By Topic

Detection of pest infestation by preprocessing sound using vector quantization

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Martin, B. ; Dept. of Electron. & Control, Sathyabama Univ., Chennai, India ; Juliet, V.

In the recent past, economic damage due to infestation of pest on palms could be mitigated significantly by early detection and treatment. Tests were conducted with currently available acoustic instrumentation and software to assess the sound impulses produced by larva's locomotory and feeding activities. The incorporation of bursts into analysis significantly assisted in applications where consistent activity patterns of hidden pest could be identified. The purpose of this research is to realize the effectiveness of a text independent identification system making use of cepstral coefficients and vector quantization. The identification system will be making use of MFCC. The MFCC extracted was then matched to all available sound codebooks that have been stored. The codebook that returns the lowest quantization error will belong to sound contained in audio input file. This confirms the result of detection of the particular species of interest. The data resulting from the analysis will serve as key characteristic in identifying presence of the pest species to which sound belongs.

Published in:

Signal Processing Systems (ICSPS), 2010 2nd International Conference on  (Volume:3 )

Date of Conference:

5-7 July 2010