Yoshikazu Miyanaga
Hokkaido University
332 Papers
1.1K Citations
Yoshikazu Miyanaga is an academic researcher from Hokkaido University. The author has contributed to research in topics: Orthogonal frequency-division multiplexing & MIMO. The author has an hindex of 18, co-authored 329 publications. Previous affiliations of Yoshikazu Miyanaga include Denso & King Mongkut's Institute of Technology Ladkrabang.
Chat about Author
Papers
QPSK error vector magnitude demodulation with RBF neural network in Rayleigh fading channels
S. Lerkvaranyu,Yoshikazu Miyanaga +1 more
- 26 Oct 2004
TL;DR: This work proposes a method to enhance the demodulation of QPSK error vector magnitude (EVM) in a direct conversion receiver (DCR) using a radial basis function (RBF) neural network, which is used to learn the characteristics of signal constellation.
On the generalizability and adaptability of a self‐organization clustering
TL;DR: The clustering method proposed in this paper is based on a self-organization method by which every useful independent base can be obtained on a characteristic space and the user's effort of learning becomes minimum compared with supervised learning.
An adaptive signal processing system for voiced speech with automatic spectrum selector
TL;DR: A new adaptive signal processing system which uses a modified MIS algorithm and has a spectrum selector using a neural network is proposed and it is shown that the proposed system is effective for speech analysis.
Maximum likelihood detection of phase shift keying modulated signal with self-organized clustering assistant
S. Lerkvaranyu,Yoshikazu Miyanaga +1 more
- 26 Oct 2004
TL;DR: The maximum likelihood detection with self-organized clustering assistant (ML-SOCA) is proposed and results were obtained with 4PSK and 8PSK in an additive white Gaussian noise (AWGN) channel.
An Improvement in the Selection Process of Machine Translation Using Inductive Learning with Genetic Algorithms
Hiroshi Echizen-ya,Kenji Araki,Yoshikazu Miyanaga,Koji Tochinai +3 more
- 31 Mar 1997
TL;DR: An improvement in the selection process and the results of evaluation experiments are described to improve how to apply genetic algorithms to be able to remove erroneous translation rules from the dictionary.