Use of Adaptive Methods to Solve the Inverse Problem of Determination of Composition of Multi-Component Solutions
| Autor: | Aleksandr O. Efitorov, Tatiana A. Dolenko, S. A. Burikov, Sergey Dolenko, Kirill Laptinskiy |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
General Computer Science
Artificial neural network Computer science Dimensionality reduction Feature extraction Feature selection 02 engineering and technology Inverse problem 01 natural sciences Electronic Optical and Magnetic Materials 010309 optics Wavelet 0103 physical sciences Principal component analysis 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Electrical and Electronic Engineering Algorithm Curse of dimensionality |
| Zdroj: | Optical Memory and Neural Networks. 27:89-99 |
| ISSN: | 1934-7898 1060-992X |
| Popis: | This study considers solving the inverse problem of determination of salt or ionic composition of multi-component solutions of inorganic salts by their Raman spectra using artificial neural networks. From the point of view of data analysis, one of the key problems here is high input dimensionality of the data, as the spectrum is usually recorded in 1–2 thousand channels. The two main approaches used for dimensionality reduction are feature selection and feature extraction. In this paper, three feature extraction methods are compared: channel aggregation, principal component analysis, and discrete wavelet transformation. It is demonstrated that for neural network solution of the inverse problem of determination of salt composition, the best results are provided by channel aggregation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink