Abstract
The behavioral study of animals and especially avians, and the way of their immunization are highly needed to understand the environment in a better way. Automatically classifying bird species by their vocalization is of crucial relevance for the research of ornithologists and ecologists. It was observed that impartial survey information for songbird species is inherently challenging due to observer biases, habitat insurance biases, and logistical constraints. To get to the bottom of all the challenges, ecologists are trying a machine that let them decide the distribution and density of species, which are essential baseline facts for conservation. For this reason, the utilization of a network of unmanned aerial vehicles is introduced for monitoring and capturing the data of a wide variety of terrestrial and aquatic species. In this study, an edge-enabled drone network has been engineered that amalgamated with the mobile edge computing framework within the drone network and the machine learning models to predict the bird species. The experiment has been performed in two geographic regions. The research reported 98.2% and 96.9% accuracy of random forest classifier with the, 0.07 and 0.4 log loss by utilizing 1.4% of CPU and 329.14 Mb of buffer memory of the edge device with an execution time of 45 milliseconds.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
