Feature selection for defect classification in machine condition monitoring

Malhi, A.; Gao, Robert X.

doi:10.1109/imtc.2003.1208117

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, more features may bring in useless information or even misleading information. Malhi and Gao [17] have shown that some features provide contradictory information and thus decrease the quality of data analysis. Also, in real time stress detection more features mean more data processing, which may reduce or limit the real time performance.…”

Section: Introductionmentioning

confidence: 99%

An Investigation of Decision Analytic Methodologies for Stress Identification

Deng

Chu

et al. 2013

International Journal on Smart Sensing and Intelligent Systems

View full text Add to dashboard Cite

Abstract-In modern society, more and more people are suffering from some type of stress.Monitoring and timely detecting of stress level will be very valuable for the person to take counter measures. In this paper, we investigate the use of decision analytics methodologies to detect stress. We present a new feature selection method based on the principal component analysis (PCA), compare three feature selection methods, and evaluate five information fusion methods for stress detection. A driving stress data set created by the MIT Media lab is used to evaluate the relative performance of these methods. Our study show that the PCA can not only reduce the needed number of features from 22 to five, but also the number of sensors used from five to two and it only uses one type of sensor, thus increasing the application usability. The selected features can be used to quickly detect stress level with good accuracy (78.94%), if support vector machine fusion method is used.

show abstract

Section: Introductionmentioning

confidence: 99%

An Investigation of Decision Analytic Methodologies for Stress Identification

Deng

Chu

et al. 2013

International Journal on Smart Sensing and Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Extracting the fault characterized information from the vibration signal is crucial to the fault diagnosis. Various techniques such as statistic parameters, FFT, wavelet transform, EMD, AR model and ANN have been applied to extract useful features successfully [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

Feature extraction and selection for fault diagnosis of gear using wavelet entropy and mutual information

Li¹,

Zhang²,

Liang³

et al. 2008

2008 9th International Conference on Signal Processing

View full text Add to dashboard Cite

This paper aims to develop an complete system including signal processing, feature extraction, feature selection and classification approaches for fault diagnosis of gear by using the wavelet transform, the entropy, the mutual information and the least-square support vector machine (LS-SVM). Firstly, the vibration signals are decomposed to several wavelet coefficients. The energy of every coefficient and the singularity values (SV) of the coefficient matrix are extracted. Two type entropies means the Shannon entropy and Renyi entropy are calculated of the energy and SV distribution. Secondly, a maximum relevance and minimum redundant (mRMR) method based on the mutual information and the greedy search technique are employed to select the optimal feature subsets for gear fault classification. A cross-validation method based on the LS-SVM is proposed to determine the number of features that the optimal subset contained. Application to practical gear fault diagnosis showed that the proposed techniques provide a more effective and fast approach to gear fault diagnosis.

show abstract

System design that minimizes both missed detections and false alarms: a case study in arc fault detection

Fowler

Land

Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.04CH37510)

View full text Add to dashboard Cite

This paper considers several comporientr in the architectwe arid design o / .~.vstem.~ lo di.w-iminate conditions ond ./im the dolo. It./?icz~~se.s on the prohlems of mirsing detections ond red~,ciiig thepossihili?, qfgetrcrating, false pmitive olorms. It tises a case stsdy of0 protective system that detects orcing./bu/ts in pow,er sw,itchhoadv on hoard ships. The result.^ in this puper can he u.sed in man." s-vstems that mr,.st monitor and dctect hazardous events hoth accttratelv mid mn.si.~tentlv ulilc miiiimizing .f&e positive olrmns rho/ coii COIISL' hartn/il results. E.romp1e.s include power plants. hospira1.r. computer instullatiom, wvh server.s. mi1itar.v seiI.sors rho/ detect ensemv veliicles, oirwali engininr monitoring. und rel~~ommunicarb,?s.

show abstract

Feature selection for defect classification in machine condition monitoring

Cited by 3 publications

References 13 publications

An Investigation of Decision Analytic Methodologies for Stress Identification

An Investigation of Decision Analytic Methodologies for Stress Identification

Feature extraction and selection for fault diagnosis of gear using wavelet entropy and mutual information

System design that minimizes both missed detections and false alarms: a case study in arc fault detection

Contact Info

Product

Resources

About