Cyber-Physical System for Environmental Monitoring Based on Deep Learning

Cyber-physical systems (CPS) constitute a promising paradigm that could fit variousapplications. Monitoring based on the Internet of Things (IoT) has become a research area withnew challenges in which to extract valuable information. This paper proposes a deep learningclassification sound system for...

Descripción completa

Detalles Bibliográficos
Autores: Monedero, Íñigo, Barbancho, Julio, Márquez, Rafael, Beltrán, Juan F.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/245394
Acceso en línea:http://hdl.handle.net/10261/245394
Access Level:acceso abierto
Palabra clave:Convolutional neural networks
Deep learning
Machine learning
Cyber-physical systems
Passive active monitoring
Internet of Things
Descripción
Sumario:Cyber-physical systems (CPS) constitute a promising paradigm that could fit variousapplications. Monitoring based on the Internet of Things (IoT) has become a research area withnew challenges in which to extract valuable information. This paper proposes a deep learningclassification sound system for execution over CPS. This system is based on convolutional neuralnetworks (CNNs) and is focused on the different types of vocalization of two species of anurans.CNNs, in conjunction with the use of mel-spectrograms for sounds, are shown to be an adequate toolfor the classification of environmental sounds. The classification results obtained are excellent (97.53%overall accuracy) and can be considered a very promising use of the system for classifying otherbiological acoustic targets as well as analyzing biodiversity indices in the natural environment. Thepaper concludes by observing that the execution of this type of CNN, involving low-cost and reducedcomputing resources, are feasible for monitoring extensive natural areas. The use of CPS enablesflexible and dynamic configuration and deployment of new CNN updates over remote IoT nodes.