A neural network approach for micro-PIXE-data

E. Rokita, P.H.A. Mutsaers, J.A. Quaedackers, Z. Tabor, M.J.A. Voigt, de

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    10 Downloads (Pure)


    The application of the artificial neural network for the processing of one-dimensional micro-PIXE data is described. The network architecture, selection of the transfer function as well as the training and verification operations are described in detail. The performed reconstructions confirm that the neural network may be used for improvement of the resolution and for processing of low statistics data. The limitations of the neural network application for two-dimensional images are discussed.
    Originele taal-2Engels
    Pagina's (van-tot)159-164
    Aantal pagina's6
    TijdschriftNuclear Instruments and Methods in Physics Research. Section B: Beam Interactions with Materials and Atoms
    Nummer van het tijdschrift1-4
    StatusGepubliceerd - 1999

    Vingerafdruk Duik in de onderzoeksthema's van 'A neural network approach for micro-PIXE-data'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit