We propose a light weight algorithm to classify cane-toads, a non-native invasive amphibian species in Australia as well as other native frog species, based on their vocalizations using sharply resource-constrained acoustic sensors. The goal is to enable fast in-network frog classification at the resource-constrained sensors so as to minimize energy consumption of the sensor network by reducing the amount of data transmitted to a central server. Each sensor randomly and independently samples a signal at a sub-Nyquist rate. The vocalization envelopes are extracted and matched with the original signal envelopes to find the best match. The computational complexity of the algorithm is O(n). It also requires less than 2KB of data memory. Our experiments on frog vocalizations show that our approach performs well, providing an accuracy of 90% and a miss rate of less than 5%.
[1]
Margaret Martonosi,et al.
Data compression algorithms for energy-constrained devices in delay tolerant networks
,
2006,
SenSys '06.
[2]
Emmanuel J. Candès,et al.
Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
,
2004,
IEEE Transactions on Information Theory.
[3]
Sanjay Jha,et al.
The design and evaluation of a hybrid sensor network for Cane-Toad monitoring
,
2005
.
[4]
Richard G. Baraniuk,et al.
The smashed filter for compressive classification and target recognition
,
2007,
Electronic Imaging.
[5]
Gerald L. Fudge,et al.
Detecting Signal Structure from Randomly-Sampled Data
,
2007,
2007 IEEE/SP 14th Workshop on Statistical Signal Processing.