A modified support vector data description based novelty detection approach for machinery components

Authors:
Shijin Wang;Jianbo Yu;Edzel Lapira;Jay Lee
Affiliations:
Department of Management Science and Engineering, School of Economics & Management, Tongji University, Shanghai 200092, PR China;College of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, PR China;Center for Intelligent Maintenance Systems, Department of Mechanical Engineering, University of Cincinnati, Cincinnati, OH 45221, United States;Center for Intelligent Maintenance Systems, Department of Mechanical Engineering, University of Cincinnati, Cincinnati, OH 45221, United States
Venue:
Applied Soft Computing
Year:
2013

Citing 23
Cited 0

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Machine Learning for the Detection of Oil Spills in Satellite Radar Images

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Support vector domain description

Pattern Recognition Letters - Special issue on pattern recognition in practice VI
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Generalized radial basis function networks for classification and novelty detetion: self-organization of optional Bayesian decision

Neural Networks
Unsupervised Feature Selection Using Feature Similarity

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pump Failure Detection Using Support Vector Data Descriptions

IDA '99 Proceedings of the Third International Symposium on Advances in Intelligent Data Analysis
Uniform object generation for optimizing one-class classifiers

The Journal of Machine Learning Research
Novelty detection: a review—part 1: statistical approaches

Signal Processing
Novelty detection: a review—part 2: neural network based approaches

Signal Processing
Support Vector Data Description

Machine Learning
An Approach to Novelty Detection Applied to the Classification of Image Regions

IEEE Transactions on Knowledge and Data Engineering
A Neural Network-Based Novelty Detector for Image Sequence Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Kernel PCA for novelty detection

Pattern Recognition
Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble

Expert Systems with Applications: An International Journal
Integrating support vector machine and genetic algorithm to implement dynamic wafer quality prediction system

Expert Systems with Applications: An International Journal
Fast support vector data descriptions for novelty detection

IEEE Transactions on Neural Networks
High-speed inline defect detection for TFT-LCD array process using a novel support vector data description

Expert Systems with Applications: An International Journal
Statistical processes monitoring based on improved ICA and SVDD

ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I
Network intrusion and fault detection: a statistical anomaly approach

IEEE Communications Magazine
Neural tree density estimation for novelty detection

IEEE Transactions on Neural Networks
A method for improving classification reliability of multilayer perceptrons

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Novelty detection is an important issue for practical industrial application, in which there is only normal operating data available in most cases. This paper proposes a systematic approach for novelty detection of mechanical components, using support vector data description (SVDD), a kernel approach for modeling the support of a distribution. To reduce the false alarm rate and increase the detection accuracy, a parameter optimization estimation scheme is proposed based on a grid search method that relies on the performance trade-off between the minimum fraction of support vectors and the maximum dual problem objective value. An evaluation value (E-value) chart based on the kernel distance for detection result is also designed to facilitate the decision visualization. To illustrate the effectiveness of the proposed method, novelty detection was applied to a particular kind of tapered roller bearing used in an industrial robot, which is investigated as a case study. The experimental results, in comparison to other methods, demonstrate that the proposed SVDD can conduct novelty detection of the monitored mechanical component effectively with higher accuracy.