Identification of Bat Echolocation Calls Using a Decision Tree Classification System

		/vol04/herr/	© Copyright 1997
		Volume 04	Received: Accepted:	---- ----

Identification of Bat Echolocation Calls Using a Decision Tree Classification System Alexander Herr, Nicholas I. Klomp & John S. Atkinson
Abstract
	This is the first published attempt to identify bats from their ultrasonic calls (recorded with ANABAT) and using a decision tree classification system. The automated identification of pulse parameters led to good results for species with distinct differences in calls, with four out of eight species classified correctly in 95% of attempts. However, the calls of three species were consistently misidentified. A new approach is required which considers other characteristics of the calls in more detail, such as the shape of the pulses (frequency change over time) in each call. Future attempts at automating bat call identification should consider the use of image analysis software.

Full Text

Multimedia Links
(none)

Reference Links
(none)

Citation Reference

Get viewers
for PS & PDF

[CI Editor] [Site Manager]