Visualization and categorization of ecological acoustic events based on discriminant features

Although sound classification in soundscape studies are generally performed by experts, the large growth of acoustic data presents a major challenge for performing such task. At the same time, the identification of more discriminating features becomes crucial when analyzing soundscapes, and this occ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Liz Maribel Huancapaza Hilasaca, Lucas Pacciullio Gaspar, Milton Cezar Ribeiro, Rosane Minghim
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Soundscape ecology Discriminant features Visualization Classification Feature selection Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/acadc71de7004e639f929bbe409dcc16
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:acadc71de7004e639f929bbe409dcc16
record_format	dspace
spelling	oai:doaj.org-article:acadc71de7004e639f929bbe409dcc162021-12-01T04:42:23ZVisualization and categorization of ecological acoustic events based on discriminant features1470-160X10.1016/j.ecolind.2020.107316https://doaj.org/article/acadc71de7004e639f929bbe409dcc162021-07-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X20312589https://doaj.org/toc/1470-160XAlthough sound classification in soundscape studies are generally performed by experts, the large growth of acoustic data presents a major challenge for performing such task. At the same time, the identification of more discriminating features becomes crucial when analyzing soundscapes, and this occurs because natural and anthropogenic sounds are very complex, particularly in Neotropical regions, where the biodiversity level is very high. In this scenario, the need for research addressing the discriminatory capability of acoustic features is of utmost importance to work towards automating these processes. In this study we present a method to identify the most discriminant features for categorizing sound events in soundscapes. Such identification is key to classification of sound events. Our experimental findings validate our method, showing high discriminatory capability of certain extracted features from sound data, reaching an accuracy of 89.91% for classification of frogs, birds and insects simultaneously. An extension of these experiments to simulate binary classification reached accuracy of 82.64%,100.0% and 99.40% for the classification between combinations of frogs-birds, frogs-insects and birds-insects, respectively.Liz Maribel Huancapaza HilasacaLucas Pacciullio GasparMilton Cezar RibeiroRosane MinghimElsevierarticleSoundscape ecologyDiscriminant featuresVisualizationClassificationFeature selectionEcologyQH540-549.5ENEcological Indicators, Vol 126, Iss , Pp 107316- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Soundscape ecology Discriminant features Visualization Classification Feature selection Ecology QH540-549.5
spellingShingle	Soundscape ecology Discriminant features Visualization Classification Feature selection Ecology QH540-549.5 Liz Maribel Huancapaza Hilasaca Lucas Pacciullio Gaspar Milton Cezar Ribeiro Rosane Minghim Visualization and categorization of ecological acoustic events based on discriminant features
description	Although sound classification in soundscape studies are generally performed by experts, the large growth of acoustic data presents a major challenge for performing such task. At the same time, the identification of more discriminating features becomes crucial when analyzing soundscapes, and this occurs because natural and anthropogenic sounds are very complex, particularly in Neotropical regions, where the biodiversity level is very high. In this scenario, the need for research addressing the discriminatory capability of acoustic features is of utmost importance to work towards automating these processes. In this study we present a method to identify the most discriminant features for categorizing sound events in soundscapes. Such identification is key to classification of sound events. Our experimental findings validate our method, showing high discriminatory capability of certain extracted features from sound data, reaching an accuracy of 89.91% for classification of frogs, birds and insects simultaneously. An extension of these experiments to simulate binary classification reached accuracy of 82.64%,100.0% and 99.40% for the classification between combinations of frogs-birds, frogs-insects and birds-insects, respectively.
format	article
author	Liz Maribel Huancapaza Hilasaca Lucas Pacciullio Gaspar Milton Cezar Ribeiro Rosane Minghim
author_facet	Liz Maribel Huancapaza Hilasaca Lucas Pacciullio Gaspar Milton Cezar Ribeiro Rosane Minghim
author_sort	Liz Maribel Huancapaza Hilasaca
title	Visualization and categorization of ecological acoustic events based on discriminant features
title_short	Visualization and categorization of ecological acoustic events based on discriminant features
title_full	Visualization and categorization of ecological acoustic events based on discriminant features
title_fullStr	Visualization and categorization of ecological acoustic events based on discriminant features
title_full_unstemmed	Visualization and categorization of ecological acoustic events based on discriminant features
title_sort	visualization and categorization of ecological acoustic events based on discriminant features
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/acadc71de7004e639f929bbe409dcc16
work_keys_str_mv	AT lizmaribelhuancapazahilasaca visualizationandcategorizationofecologicalacousticeventsbasedondiscriminantfeatures AT lucaspacciulliogaspar visualizationandcategorizationofecologicalacousticeventsbasedondiscriminantfeatures AT miltoncezarribeiro visualizationandcategorizationofecologicalacousticeventsbasedondiscriminantfeatures AT rosaneminghim visualizationandcategorizationofecologicalacousticeventsbasedondiscriminantfeatures
_version_	1718405815962959872

Visualization and categorization of ecological acoustic events based on discriminant features

Ejemplares similares