Cyber-Physical System for Environmental Monitoring Based on Deep Learning

Abstract

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.