Title :
Multi-aspect pattern classification using predictive networks and error mapping
Author :
Salazar, Jaime ; Robinson, Marc ; Azimi-Sadjadi, Mahmood R.
Author_Institution :
Dept. of Electr. & Comput. Eng., Colorado State Univ., Fort Collins, CO, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
A classification scheme is developed for classifying underwater mine-like and non-mine-like objects from acoustic backscattered signals. This scheme uses a predictive network along with a neural network classifier. The results of this scheme on an acoustic backscattered data set are given
Keywords :
Gaussian distribution; acoustic signal processing; backpropagation; belief networks; linear predictive coding; object detection; pattern classification; probability; signal classification; acoustic backscattered signals; error mapping; multi-aspect pattern classification; neural network classifier; predictive networks; underwater mine-like objects; underwater nonmine-like objects; Acoustic signal detection; Acoustical engineering; Computer errors; Fusion power generation; Laboratories; Neural networks; Pattern classification; Probability; Signal processing; Underwater acoustics;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007799
