The combination of principal component analysis with neural network as a highly efficient 3D EIT solution

3rd World Congress on Industrial Process Tomography

Volumn , Issue , 2003, Pages 664-670

  Stasiak, Magdalena ^a   Siwek, Krzysztof ^b   Sikora, Ryszard ^c   Filipowicz, Stefan F ^b   Sikora, Jan ^b  

^a LODZ UNIVERSITY OF TECHNOLOGY   (Poland)

^b WARSAW UNIVERSITY OF TECHNOLOGY   (Poland)

^c WEST POMERANIAN UNIVERSITY OF TECHNOLOGY   (Poland)

Author keywords

Boundary element method; Impedance tomography; Neural network; Principal component analysis

Indexed keywords

BOUNDARY ELEMENT METHOD; CLUSTERING ALGORITHMS; COMPLEX NETWORKS; ELECTRIC IMPEDANCE TOMOGRAPHY; FINITE ELEMENT METHOD; INVERSE PROBLEMS; NEURAL NETWORKS; PROBLEM SOLVING; SAILING VESSELS; TOMOGRAPHY;

ELECTRICAL IMPE DANCE TOMOGRAPHY (EIT); GEOMETRICAL REPRESENTATION; HIGH DIMENSIONAL DATA; IMPEDANCE TOMOGRAPHY; LOW-DIMENSIONAL SUBSPACE; NEURAL NETWORK METHOD; NEURAL NETWORK SIZE; REAL-TIME RECONSTRUCTION;

PRINCIPAL COMPONENT ANALYSIS;

EID: 84910149895     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. CICHOCKI A., AMARI S., (2002), Adaptive blind signal and image processing, Wiley, April.
2. BRADLEY CH., PULLAN A., (2002), Application of the BEM in biopotential problems, Engineering Analysis with Boundary Elements 26, pp. 391-403.
3. DURAISWAMI R., CHAHINE G.L., SARKAR K., (1997), Boundary element techniques for efficient 2D and 3D electrical impedance tomography, Chemical Engineering Science, Vol. 52, No.13.
4. FERGUSON A.S., STROINK G., (1997), Factors Affecting the Accuracy of the Boundary Element Method in the Forward Problem, IEEE Transactions on Biomedical Engineering, Vol.44, No.11.
5. HSIAO CH., CHAHINE G., GUMEROV N., (2001), Application of a Hybrid Genetic/Powell Algorithm and a Boundary Element Method to Electrical Impedance Tomography, Journal of Computational Physic Vol. 173, pp. 433-454.
6. JOLLIFFE I.T., (1986), Principal Component Analysis, Springer Series in Statistics.
7. LISBOA P.J.G., IFEACHOR E.C., SZCZEPANIAK P.S., (2000), Artificial Neural Networks In Biomedicine, Springer-Verlag, London.
8. MINKA T.P., (2000), Automatic choice of dimensionality for PCA, MIT Technical Report No. 514, MIT Media Laboratory.
9. MOLINARI M., COX S.J., BLOTT B.H., DANIELL G.J., (2001), Efficient Non-Linear 3D Electrical Tomography Reconstruction, 2nd World Congress on Industrial Process Tomography.
10. OSOWSKI S., (2000), Neural Network, Warsaw University of Technology Publishers.
11. Ratajewicz-Mikolajczak E., SIKORA J., (2002), Neural Networks Method For Identification of Objects Behind the Screen, IEEE Transactions on Medical Imaging, Vol. 21, No 6.
12. SIKORA J., (2000), Numerical Algorithms in Impedance Tomography, Warsaw University of Technology Publishers (in Polish).
13. SIKORA J., ARRIDGE S., (2002), Some numerical aspects of 3D BEM application to optical tomography, IV International Workshop, pp. 59-62.
14. SIKORA R., Filipowicz S., Giza Z., Sikora J., (2000), New methods of imaging in electrical impedance tomography, COMPEL, vol. 19, No. 2, pp. 346-351.
15. STASIAK M., SIKORA J., FILIPOWICZ S.F., (2002), Neural Network Approach to Inverse Problem Solution in three-dimensional Impedance Tomography, 2nd International Symposium on Process Tomography, pp. 175-182.
16. WANG Y., WAHL F.M., (1997), Multiobjective neural network for image reconstruction, IEE Proceedings- Vis. Image Signal Process., Vol.144, No.4.
17. ZURADA J., (1992), Introduction to Artificial Neural Systems, West Publishing Company, USA.
18. PC OPERA 3D, Software for electromagnetic design from Vector Fields, http://www.vectorfields.co.uk