Fault Condition Detection Based on Wavelet Packet Transform and Support Vector Data Description

A new monitoring and diagnostics method using support vector data description (SVDD) is proposed which only needs samples under healthy condition. The method is an ideal candidate for coping with the problem of a shortage of the unhealthy condition samples. We firstly select several nodes of the monitored structure, and decompose the signals from these nodes with wavelet packet transform (WPT). To monitoring structural health efficiently, we assemble a combine feature by using wavelet packet energy distributions of these nodes. The feature is then applied as the input of a developed SVDD classifier. Experiment shows that the SVDD classifier was able to distinguish the normal and abnormal condition ideally, and can be used as an automation approach for structural health monitoring.

Download Full-text

Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description

Mechanical Systems and Signal Processing ◽

10.1016/j.ymssp.2008.05.011 ◽

2009 ◽

Vol 23 (3) ◽

pp. 669-681 ◽

Cited By ~ 125

Author(s):

Yuna Pan ◽

Jin Chen ◽

Lei Guo

Keyword(s):

Wavelet Packet ◽

Assessment Method ◽

Performance Degradation ◽

Support Vector ◽

Support Vector Data Description ◽

Vector Data ◽

Data Description

Download Full-text

MK-FSVM-SVDD: A Multiple Kernel-based Fuzzy SVM Model for Predicting DNA-binding Proteins via Support Vector Data Description

Current Bioinformatics ◽

10.2174/1574893615999200607173829 ◽

2020 ◽

Vol 15 ◽

Author(s):

Yi Zou ◽

Hongjie Wu ◽

Xiaoyi Guo ◽

Li Peng ◽

Yijie Ding ◽

...

Keyword(s):

Dna Binding ◽

Binding Proteins ◽

Detection Efficiency ◽

Dna Binding Proteins ◽

Support Vector ◽

Support Vector Data Description ◽

Vector Data ◽

Data Description ◽

Multiple Kernel ◽

Svm Model

Background: Detecting DNA-binding proetins (DBPs) based on biological and chemical methods is time consuming and expensive. Objective: In recent years, the rise of computational biology methods based on Machine Learning (ML) has greatly improved the detection efficiency of DBPs. Method: In this study, Multiple Kernel-based Fuzzy SVM Model with Support Vector Data Description (MK-FSVM-SVDD) is proposed to predict DBPs. Firstly, sex features are extracted from protein sequence. Secondly, multiple kernels are constructed via these sequence feature. Than, multiple kernels are integrated by Centered Kernel Alignment-based Multiple Kernel Learning (CKA-MKL). Next, fuzzy membership scores of training samples are calculated with Support Vector Data Description (SVDD). FSVM is trained and employed to detect new DBPs. Results: Our model is test on several benchmark datasets. Compared with other methods, MK-FSVM-SVDD achieves best Matthew's Correlation Coefficient (MCC) on PDB186 (0.7250) and PDB2272 (0.5476). Conclusion: We can conclude that MK-FSVM-SVDD is more suitable than common SVM, as the classifier for DNA-binding proteins identification.

Download Full-text