A signal processing system using a neural network for the laser Doppler velocimetry is described. The proposed system is based on spectrum analysis using a fast Fourier transform and adaptive prediction using a neural network. The neural network learns fluctuation of the velocity using the backpropagation algorithm and predicts the velocity related to the Doppler frequency adaptively. Actual measurement on a rotating acrylic disk was carried out. An increase in the accuracy of the velocity measurement was obtained.
|Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
|11 pt 4
|Published - 1989 12月 1
|Images of the Twenty-First Century - Proceedings of the 11th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Part 2 - Seattle, WA, USA
継続期間: 1989 11月 9 → 1989 11月 12
ASJC Scopus subject areas
- コンピュータ ビジョンおよびパターン認識