Your browser doesn't support javascript.
loading
Robustness and accuracy improvement of data processing with 2D neural networks for transient absorption dynamics.
Zhao, Ruixuan; Wu, Daxin; Wen, Jiao; Zhang, Qi; Zhang, Guanglei; Li, Jiebo.
  • Zhao R; Institute of Medical Photonics, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing 100191, P. R. China. jiebo39@buaa.edu.cn.
Phys Chem Chem Phys ; 23(31): 16998-17008, 2021 Aug 12.
Article en En | MEDLINE | ID: mdl-34338705
ABSTRACT
To achieve the goal of efficiently analyzing transient absorption spectra without arbitrary assumption and to overcome the limitations of conventional methods in fitting ability and highly noised backgrounds, it is essential to develop new tools to achieve more accurate and robust prediction based on the intrinsic properties of a spectrum even under strong noise. In this work, Lasso regression and neural network were combined to achieve an effective fitting. Compared to the conventional global fitting method, our network could automatically determine the exponential form on each wave unit, in which the accuracy was as high as 97%. Thereafter, the lifetime with the corresponding amplitude ratio could be easily predicted by the neural network on each wave unit. This kind of prediction is difficult to achieve by global fitting due to the limitation of computational resources. Furthermore, more accurate fitting even under weak signals could be achieved for the mean square error (MSE) decreasing by more than 100 times on average compared to conventional global fitting methods. Attributed to its improved accuracy and robustness, our developed algorithm could be readily applied to analyze time-resolved transient spectra.

Texto completo: 1 Banco de datos: MEDLINE Idioma: En Año: 2021 Tipo del documento: Article

Texto completo: 1 Banco de datos: MEDLINE Idioma: En Año: 2021 Tipo del documento: Article