Time-frequency analysis based methods for classification of newborn cry signals/
Since, the t-f analysis is a good approach for analyzing the highly non-stationary characteristic, in time and frequency scale simultaneously without eliminating any salient information, this research work address the development of an objective method for classifying different infant cry signals pr...
Saved in:
| Main Author: | |
|---|---|
| Corporate Author: | |
| Format: | Thesis Book |
| Language: | English |
| Published: |
Perlis, Malaysia
School of Mechatronic Engineering
2016
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Since, the t-f analysis is a good approach for analyzing the highly non-stationary characteristic, in time and frequency scale simultaneously without eliminating any salient information, this research work address the development of an objective method for classifying different infant cry signals predominantly using two different t-f methods namely QTFDs (spectrogram (SPEC), Wigner-Ville distribution (WVD), Smoothed-Wigner Ville distribution (SWVD), Choi-William distribution (CWD) and Modified B-distribution (MBD)) and WPT based method (wavelet packet spectrum (Wpspectrum)). A cluster of t-f based features was extracted from the suggested t-f methods and their efficacy was examined using two supervised neural networks, namely probabilistic neural network (PNN) and general regression neural network (GRNN). |
|---|---|
| Physical Description: | xvi, 239 pages colour illustration 30 cm. |
| Bibliography: | Includes bibliographical references. |