Title :
Underwater Vehicle Noise Source Recognition Using Structure Dynamic Adjustable SVM
Author :
Gao Zhihua ; Ben, Ben ; Cui Lilin
Author_Institution :
Dept. of Comput. Eng., Naval Univ. of Eng., Wuhan, China
Abstract :
Based on SVM and incremental learning, this paper proposes a new method for recognition of underwater vehicle noise source on small samples. The new method may establish a classifier which structure is dynamic adjustable, and it can solve both Example- Incremental learning and Class-Incremental learning. The experimentation shows the generalization of classifier can be improved, and the classifier has incremental learning capability.
Keywords :
acoustic noise; learning (artificial intelligence); signal classification; support vector machines; underwater sound; underwater vehicles; class-incremental learning; example-incremental learning; structure dynamic adjustable SVM; underwater vehicle noise source recognition; Acoustic noise; Artificial neural networks; Automotive engineering; Learning systems; Pervasive computing; Support vector machine classification; Support vector machines; Underwater vehicles; Vehicle dynamics; Vibrations;
Conference_Titel :
Ubiquitous, Autonomic and Trusted Computing, 2009. UIC-ATC '09. Symposia and Workshops on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4244-4902-6
Electronic_ISBN :
978-0-7695-3737-5
DOI :
10.1109/UIC-ATC.2009.58
