Biorthogonal wavelet trees in the classification of embedded signal classes for intelligent sensors using machine learning applications

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Biorthogonal wavelet trees in the classification of embedded signal classes for intelligent sensors using machine learning applications. / Mercorelli, Paolo.
In: Journal of the Franklin Institute, Vol. 344, No. 6, 01.09.2007, p. 813-829.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{c7531a3afdef4d05b51fa31fba25b675,
title = "Biorthogonal wavelet trees in the classification of embedded signal classes for intelligent sensors using machine learning applications",
abstract = "The paper deals with a method of constructing orthonormal bases of coordinates which maximize, through redundant dictionaries (frames) of biorthogonal bases, a class separability index or distances among classes. The method proposes an algorithm which consists of biorthogonal expansions over two redundant dictionaries. Embedded classes are often present in multiclassification problems. It is shown how the biorthogonality of the expansion can really help to construct a coordinate system which characterizes the classes. The algorithm is created for training wavelet networks in order to provide an efficient coordinate system maximizing the Cross Entropy function between two complementary classes. Sine and cosine wavelet packets are basis functions of the network. Thanks to their packet structure, once selected the depth of the tree, an adaptive number of basis functions is automatically chosen. The algorithm is also able to carry out centering and dilation of the basis functions in an adaptive way. The algorithm works with a preliminary extracted feature through shrinkage technique in order to reduce the dimensionality of the problem. In particular, our attention is pointed out for time-frequency monitoring, detection and classification of transients in rail vehicle systems and the outlier problem. In the former case the goal is to distinguish transients as inrush current and no inrush current and a further distinction between the two complementary classes: dangerous inrush current and no dangerous inrush current. The proposed algorithm is used on line in order to recognize the dangerous transients in real time and thus shut-down the vehicle. The algorithm can also be used in a general application of the outlier detection. A similar structure is used in developed algorithms which are currently integrated in the inferential modeling platform of the unit responsible for Advanced Control and Simulation Solutions within ABB's (Asea Brown Boveri) industry division. It is shown how impressive and rapid performances are achieved with a limited number of wavelets and few iterations. Real applications using real measured data are included to illustrate and analyze the effectiveness of the proposed method.",
keywords = "Machine learning, Signal classification, Trigonometric bases, Wavelet networks, Wavelet packets, Classification (of information), Computer simulation, Learning systems, Problem solving, Signal processing, Smart sensors, Biorthogonal expansions, Multiclassification problems, Wavelet transforms, Engineering",
author = "Paolo Mercorelli",
note = "Cited By (since 1996): 1 Export Date: 22 May 2012 Source: Scopus CODEN: JFINA doi: 10.1016/j.jfranklin.2006.10.003 Language of Original Document: English Correspondence Address: Mercorelli, P.; Department of Vehicles, Production and Process Engineering, University of Applied Sciences Wolfsburg, Robert-Koch-Platz 8-a, 38440 Wolfsburg, Germany; email: p.mercorelli@fh-wolfsburg.de References: Mercorelli, P., Terwiesch, P., A black box identification in harmonic domain (2003) VDE Eur. Trans. Electr. Power, 13 (1), pp. 29-40; Zhang, Q., Using wavelet network in nonparametric estimation (1997) IEEE Trans. Neural Networks, 8 (2), pp. 227-236; Terwiesch, P., Menth, S., Schmidt, S., Analysis of transients in electrical railway networks using wavelets (1998) IEEE Trans. Ind. Electron., 45 (6), pp. 955-959; Mercorelli, P., Terwiesch, P., A signal classification algorithm using smooth local trigonometric bases (2002) Automatisierungstechnik Oldenburg Verlag, 50 (11), pp. 541-550; R Coifman, R., Wickerhauser, M.V., Entropy based algorithm for best basis selection (1992) IEEE Trans. Inform. Theory, 32, pp. 712-718; Daubechies, I., (1995) Cen Lectures on Wavelets, , Publisher Society for Industrial and Applied Mathematics, Philadelphia, PA;",
year = "2007",
month = sep,
day = "1",
doi = "10.1016/j.jfranklin.2006.10.003",
language = "English",
volume = "344",
pages = "813--829",
journal = "Journal of the Franklin Institute",
issn = "0016-0032",
publisher = "Elsevier Ltd",
number = "6",

}

RIS

TY - JOUR

T1 - Biorthogonal wavelet trees in the classification of embedded signal classes for intelligent sensors using machine learning applications

