Development of a calibration model for near infrared spectroscopy using a convolutional neural network

Abstract

Development of qualitative or quantitative models is essential to exploit the full potential of near infrared (NIR) spectroscopy. In tandem with one-dimensional convolutional neural network (1D-CNN), a data-driven model is developed using NIR spectroscopy to estimate organic contents. First, the 1D-CNN model is designed to capture the features of the NIR spectra by means of several convolutional and pooling operations. Then, the suitable hyper-parameters of 1D-CNN are obtained by using the grid search algorithm to achieve the optimal performance. Furthermore, the dropout operation is added into the 1D-CNN to suppress the overfitting problem by means of removing some neurons, and the probability distribution of throwing follows the Bernoulli distribution. The developed framework is validated by the application in the sugar content estimation of Huangshan Maofeng tea. The experimental results demonstrate that the key features of the NIR spectra are successfully extracted by the proposed strategy; thereby, a new effective scheme for analyzing NIR spectra is provided for food analysis.

Rapid identification of the geographical origin of Baimudan tea using a Multi-AdaBoost model integrated with Raman Spectroscopy

“…While traditional AdaBoost is commonly used for binary classification applications, Multi-AdaBoost was extended to address complex multi-classification problems, rendering it more suitable for such scenarios. Furthermore, Multi-AdaBoost holds great potential for application in spectral analysis ( Li and Rong, 2022 ).…”

To Quickly Detect the Geographical Origin of Baimudan Tea by Multi-AdaBoost Model Combined with Raman Spectroscopy

“…Traditional AdaBoost, a commonly used ensemble learning classi cation algorithm, is suitable for the application of two classi cation. While Multi-AdaBoost is extended to multi-classi cation, making it more suitable for complex multi-classi cation problems.In addition, Multi-AdaBoost has great potential for the application in spectral analysis (Li and Rong 2022). So far, the analysis of Multi-AdaBoost algorithm combined with Raman spectroscopy has not been reported.…”