Variational Bayes Decomposition for Inverse Estimation with Superimposed Multispectral Intensity
This addresses inverse estimation challenges in material science and related fields, but appears incremental as it builds on existing variational Bayesian and particle modeling approaches.
The paper tackles the problem of estimating unobservable object features from noisy superimposed multispectral intensity data by proposing a variational Bayesian inference method with stochastic particle modeling and smooth priors, achieving accurate inference as demonstrated in two experimental validations.
A variational Bayesian inference for measured wave intensity, such as X-ray intensity, is proposed in this paper. The data is popular to obtain information about unobservable features of an object, such as a material sample and the components of it. The proposed method assumes particles represent the wave, and their behaviors are stochastically modeled. The inference is accurate even if the data is noisy because of a smooth prior setting. Moreover, in this paper, two experimental results show feasibility of the proposed method.