Compressor Surge Detection Based on Support Vector Data Description

2012 ◽  
Vol 152-154 ◽  
pp. 1545-1549
Author(s):  
Chang Zheng Li ◽  
Yong Lei
Keyword(s):  
Support Vector Machine ◽  
Active Control ◽  
Axial Flow ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Vector Data ◽  
Data Description ◽  
Compressor Surge ◽  
Aerodynamic Instability ◽  
One Class Classification

Axial flow compressors work as an indispensable device in industry fields. Surge is a phenomenon of aerodynamic instability, which characterized by disruption of flow. When a compressor works in surge state, the vibration is so intense that it may causes accidents. Detecting surge timely and accurately not only insure safety of compressors but also is a key of active control of aerodynamic instability. Support vector data description (SVDD) is a one-class classification method developed based on the theory of support vector machine (SVM). In this paper, we introduce SVDD into the field of compressor surge detection. It demonstrates that SVDD method can give a warning far ahead of surge.

The Temperature Prediction in Blast Furnace Base on Fuzzy Least Squares Support Vector Machine

2013 ◽  
Vol 336-338 ◽  
pp. 566-569
Author(s):  
Qing Xin Zhang ◽  
Yong Tao ◽  
Zhan Bo Cui
Keyword(s):  
Support Vector Machine ◽  
Blast Furnace ◽  
Least Squares ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Vector Data ◽  
Furnace Temperature ◽  
Temperature Prediction ◽  
Data Description ◽  
Simulation Results

The temperature prediction in blast furnace loses accuracy or Forecasts failure when the temperatures change is at normal levels and obvious. This paper introduces fuzzy membership of samples basing on support vector data description and the fuzzy least squares support vector machine to forecast the blast furnace temperature. Then the simulation was done by using the forecast samples and the model after training by MATLAB. Comparing the simulation results of LS-FSVM with LS-SVM, the model basing on LS-FSVM enhances anti-jamming ability. The accuracy of the temperature prediction in blast furnace promotes significantly when the temperature of blast furnace fluctuates.

scholarly journals A Support Vector Data Description Approach to NLOS Identification in UWB Positioning

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Shiwei Tian ◽  
Luwen Zhao ◽  
Guangxia Li
Keyword(s):  
Identification Problem ◽  
Classification Problem ◽  
Line Of Sight ◽  
Support Vector ◽  
Delay Spread ◽  
Support Vector Data Description ◽  
Vector Data ◽  
Data Description ◽  
One Class Classification ◽  
Mean Excess Delay

Non-line-of-sight (NLOS) propagation is one of the most important challenges in radio positioning, and, in recent years, significant attention has been drawn to the identification and mitigation of NLOS signals. This paper focuses on the identification of NLOS signals. The authors consider the NLOS identification problem as a one-class classification problem and apply the support vector data description (SVDD), providing accurate data descriptions utilizing kernel techniques, to perform NLOS identification in ultrawide bandwidth (UWB) positioning. Our work is based on the fact that some features extracted from the received signal waveforms, such as the kurtosis, the mean excess delay spread, and the root mean square delay spread, are different between line-of-sight (LOS) and NLOS signals. Numerical simulations are performed to demonstrate the performance, using a dataset derived from a measurement campaign.

KERNEL WHITENING FOR ONE-CLASS CLASSIFICATION

2003 ◽  
Vol 17 (03) ◽  
pp. 333-347 ◽  
Author(s):  
DAVID M. J. TAX ◽  
PIOTR JUSZCZAK
Keyword(s):  
Feature Space ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Good Representation ◽  
Vector Data ◽  
Data Description ◽  
Unit Variance ◽  
Good Distinction ◽  
One Class Classification ◽  
Target Data

In one-class classification one tries to describe a class of target data and to distinguish it from all other possible outlier objects. Obvious applications are areas where outliers are very diverse or very difficult or expensive to measure, such as in machine diagnostics or in medical applications. In order to have a good distinction between the target objects and the outliers, good representation of the data is essential. The performance of many one-class classifiers critically depends on the scaling of the data and is often harmed by data distributions in (nonlinear) subspaces. This paper presents a simple preprocessing method which actively tries to map the data to a spherical symmetric cluster and is almost insensitive to data distributed in subspaces. It uses techniques from Kernel PCA to rescale the data in a kernel feature space to unit variance. This transformed data can now be described very well by the Support Vector Data Description, which basically fits a hypersphere around the data. The paper presents the methods and some preliminary experimental results.

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

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.

Sign in / Sign up

Export Citation Format

Share Document