Optimization of disorder dispersion spectrometer using artificial neural networks

We propose an approach to reconstruct spectrum using artificial neural networks (ANNs) instead of directly solving a matrix equation using calibration coefficients. ANNs are particularly effective in reconstructing spectra in noise environment by learning the relationship between inputs and outputs with large amount of data training. There are several different training methods for ANNs. Compared with scaled conjugate gradient algorithm and Levenberg–Marquardt algorithm, Bayesian regularization (BR) algorithm is demonstrated to be a better training algorithm for spectral reconstruction. We also compare the spectral reconstruction of BR algorithm and that of the traditional algorithms. Experimental results indicate that the spectral reconstruction of BR algorithm is nearly in line with that measured by a commercial spectrometer. Obvious deviations are occurred in the spectral reconstruction of the traditional algorithms due to inevitable background noise, rounding errors, and temperature variations. Therefore, spectral reconstruction using ANNs with a train method of BR algorithm is a more suitable choice for the disorder dispersion spectrometer.