The Role of Artificial Neural Networks in the Analysis of Ultrasonic Bat Calls: A Case Study Robert C. Stocker
Abstract
	Species identification is typically complex, often subjective and results are variable. Automated computer analysis of species call data has the potential for reliable, consistent and accurate classification eliminating subjectivity. This study applies feed forward back propagation neural network architectures to identify bat species through analysis of echolocation call data. Results show that successful classification is dependent upon the structure of call data together with network design and implementation issues. Performance criteria are demonstrated and further research directions are indicated.

Full Text

Multimedia Links
(none)

Reference Links
(none)

Citation Reference

Get viewers
for PS & PDF

[CI Editor] [Site Manager]