AU - Mercorelli, Paolo

N1 - Cited By (since 1996): 1 Export Date: 22 May 2012 Source: Scopus CODEN: JFINA doi: 10.1016/j.jfranklin.2006.10.003 Language of Original Document: English Correspondence Address: Mercorelli, P.; Department of Vehicles, Production and Process Engineering, University of Applied Sciences Wolfsburg, Robert-Koch-Platz 8-a, 38440 Wolfsburg, Germany; email: p.mercorelli@fh-wolfsburg.de References: Mercorelli, P., Terwiesch, P., A black box identification in harmonic domain (2003) VDE Eur. Trans. Electr. Power, 13 (1), pp. 29-40; Zhang, Q., Using wavelet network in nonparametric estimation (1997) IEEE Trans. Neural Networks, 8 (2), pp. 227-236; Terwiesch, P., Menth, S., Schmidt, S., Analysis of transients in electrical railway networks using wavelets (1998) IEEE Trans. Ind. Electron., 45 (6), pp. 955-959; Mercorelli, P., Terwiesch, P., A signal classification algorithm using smooth local trigonometric bases (2002) Automatisierungstechnik Oldenburg Verlag, 50 (11), pp. 541-550; R Coifman, R., Wickerhauser, M.V., Entropy based algorithm for best basis selection (1992) IEEE Trans. Inform. Theory, 32, pp. 712-718; Daubechies, I., (1995) Cen Lectures on Wavelets, , Publisher Society for Industrial and Applied Mathematics, Philadelphia, PA;

PY - 2007/9/1

Y1 - 2007/9/1

N2 - The paper deals with a method of constructing orthonormal bases of coordinates which maximize, through redundant dictionaries (frames) of biorthogonal bases, a class separability index or distances among classes. The method proposes an algorithm which consists of biorthogonal expansions over two redundant dictionaries. Embedded classes are often present in multiclassification problems. It is shown how the biorthogonality of the expansion can really help to construct a coordinate system which characterizes the classes. The algorithm is created for training wavelet networks in order to provide an efficient coordinate system maximizing the Cross Entropy function between two complementary classes. Sine and cosine wavelet packets are basis functions of the network. Thanks to their packet structure, once selected the depth of the tree, an adaptive number of basis functions is automatically chosen. The algorithm is also able to carry out centering and dilation of the basis functions in an adaptive way. The algorithm works with a preliminary extracted feature through shrinkage technique in order to reduce the dimensionality of the problem. In particular, our attention is pointed out for time-frequency monitoring, detection and classification of transients in rail vehicle systems and the outlier problem. In the former case the goal is to distinguish transients as inrush current and no inrush current and a further distinction between the two complementary classes: dangerous inrush current and no dangerous inrush current. The proposed algorithm is used on line in order to recognize the dangerous transients in real time and thus shut-down the vehicle. The algorithm can also be used in a general application of the outlier detection. A similar structure is used in developed algorithms which are currently integrated in the inferential modeling platform of the unit responsible for Advanced Control and Simulation Solutions within ABB's (Asea Brown Boveri) industry division. It is shown how impressive and rapid performances are achieved with a limited number of wavelets and few iterations. Real applications using real measured data are included to illustrate and analyze the effectiveness of the proposed method.

AB - The paper deals with a method of constructing orthonormal bases of coordinates which maximize, through redundant dictionaries (frames) of biorthogonal bases, a class separability index or distances among classes. The method proposes an algorithm which consists of biorthogonal expansions over two redundant dictionaries. Embedded classes are often present in multiclassification problems. It is shown how the biorthogonality of the expansion can really help to construct a coordinate system which characterizes the classes. The algorithm is created for training wavelet networks in order to provide an efficient coordinate system maximizing the Cross Entropy function between two complementary classes. Sine and cosine wavelet packets are basis functions of the network. Thanks to their packet structure, once selected the depth of the tree, an adaptive number of basis functions is automatically chosen. The algorithm is also able to carry out centering and dilation of the basis functions in an adaptive way. The algorithm works with a preliminary extracted feature through shrinkage technique in order to reduce the dimensionality of the problem. In particular, our attention is pointed out for time-frequency monitoring, detection and classification of transients in rail vehicle systems and the outlier problem. In the former case the goal is to distinguish transients as inrush current and no inrush current and a further distinction between the two complementary classes: dangerous inrush current and no dangerous inrush current. The proposed algorithm is used on line in order to recognize the dangerous transients in real time and thus shut-down the vehicle. The algorithm can also be used in a general application of the outlier detection. A similar structure is used in developed algorithms which are currently integrated in the inferential modeling platform of the unit responsible for Advanced Control and Simulation Solutions within ABB's (Asea Brown Boveri) industry division. It is shown how impressive and rapid performances are achieved with a limited number of wavelets and few iterations. Real applications using real measured data are included to illustrate and analyze the effectiveness of the proposed method.

