Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices

Forests play a fundamental role in preserving the environment and fighting global warming. Unfortunately, they are continuously reduced by human interventions such as deforestation, fires, etc. This paper proposes and evaluates a framework for automatically detecting illegal tree-cutting activity in...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alessandro Andreadis, Giovanni Giambene, Riccardo Zambon
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	convolutional neural networks internet of things edge computing sound classification low power LoRa Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/9cd91ac1ea3c4f46aad8e22066a3a250
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9cd91ac1ea3c4f46aad8e22066a3a250
record_format	dspace
spelling	oai:doaj.org-article:9cd91ac1ea3c4f46aad8e22066a3a2502021-11-25T18:57:43ZMonitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices10.3390/s212275931424-8220https://doaj.org/article/9cd91ac1ea3c4f46aad8e22066a3a2502021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7593https://doaj.org/toc/1424-8220Forests play a fundamental role in preserving the environment and fighting global warming. Unfortunately, they are continuously reduced by human interventions such as deforestation, fires, etc. This paper proposes and evaluates a framework for automatically detecting illegal tree-cutting activity in forests through audio event classification. We envisage ultra-low-power tiny devices, embedding edge-computing microcontrollers and long-range wireless communication to cover vast areas in the forest. To reduce the energy footprint and resource consumption for effective and pervasive detection of illegal tree cutting, an efficient and accurate audio classification solution based on convolutional neural networks is proposed, designed specifically for resource-constrained wireless edge devices. With respect to previous works, the proposed system allows for recognizing a wider range of threats related to deforestation through a distributed and pervasive edge-computing technique. Different pre-processing techniques have been evaluated, focusing on a trade-off between classification accuracy with respect to computational resources, memory, and energy footprint. Furthermore, experimental long-range communication tests have been conducted in real environments. Data obtained from the experimental results show that the proposed solution can detect and notify tree-cutting events for efficient and cost-effective forest monitoring through smart IoT, with an accuracy of 85%.Alessandro AndreadisGiovanni GiambeneRiccardo ZambonMDPI AGarticleconvolutional neural networksinternet of thingsedge computingsound classificationlow powerLoRaChemical technologyTP1-1185ENSensors, Vol 21, Iss 7593, p 7593 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	convolutional neural networks internet of things edge computing sound classification low power LoRa Chemical technology TP1-1185
spellingShingle	convolutional neural networks internet of things edge computing sound classification low power LoRa Chemical technology TP1-1185 Alessandro Andreadis Giovanni Giambene Riccardo Zambon Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices
description	Forests play a fundamental role in preserving the environment and fighting global warming. Unfortunately, they are continuously reduced by human interventions such as deforestation, fires, etc. This paper proposes and evaluates a framework for automatically detecting illegal tree-cutting activity in forests through audio event classification. We envisage ultra-low-power tiny devices, embedding edge-computing microcontrollers and long-range wireless communication to cover vast areas in the forest. To reduce the energy footprint and resource consumption for effective and pervasive detection of illegal tree cutting, an efficient and accurate audio classification solution based on convolutional neural networks is proposed, designed specifically for resource-constrained wireless edge devices. With respect to previous works, the proposed system allows for recognizing a wider range of threats related to deforestation through a distributed and pervasive edge-computing technique. Different pre-processing techniques have been evaluated, focusing on a trade-off between classification accuracy with respect to computational resources, memory, and energy footprint. Furthermore, experimental long-range communication tests have been conducted in real environments. Data obtained from the experimental results show that the proposed solution can detect and notify tree-cutting events for efficient and cost-effective forest monitoring through smart IoT, with an accuracy of 85%.
format	article
author	Alessandro Andreadis Giovanni Giambene Riccardo Zambon
author_facet	Alessandro Andreadis Giovanni Giambene Riccardo Zambon
author_sort	Alessandro Andreadis
title	Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices
title_short	Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices
title_full	Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices
title_fullStr	Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices
title_full_unstemmed	Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices
title_sort	monitoring illegal tree cutting through ultra-low-power smart iot devices
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9cd91ac1ea3c4f46aad8e22066a3a250
work_keys_str_mv	AT alessandroandreadis monitoringillegaltreecuttingthroughultralowpowersmartiotdevices AT giovannigiambene monitoringillegaltreecuttingthroughultralowpowersmartiotdevices AT riccardozambon monitoringillegaltreecuttingthroughultralowpowersmartiotdevices
_version_	1718410479104163840

Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices

Ejemplares similares