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

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

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, Jahrgang 344, Nr. 6, 01.09.2007, S. 813-829.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

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 -

DOI

Zuletzt angesehen

Publikationen

  1. Using a Bivariate Polynomial in an EKF for State and Inductance Estimations in the Presence of Saturation Effects to Adaptively Control a PMSM
  2. Multivariate Optimization of Analytical Methodology and a First Attempt to an Environmental Risk Assessment of β-Blockers in Hospital Wastewater
  3. Diskurs über Nachhaltigkeit als Herausforderung für Disziplinen zur ethischen Vergewisserung – konkretisiert am Beispiel Erziehungswissenschaft
  4. Degradation and elimination of anticancer drugs by water and wastewater treatment - toxicity and biodegradability before and after the treatment
  5. Konzept eines Orientierungsrahmens für den Lernbereich Globale Entwicklung im Fach Informatik im Rahmen der Bildung fur Nachhaltige Entwicklung
  6. Perspektive Nachhaltigkeit: Zur beruflichen Zufriedenheit und Belastung von psychiatrischen Fachärzten in der ambulanten Versorgung in der Schweiz
  7. An IAD framework analysis of minigrid institutions for sustainable rural electrification in East Africa
  8. Untersuchungen zur Struktur und zur Moos- und Flechtenflora in unbewirtschafteten und bewirtschafteten Buchenwäldern des Nordostdeutschen Tieflandes
  9. Use of lignins from sugarcane bagasse for assembling microparticles loaded with Azadirachta indica extracts for use as neem-based organic insecticides
  10. Earnings Less Risk-Free Interest Charge (ERIC) and Stock Returns—A Value-Based Management Perspective on ERIC’s Relative and Incremental Information Content
  11. Thomas Berker / Maren Hartmann / Yves Punie / Katie J. Ward (Eds.): Domestication of Media and Technology, Maidenhead: Open University Press, 2006. ISBN: 0-335-21768-0
  12. New and Rapid Fully Automated Method for Determination of Tazobactam and Piperacillin in Fatty Tissue and Serum by Column-Switching Liquid Chromatography
  13. Los Huehuetlatolli del Códice Florentino como representaciones (icono)-gráficas de la producción comunicativa de los “naturales” de Nueva España como “pecadores”
  14. Monoculture and mixture-planting of non-native Douglas fir alters species composition, but promotes the diversity of ground beetles in a temperate forest system
  15. Description of the first instar larvae of three species of Meloe with a key to the triungulins of Central European species of this genus (Coleoptera : Meloidae)
  16. Consumer concerns about drinking water in an area with high levels of naturally occurring arsenic in groundwater, and the implications for managing health risks
  17. Die gesellschaften der Bidentetea tripartitae Tx. et al. ex von Rochow 1951 in Mecklenburg-Vorpommern mit anmerkungen zur synsystematik und nomenklatur der klasse
  18. Rezension zu: Otto, Hans-Uwe / Polutta, Andreas / Ziegler, Holger (Hg.): Evidence-based Practice – Modernising the Knowledge Base of Social Work?. Opladen: Barbara Budrich 2009
  19. Niedrigeinkommensmobilität und Persistenz: Sind Niedrigeinkommen bei Selbstständigen nur vorübergehend und welche Rolle spielen institutionelle Rahmenbedingungen?
  20. A New and Rapid Method for Monitoring the New Oxazolidinone Antibiotic Linezolid in Serum and Urine by High Performance Liquid Chromatography-Integrated Sample Preparation
  21. YouTube, Seniorentaxi und Bienen: Inwiefern wird das Kontextinteresse an realitätsbezogenen Mathematikaufgaben durch das Geschlecht und den sozialen Hintergrund beeinflusst?
  22. Modeling the distribution of white spruce (Picea glauca) for Alaska with high accuracy: an open access role-model for predicting tree species in last remaining wilderness areas
  23. Die BINK-Strategie zur Förderung nachhaltigen Konsumverhaltens und nachhaltiger Konsumkultur in Bildungsorganisationen – Weiterentwicklung auf der Basis einer formativen Evaluation
  24. Bilharz, Michael (2008): "Key Points" nachhaltigen Konsums. Ein strukturpolitisch fundierter Strategieansatz für die Nachhaltigkeitskommunikation im Kontext aktivierender Verbraucherpolitik.
  25. Kulick, Andreas/Goldhammer, Michael (Hrsg.): Der Terrorist als Feind? – Personalisierung im Polizei- und Völkerrecht, Beiträge zum Sicherheitsrecht und zur Sicherheitspolitik, Bd.5. Tübingen: MohrSiebeck, 2020.
  26. Ready biodegradability of trifluoromethylated phenothiazine drugs, structural elucidation of their aquatic transformation products, and identification of environmental risks studied by LC-MS( n ) and QSAR
  27. Wirksamkeit eines internet- und smartphone-basierten Dankbarkeitstrainings zur Förderung der gedanklichen Distanzierung von arbeitsbezogenen Problemen –Sekundäranalyse einer randomisiert - kontrollierten Studie
  28. Degradation of the tricyclic antipsychotic drug chlorpromazine under environmental conditions, identification of its main aquatic biotic and abiotic transformation products by LC-MS n and their effects on environmental bacteria
  29. Photocatalytic degradation of sulfamethoxypyridazine with TiO2, FeCl3 and TiO2/FeCl3: Biodegradability, toxicity assessment, and LC-UV-MS/MS identification of the photodegradation products in aqueous and sewage treatment plant effluent
  30. Stellungnahme der AG Methoden der gesundheitsökonomischen Evaluation (AG MEG) in der Deutschen Gesellschaft für Sozialmedizin und Prävention (DGSMP) zum 1. Entwurf des IQWiG Methodenpapiers zur Kosten-Nutzen-Bewertung von Arzneimitteln