2 papers
quant-ph2025
Time-series forecasting for nonlinear high-dimensional system using hybrid method combining autoencoder and multi-parallelized quantum long short-term memory and gated recurrent unit
Makoto Takagi, Ryuji Kokubo, Misato Kurosawa +7
A time-series forecasting method for high-dimensional spatial data is proposed. The method involves optimal selection of sparse sensor positions to efficiently represent the spatia…
physics.flu-dyn2024
Triple decomposition and sparse representation for noisy pressure-sensitive paint data
Koyo Kubota, Makoto Takagi, Tsubasa Ikami +5
Triple decomposition is a useful analytical method for extracting the mean value, organized coherent motion, and stochastic part from a fluctuating quantity. Although the pressure-…