RDE with Forgetting: An Approximate Solution for Large Values of $$k$$ with an Application to Fault Detection Problems

详细信息    查看全文

• 作者：Clauber Gomes Bezerra (7)
  Bruno Sielly Jales Costa (8)
  Luiz Affonso Guedes (9)
  Plamen Parvanov Angelov (10) (11)
  
  7. Federal Institute of Rio Grande do Norte - IFRN ; Campus EaD ; Natal ; Brazil
  8. Federal Institute of Rio Grande do Norte - IFRN ; Campus Zona Norte ; Natal ; Brazil
  9. Department of Computer Engineering and Automation - DCA ; Federal University of Rio Grande do Norte - UFRN ; Natal ; Brazil
  10. Data Science Group ; School of Computing and Communications ; Lancaster University ; Lancaster ; LA1 4WA ; UK
  11. Chair of Excellence ; Carlos III University ; Madrid ; Spain
  
• 关键词：Outlier detection ; Novelty detection ; Fault detection ; Recursive density estimation
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9047
• 期：1
• 页码：169-178
• 全文大小：844 KB
• 参考文献：1. Singh, K., Upadhyaya, S.: Outlier Detection: Applications And Techniques. International Journal of Computer Science Issues (2012)
  2. Venkatasubramanian, V.: Abnormal events management in complex process plants: Challenges and opportunities in intelligent supervisory control, em Foundations of Computer-Aided Process Operations, pp. 117鈥?32 (2003)
  3. Angelov, P., Buswell, R.: Evolving rule-based models: A tool for intelligent adaptation. In: Joint 9th IFSA World Congress and 20th NAFIPS International Conference, vol. 2, pp. 1062鈥?067 (2001)
  4. Angelov, P.: Anomalous system state identification, patent GB1208542.9, priority date: May 15, 2012 (2012)
  5. Angelov, P.: Autonomous Learning Systems: From Data to Knowledge in Real Time. John Willey and Sons (2012)
  6. Angelov, P., Ramezani, R., Zhou, X.: Autonomous novelty detection and object tracking in video streams using evolving clustering and takagi-sugeno type neuro-fuzzy system. In: IEEE International Joint Conference on Neural Networks, IJCNN 2008. IEEE World Congress on Computational Intelligence, pp. 1456鈥?463 (2008)
  7. Ramezani, R., Angelov, P., Zhou, X.: A fast approach to novelty detection in video streams using recursive density estimation. In: 4th International IEEE Conference on Intelligent Systems, IS 2008, vol. 2, pp 142鈥?47 (2008)
  8. Kolev, D., Angelov, P., Markarian, G., Suvorov, M., Lysanov, S.: ARFA: Automated real time flight data analysis using evolving clustering, classifiers and recursive density estimation. In: Proceedings of the IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, pp. 91鈥?7 (2013)
  9. Malhi, A, Gao, R (2004) PCA-based feature selection scheme for machine defect classification. IEEE Transactions on Instrumentation and Measurement 53: pp. 1517-1525 CrossRef
  10. Kembhavi, A, Harwood, D, Davis, L (2011) Vehicle detection using partial least squares. IEEE Transactions on Pattern Analysis and Machine Intelligence 33: pp. 1250-1265 CrossRef
  11. Song, F., Mei, D., Li, H.: Feature selection based on linear discriminant analysis. In: 2010 International Conference on Intelligent System Design and Engineering Application (ISDEA), vol. 1, pp. 746鈥?49 (2010)
  12. Pande, SS, Prabhu, BS (1990) An expert system for automatic extraction of machining features and tooling selection for automats. Computer-Aided Engineering Journal 7: pp. 99-103 CrossRef
  13. Dash, S., Rengaswamy, R., Venkatasubramanian, V.: Fuzzy-logic based trend classification for fault diagnosis of chemical processes. Computers & Chemical Engineering 27(3), 347鈥?62
  14. Anzanello, M.J.: Feature Extraction and Feature Selection: A Survey of Methods in Industrial Applications. John Wiley & Sons, Inc. (2010)
  15. Levine, M (1969) Feature extraction: A survey. Proceedings of the IEEE 57: pp. 1391-1407 CrossRef
  16. Liu, H., Chen, G., Jiang, S., Song, G: A survey of feature extraction approaches in analog circuit fault diagnosis. In: Pacific-Asia Workshop on Computational Intelligence and Industrial Application, PACIIA 2008, vol. 2, pp. 676鈥?80 (2008)
  17. Bartys, M., Patton, R., Syfert, M., de las Heras, S., Quevedo, J.: Introduction to the DAMADICS actuator FDI benchmark study. Control Engineering Practice 14(6), 577鈥?96 (2006) ISSN 0967鈥?661
  18. DAMADICS Information Web site. http://diag.mchtr.pw.edu.pl/damadics/
  19. Costa, BSJ, Angelov, PP, Guedes, LA (2014) Real-time fault detection using recursive density estimation. Journal of Control, Automation and Electrical Systems 25: pp. 428-437 CrossRef
  20. Costa, BSJ, Angelov, PP, Guedes, LA (2014) Fully unsupervised fault detection and identification based on recursive density estimation and self-evolving cloud-based classifier. Neurocomputing 150: pp. 289-303 CrossRef
  21. Costa, B.S.J., Angelov, P.P., Guedes, L.A.: A new unsupervised approach to fault detection and identification. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 1557鈥?564, July 6鈥?1 (2014)
  22. Chen, W, Khan, AQ, Abid, M, Ding, SX (2011) Integrated design of observer based fault detection for a class of uncertain nonlinear systems. Applied Mathematics and Computer Science 21: pp. 423-430
  23. Lemos, A, Caminhas, W, Gomide, F (2013) Adaptive fault detection and diagnosis using an evolving fuzzy classifier. Inf. Sci. 220: pp. 64-85 CrossRef
  
• 作者单位：Statistical Learning and Data Sciences
• 丛书名：978-3-319-17090-9
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Recursive density estimation is a very powerful metric, based on a kernel function, used to detect outliers in a n-dimensional data set. Since it is calculated in a recursive manner, it becomes a very interesting solution for on-line and real-time applications. However, in its original formulation, the equation defined for density calculation is considerably conservative, which may not be suitable for applications that require fast response to dynamic changes in the process. For on-line applications, the value of k, which represents the index of the data sample, may increase indefinitely and, once that the mean update equation directly depends on the number of samples read so far, the influence of a new data sample may be nearly insignificant if the value of k is high. This characteristic creates, in practice, a stationary scenario that may not be adequate for fault detect applications, for example. In order to overcome this problem, we propose in this paper a new approach to RDE, holding its recursive characteristics. This new approach, called RDE with forgetting, introduces the concept of moving mean and forgetting factor, detailed in the next sections. The proposal is tested and validated on a very well known real data fault detection benchmark, however can be generalized to other problems.