KW - Machine learning

KW - Signal classification

KW - Trigonometric bases

KW - Wavelet networks

KW - Wavelet packets

KW - Classification (of information)

KW - Computer simulation

KW - Learning systems

KW - Problem solving

KW - Signal processing

KW - Smart sensors

KW - Biorthogonal expansions

KW - Multiclassification problems

KW - Wavelet transforms

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=34547415047&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/2ed0adf5-92c2-3cf0-8463-97217c7b1105/

U2 - 10.1016/j.jfranklin.2006.10.003

DO - 10.1016/j.jfranklin.2006.10.003

M3 - Journal articles

VL - 344

SP - 813

EP - 829

JO - Journal of the Franklin Institute

JF - Journal of the Franklin Institute

SN - 0016-0032

IS - 6

ER -

Recently viewed

Publications

  1. Median based algorithm as an entropy function for noise detectionin wavelet trees for data reconciliation
  2. Advanced Neural Classifier-Based Effective Human Assistance Robots Using Comparable Interactive Input Assessment Technique
  3. A Wavelet Based Algorithm without a Priori Knowledge of Noise Level for Gross Errors Detection
  4. Fostering Circularity: Building a Local Community and Implementing Circular Processes
  5. Calculation of Average Mutual Information (AMI) and false-nearest neighbors (FNN) for the estimation of embedding parameters of multidimensional time series in matlab
  6. Modeling and Performance Analysis of a Node in Fault Tolerant Wireless Sensor Networks
  7. Discourse Analyses in Chat-based CSCL with Learning Protocols
  8. Database Publishing Without Databases
  9. A Lightweight Simulation Model for Soft Robot's Locomotion and its Application to Trajectory Optimization
  10. Transformer with Tree-order Encoding for Neural Program Generation
  11. Closed-loop control of product geometry by using an artificial neural network in incremental sheet forming with active medium
  12. Preventive Emergency Detection Based on the Probabilistic Evaluation of Distributed, Embedded Sensor Networks
  13. A transfer operator based computational study of mixing processes in open flow systems
  14. Automatic enumeration of all connected subgraphs.
  15. Methodologies for Noise and Gross Error Detection using Univariate Signal-Based Approaches in Industrial Application
  16. Enabling Road Condition Monitoring with an on-board Vehicle Sensor Setup
  17. Efficient and accurate ℓ p-norm multiple kernel learning
  18. Neural network-based adaptive fault-tolerant control for strict-feedback nonlinear systems with input dead zone and saturation
  19. Different complex word problems require different combinations of cognitive skills
  20. Semantic Parsing for Knowledge Graph Question Answering with Large Language Models
  21. Control of the inverse pendulum based on sliding mode and model predictive control
  22. Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments
  23. Latent structure perceptron with feature induction for unrestricted coreference resolution
  24. Selecting and Adapting Methods for Analysis and Design in Value-Sensitive Digital Social Innovation Projects: Toward Design Principles
  25. Modeling Effective and Ineffective Knowledge Communication and Learning Discourses in CSCL with Hidden Markov Models
  26. Problem structuring for transitions
  27. Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
  28. Spatial mislocalization as a consequence of sequential coding of stimuli
  29. DialogueMaps: Supporting interactive transdisciplinary dialogues with a web-based tool for multi-layer knowledge maps
  30. Real-time RDF extraction from unstructured data streams
  31. A Multivariate Method for Dynamic System Analysis
  32. On the Decoupling and Output Functional Controllability of Robotic Manipulation
  33. Analysis of long-term statistical data of cobalt flows in the EU
  34. Supporting the Development and Implementation of a Digitalization Strategy in SMEs through a Lightweight Architecture-based Method
  35. FFTSMC with Optimal Reference Trajectory Generated by MPC in Robust Robotino Motion Planning with Saturating Inputs