Computational method for segmentation and classification of ingestive sounds in sheep
In this work we propose a novel method to analyze and recognize automatically sound signals of chewing and biting. For the automatic segmentation and classification of acoustical ingestive behaviour of sheep the method use an appropriate acoustic representation and statistical modelling based on hid...
| Autores: | , , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2009 |
| País: | Argentina |
| Recursos: | Consejo Nacional de Investigaciones Científicas y Técnicas |
| Repositorio: | CONICET Digital (CONICET) |
| Idioma: | inglés |
| OAI Identifier: | oai:ri.conicet.gov.ar:11336/97578 |
| Acesso em linha: | http://hdl.handle.net/11336/97578 |
| Access Level: | acceso abierto |
| Palavra-chave: | ACOUSTIC MODELING HIDDEN MARKOV MODELS GRAZING SHEEP INGESTIVE 15 BEHAVIOUR https://purl.org/becyt/ford/1.2 https://purl.org/becyt/ford/1 |
| Resumo: | In this work we propose a novel method to analyze and recognize automatically sound signals of chewing and biting. For the automatic segmentation and classification of acoustical ingestive behaviour of sheep the method use an appropriate acoustic representation and statistical modelling based on hidden Markov models. We analyzed 1813 seconds of chewing data from four sheep eating two different forages typically found in grazing production systems, orchardgrass and alfalfa, each at two sward heights. Because identification of species consumed when in mixed swards is a key issue in grazing science, we tested the possibility to discriminate species and sward height by using the proposed approach. Signals were correctly classified by forage and sward height in 67% of the cases, whereas forage was correctly identified 84% of the time. The results showed an overall performance of 82% for the recognition of chewing events. |
|---|