training data;
Conference_Titel :
Signal Processing, 2006 8th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9736-3
Electronic_ISBN :
0-7803-9736-3
DOI :
10.1109/ICOSP.2006.346048
