Imbalance detection and classification system based on wavelet analysis and artificial neural networks

Gerasimov, A. V.; Vasil’kov, Yu. V.
November 2013
Automation & Remote Control;Nov2013, Vol. 74 Issue 11, p1883
Academic Journal
We present a robust algorithm for sequential imbalance detection (detecting a change of properties) for random processes with a wavelet packet transform. Based on this detector and artificial neural networks, we develop a classification system for different types of imbalance. We compare the resulting system with Shewhart control charts. The resulting system can be successfully used in selective control and under other conditions of imbalance detection and classification related to insufficient information about the signal before and after the change.


Related Articles

  • Classification of Non Stationary Signals Using Ben Wavelet and Artificial Neural Networks. Benbrahim, Mohammed; Benjelloun, Khalid; Ibenbrahim, Aomar; Daoudi, Adil // International Journal of Signal Processing;2006, Vol. 2 Issue 1, p34 

    The automatic classification of non stationary signals is an important practical goal in several domains. An essential classification task is to allocate the incoming signal to a group associated with the kind of physical phenomena producing it. In this paper, we present a modular system...

  • Analysis of the EEG Signal for a Practical Biometric System. Abdullah, Muhammad Kamil; Subari, Khazaimatol S.; Loong, Justin Leo Cheang; Ahmad, Nurul Nadia // World Academy of Science, Engineering & Technology;Aug2010, Issue 44, p1123 

    No abstract available.

  • Introduction to the use of wavelet multiresolution analysis for intelligent structural health monitoring. Taha, M. M. Reda; Noureldin, A.; Osman, A.; El-Sheimy, N. // Canadian Journal of Civil Engineering;Oct2004, Vol. 31 Issue 5, p719 

    This paper suggests the use of wavelet multiresolution analysis (WMRA) as a reliable tool for digital signal processing in structural health monitoring (SHM) systems. A damage occurrence detection algorithm using WMRA augmented with artificial neural networks (ANN) is described. The suggested...

  • Multi-Stage, Multi-Resolution Method for Automatic Characterization of Epileptic Spikes in EEG. Ganesan, M.; Sumesh, E. P.; Vidhyalavanya, R. // International Journal of Signal Processing, Image Processing & P;Jun2010, Vol. 3 Issue 2, p33 

    In this paper, a technique is proposed for the automatic detection of the spikes in long term 18 channel human electroencephalograms (EEG) with less number of data set. The scheme for detecting epileptic and non epileptic spikes in EEG is based on a multi resolution, multi-level analysis and...

  • Discrete Wavelet Transform and Support Vector Machines Algorithm for Classification of Fault Types on Transmission Line. Kunadumrongrath, K.; Ngaopitakkul, A. // Proceedings of the International MultiConference of Engineers & ;2012, Special section p1 

    This paper proposes a new technique using discrete wavelet transform (DWT) and support vector machines (SVM) to classify the fault types on transmission systems. The DWT is used to detect the high frequency components from fault signals. Positive sequence current signals are used in fault...

  • Fault Analysis of Engine Timing Gear and Valve Clearance Using Discrete Wavelet and a Support Vector Machine. Jian-Da Wu; Jian-Bin Chain; Chen-Wei Chung; Hao Yu // International Journal of Computer Theory & Engineering;Jun2012, Vol. 4 Issue 3, p386 

    An engine fault diagnosis method based on discrete wavelet transform and a support vector machine using engine vibration and sound signals is proposed in the present study. The use of mechanical vibration and sound signals for fault analysis in rotating machinery has grown significantly due to...

  • Neural Network Speed Sensorless Direct Vector Control of Induction Motor Using Fuzzy Logic in Speed Control Loop. Mouna, Ben Hamed; Aicha, Abid; Lassaad, Sbita // International Review of Electrical Engineering;Sep/Oct2011 Part A, Vol. 6 Issue 5, p2237 

    This paper deals with performance analysis and implementation of a robust sensorless speed controller associated with a new direct rotor flux oriented control (DRFOC) for induction motor (IM) drives. The robustness s is guaranted by the use of a fuzzy logic controller. Due to the drawbacks of...

  • Application of InP Neural Network to ECG Beat Classification. Olmez, Tamer; Dokur, Zumray // Neural Computing & Applications;2003, Vol. 11 Issue 3/4, p144 

    This paper presents an application of a hybrid neural network structure to the classification of the electrocardiogram (ECG) beats. Three different feature extraction methods are comparatively examined: discrete cosine transform, wavelet transform and a direct method. Classification...

  • Efficient Bio Metric IRIS Recognition System Using Fuzzy Neural Network. Karthikeyan, T. // International Journal of Advanced Networking & Applications;May/Jun2010, Vol. 1 Issue 6, p371 

    The High protection mechanism and security is very essential things in a grow of computer world. Biometric Authentication is in rider seat of the computer society. Authentication and security based on "what you are?" rather than what you have? Like Identity Card, Physical Key and what you know?...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics