Abstract
Automatic target classification under all conditions is a key challenge for modern radar and sonar systems. Echolocating nectar feeding bats are able to detect and select flowers of bat-pollinated plants even in highly cluttered environments. It is thought that these flowers have evolved to ease classification by bats, and that their echo-acoustic signatures contain critical information that aids the bat in choosing the most suitable flowers. In investigating the features of these flowers that aid the bats search for nectar, the strategy underpinning the task of classification of static targets by bats may be understood and this may additionally offer lessons for radar and sonar systems. Here, we analyse a real set of data containing high range resolution profiles of unpollinated corollas of Cobaea scandens, which is a flower of the type that is pollinated by bats. These were collected by transmitting a synthetic wideband linear chirp with an acoustic radar capable of very high range resolution. Classification performance of a k-NN classifier and a Naïve Bayesian classifier is assessed using information available in both the time and frequency domains. This facilitates quantification of the differences in these echoes because of the flower wilting process and lack of physical parts.
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
Disclaimer: 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.