Loading...

Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks

Shariat, K ; Sharif University of Technology | 2022

32 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.aca.2021.338697
  3. Publisher: Elsevier B.V , 2022
  4. Abstract:
  5. In recent years, convolutional neural networks and deep neural networks have been used extensively in various fields of analytical chemistry. The use of these models for calibration tasks has been highly effective; however, few reports have been published on their properties and characteristics of analytical figures of merit. Currently, most performance measures for these types of networks only incorporate some function of prediction error. While useful, these measures are incomplete and cannot be used as an objective comparison among different models. In this report, a new method for calculating the sensitivity of any type of neural network is proposed and studied on both simulated and real datasets. Generalized analytical sensitivity is defined and calculated for neural networks as an additional figure of merit. Moreover, the dependence of convolutional neural networks on regularization dataset size is studied and compared with other conventional calibration methods. © 2021 Elsevier B.V
  6. Keywords:
  7. Analytical figures of merit ; Convolutional neural networks ; Sensitivity ; Chemical analysis ; Convolution ; Deep neural networks ; Analytical figure of merits ; Calibration tasks ; Deep learning ; Neural-networks ; Performance measure ; Prediction errors ; Property ; Sensitivity expressions ; Calibration ; Convolutional neural network ; Prediction ; Quantitative analysis ; Sensitivity analysis ; Simulation ; Deep neural network ; Prediction error ; Neural Networks, Computer
  8. Source: Analytica Chimica Acta ; Volume 1192 , 2022 ; 00032670 (ISSN)
  9. URL: https://www.sciencedirect.com/science/article/abs/pii/S0003267021005237