Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2 results about "Basis expansion" patented technology

Basis expansion is a simple extension of linear models to model nonlinearity. It is to transform the predictors (x-variables) with nonlinear representations, in another word, replace \(x\) in the model with \(\phi_1(x), \phi_2(x), \ldots\) for some chosen basis functions.

Spectrally modulated radiation thermometry device and method

The application discloses a kind of spectral modulation radiation temperature measuring device and method, belongs to optical radiation temperature measuring technical field.For the problems, such as limited spectral channel, difficult to realize single-exposure multi-channel synchronous acquisition, temperature measuring stability and insufficient inversion robustness of existing radiation temperature measuring technology under long-distance, high dynamic and complex background conditions, the present application sets up wide-spectrum modulation optical window at the incident end, and combines wide-spectrum modulation multi-modal spectral chip, to synchronously acquire multi-channel wide-spectrum modulation radiation image under single exposure;Pretreatment is carried out using system on chip, and wide-spectrum modulation response model, emissivity spectral basis expansion model and time domain regularization are fused in temperature inversion calculation platform, to realize stable inversion of real temperature field, emissivity distribution and temperature rising sequence, suitable for non-contact temperature measurement in long-distance high-temperature target and other fields.
Owner:XINGTU OPTOELECTRONICS TECHNOLOGY (JILIN) CO LTD

Bi-lstm-sa low complexity otfs channel estimation method and system based on basis expansion model

The application relates to a Bi-LSTM-SA low-complexity OTFS channel estimation method and system based on a basis expansion model and belongs to the technical field of wireless communication and deep learning. In view of the problems of low channel estimation accuracy and high equalization complexity in a high-speed mobile scene, the application converts time-domain channel estimation into low-dimensional basis coefficient estimation through a basis expansion model, extracts basis coefficient time sequence features by using a self-attention enhanced bidirectional long short-term memory network, and realizes high-precision channel estimation. Meanwhile, a two-stage equalizer is adopted, single-tap equalization is carried out in a time-frequency domain, and residual interference is suppressed through iterative interference cancellation in a delay-Doppler domain. The application effectively balances estimation accuracy and calculation complexity, and improves the anti-Doppler spread capability and spectral utilization efficiency of a system.
Owner:CHONGQING UNIV OF POSTS & TELECOMM