Ng, Chee Han (2011) Identification of selected frogs acoustics samples using wavelet entropy. Masters thesis, Universiti Malaysia Sabah.
|
Text
mt0000000375.pdf Download (2MB) | Preview |
Abstract
Biodiversity is one of the major studies in bio-conservation, which enable to evaluate the quality of ecosystem in a specific area, especially for protected area. In order to monitor the quality of the ecosystem structure, a long term rapid diversity assessment is needed. In term of that, bioacoustics has been introduced as a beneficial method for local species richness estimation. However, this method is still in the infancy state and many improvements are needed for more practical purposes. This research is carried out to develop new bioacoustics species identification method using wavelet entropy with the improvement in the species identification accuracy. To evaluate the new identification system, a set of sound signals of nine frog species from Microhylidae family were collected. Ten syllables were segmented from each frog sound and extracted with the corresponding features which were carried out in this research, namely continuous wavelet entropy, discrete wavelet entropy and wavelet packet entropy as test samples. The test samples were then sent into the k-nearest neighbour (k-NN) classifier for species identification. Based on the test samples, this thesis work has proven that the wavelet packet entropy is the best method in the Tsallis entropy approach for species identification on bioacoustics signals.
| Item Type: | Thesis (Masters) |
|---|---|
| Keyword: | bio-conservation, ecosystem, frog, wavelet entropy, bioacoustics signal,Microhylidae family |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Department: | SCHOOL > School of Science and Technology |
| Depositing User: | SITI AZIZAH BINTI IDRIS - |
| Date Deposited: | 09 Jun 2014 13:52 |
| Last Modified: | 30 Oct 2017 09:51 |
| URI: | https://eprints.ums.edu.my/id/eprint/9188 |
Actions (login required)
 |
View Item |