Determining class of underwater vehicles in passive sonar using hidden Markov model with Hausdorff similarity measure

Autor:	B. Fazaeefar, H. Amindavar, H. Peyvandi
Rok vydání:	2002
Předmět:	Engineering business.industry Speech recognition Feature extraction Pattern recognition Similarity measure Sonar signal processing Sonar Object detection Computer Science::Sound Robustness (computer science) Artificial intelligence Hidden Markov model business Underwater acoustics
Zdroj:	Proceedings of 1998 International Symposium on Underwater Technology.
DOI:	10.1109/ut.1998.670104
Popis:	The main purpose of this paper is about detection and classification of underwater vehicles (UVs) using features extracted from their acoustic signals. We have proposed an algorithm for the above purpose based on hidden Markov model (HMM) with Hausdorff similarity measure (HSM). The HMM is a proper stochastic model for speech recognition and classification of spoken words. We used this model to recognize UVs acoustic signal among other environmental noise and therefore would be a good candidate to classify some UVs. We considered three classes and simulate their sounds, and constructed three trained HMM with optimal number of states. Measurement of similarity is done by HSM instead Euclidean measure, in train and test section. Robustness and better performance are two promising results. The new method only demands more computation and therefore faster processors.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::3ddabeffdb2d9b0e0fe458a8319f0662 https://doi.org/10.1109/ut.1998.670104 Zobrazit plný text záznamu