Signal reconstruction from sampled data using neural network

A. Sudou, P. Hartono, R. Saegusa, S. Hashimoto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    For reconstructing a signal from sampling data, the method based on Shannon's sampling theorem is usually employed. The reconstruction error appears when the signal does not satisfy the Nyquist condition. This paper proposes a new reconstruction method by using a linear perceptron and multilayer perceptron as FIR filter. The perceptron, which has weights obtained by learning when adapting the original signal, suppresses the difference between the reconstructed signal and the original signal even when the Nyquist condition does not stand. Although the proposed method needs weight data, the total data size is much smaller than the ordinary sampling method, as the most suitable reconstruction filter is exclusively adapted to the given sampling data.

    Original languageEnglish
    Title of host publicationNeural Networks for Signal Processing - Proceedings of the IEEE Workshop
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages707-715
    Number of pages9
    Volume2002-January
    ISBN (Print)0780376161
    DOIs
    Publication statusPublished - 2002
    Event12th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2002 - Martigny, Switzerland
    Duration: 2002 Sep 6 → …

    Other

    Other12th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2002
    CountrySwitzerland
    CityMartigny
    Period02/9/6 → …

    Fingerprint

    Signal reconstruction
    Sampling
    Neural networks
    FIR filters
    Multilayer neural networks

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Artificial Intelligence
    • Software
    • Computer Networks and Communications
    • Signal Processing

    Cite this

    Sudou, A., Hartono, P., Saegusa, R., & Hashimoto, S. (2002). Signal reconstruction from sampled data using neural network. In Neural Networks for Signal Processing - Proceedings of the IEEE Workshop (Vol. 2002-January, pp. 707-715). [1030082] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NNSP.2002.1030082

    Signal reconstruction from sampled data using neural network. / Sudou, A.; Hartono, P.; Saegusa, R.; Hashimoto, S.

    Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. Vol. 2002-January Institute of Electrical and Electronics Engineers Inc., 2002. p. 707-715 1030082.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Sudou, A, Hartono, P, Saegusa, R & Hashimoto, S 2002, Signal reconstruction from sampled data using neural network. in Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. vol. 2002-January, 1030082, Institute of Electrical and Electronics Engineers Inc., pp. 707-715, 12th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2002, Martigny, Switzerland, 02/9/6. https://doi.org/10.1109/NNSP.2002.1030082
    Sudou A, Hartono P, Saegusa R, Hashimoto S. Signal reconstruction from sampled data using neural network. In Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. Vol. 2002-January. Institute of Electrical and Electronics Engineers Inc. 2002. p. 707-715. 1030082 https://doi.org/10.1109/NNSP.2002.1030082
    Sudou, A. ; Hartono, P. ; Saegusa, R. ; Hashimoto, S. / Signal reconstruction from sampled data using neural network. Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. Vol. 2002-January Institute of Electrical and Electronics Engineers Inc., 2002. pp. 707-715
    @inproceedings{339716b410604bd28153d1fd712bae6e,
    title = "Signal reconstruction from sampled data using neural network",
    abstract = "For reconstructing a signal from sampling data, the method based on Shannon's sampling theorem is usually employed. The reconstruction error appears when the signal does not satisfy the Nyquist condition. This paper proposes a new reconstruction method by using a linear perceptron and multilayer perceptron as FIR filter. The perceptron, which has weights obtained by learning when adapting the original signal, suppresses the difference between the reconstructed signal and the original signal even when the Nyquist condition does not stand. Although the proposed method needs weight data, the total data size is much smaller than the ordinary sampling method, as the most suitable reconstruction filter is exclusively adapted to the given sampling data.",
    author = "A. Sudou and P. Hartono and R. Saegusa and S. Hashimoto",
    year = "2002",
    doi = "10.1109/NNSP.2002.1030082",
    language = "English",
    isbn = "0780376161",
    volume = "2002-January",
    pages = "707--715",
    booktitle = "Neural Networks for Signal Processing - Proceedings of the IEEE Workshop",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Signal reconstruction from sampled data using neural network

    AU - Sudou, A.

    AU - Hartono, P.

    AU - Saegusa, R.

    AU - Hashimoto, S.

    PY - 2002

    Y1 - 2002

    N2 - For reconstructing a signal from sampling data, the method based on Shannon's sampling theorem is usually employed. The reconstruction error appears when the signal does not satisfy the Nyquist condition. This paper proposes a new reconstruction method by using a linear perceptron and multilayer perceptron as FIR filter. The perceptron, which has weights obtained by learning when adapting the original signal, suppresses the difference between the reconstructed signal and the original signal even when the Nyquist condition does not stand. Although the proposed method needs weight data, the total data size is much smaller than the ordinary sampling method, as the most suitable reconstruction filter is exclusively adapted to the given sampling data.

    AB - For reconstructing a signal from sampling data, the method based on Shannon's sampling theorem is usually employed. The reconstruction error appears when the signal does not satisfy the Nyquist condition. This paper proposes a new reconstruction method by using a linear perceptron and multilayer perceptron as FIR filter. The perceptron, which has weights obtained by learning when adapting the original signal, suppresses the difference between the reconstructed signal and the original signal even when the Nyquist condition does not stand. Although the proposed method needs weight data, the total data size is much smaller than the ordinary sampling method, as the most suitable reconstruction filter is exclusively adapted to the given sampling data.

    UR - http://www.scopus.com/inward/record.url?scp=84953738891&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84953738891&partnerID=8YFLogxK

    U2 - 10.1109/NNSP.2002.1030082

    DO - 10.1109/NNSP.2002.1030082

    M3 - Conference contribution

    AN - SCOPUS:84953738891

    SN - 0780376161

    VL - 2002-January

    SP - 707

    EP - 715

    BT - Neural Networks for Signal Processing - Proceedings of the IEEE Workshop

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -