2011 IEEE 13th International Symposium on High-Assurance Systems Engineering 2011
DOI: 10.1109/hase.2011.60
|View full text |Cite
|
Sign up to set email alerts
|

Using Feature Selection to Determine Optimal Depth for Wavelet Packet Decomposition of Vibration Signals for Ocean System Reliability

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2011
2011
2024
2024

Publication Types

Select...
4
2

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 17 publications
0
3
0
Order By: Relevance
“…The comparison shows that SVM outperforms ANNs. Wald et al (2011) presented an unsupervised feature selection method for deciding the optimal depth for wavelet packet decomposition (WPD). The paper shows that using feature selection to determine the depth for WPD led to a model, which can retain almost all the accuracy of models built using a much deeper transform.…”
Section: Diagnosticsmentioning
confidence: 99%
“…The comparison shows that SVM outperforms ANNs. Wald et al (2011) presented an unsupervised feature selection method for deciding the optimal depth for wavelet packet decomposition (WPD). The paper shows that using feature selection to determine the depth for WPD led to a model, which can retain almost all the accuracy of models built using a much deeper transform.…”
Section: Diagnosticsmentioning
confidence: 99%
“…The comparison shows that SVM outperforms Artificial Neural Network (ANN). An unsupervised feature selection method for deciding the optimal depth for Wavelet Packet Decomposition (WPD) has been presented in [35]. The paper shows that using feature selection to determine the depth for WPD led to a model which can retain almost all the accuracy of models built using a much deeper transform.…”
Section: Diagnosticsmentioning
confidence: 99%
“…A variety of preprocessing techniques on the raw waveform have been implemented and evaluated, including Fourier transforms, 18 wavelet transforms, 19 and wavelet packet decompositions. [20][21][22] Like our prior work, this case study uses data preprocessed by a streaming implementation of a Haar wavelet transform. Results of state distinction for subsets of these as well as other pairs of velocities for the dynamometer have been previously reported, 23,24 and distinctions due to various loads are currently being investigated.…”
Section: Case Studymentioning
confidence: 99%