Abstract

As a mineral, the traditional Chinese medicine calamine has a similar shape to many other minerals. Investigations of commercially available calamine samples have shown that there are many fake and inferior calamine goods sold on the market. The conventional identification method for calamine is complicated, therefore as a result of the large scale of calamine samples, a rapid identification method is needed. To establish a qualitative model using near-infrared (NIR) spectroscopy for rapid identification of various calamine samples, large quantities of calamine samples including crude products, counterfeits and processed products were collected and correctly identified using the physicochemical and powder X-ray diffraction method. The NIR spectroscopy method was used to analyze these samples by combining the multi-reference correlation coefficient (MRCC) method and the error back propagation artificial neural network algorithm (BP-ANN), so as to realize the qualitative identification of calamine samples. The accuracy rate of the model based on NIR and MRCC methods was 85%; in addition, the model, which took comprehensive multiple factors into consideration, can be used to identify crude calamine products, its counterfeits and processed products. Furthermore, by in-putting the correlation coefficients of multiple references as the spectral feature data of samples into BP-ANN, a BP-ANN model of qualitative identification was established, of which the accuracy rate was increased to 95%. The MRCC method can be used as a NIR-based method in the process of BP-ANN modeling.

© 2017 The Author(s)

Rapid identification of the variety of maize seeds based on near-infrared spectroscopy coupled with locally linear embedding

Shu Liu, Zhengguang Chen, and Feng Jiao
Appl. Opt. 61(7) 1704-1710 (2022)

Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network

Haiquan Ding, Qipeng Lu, Hongzhi Gao, and Zhongqi Peng
Biomed. Opt. Express 5(4) 1145-1152 (2014)

Wood quality of Chinese zither panel based on convolutional neural network and near-infrared spectroscopy

Yinglai Huang, Shiyu Meng, Peng Zhao, and Chao Li
Appl. Opt. 58(18) 5122-5127 (2019)

Energetic materials identification by laser-induced breakdown spectroscopy combined with artificial neural network

Amir Hossein Farhadian, Masoud Kavosh Tehrani, Mohammad Hossein Keshavarz, and Seyyed Mohammad Reza Darbani
Appl. Opt. 56(12) 3372-3377 (2017)

Intelligent optical performance monitor using multi-task learning based artificial neural network

Zhiquan Wan, Zhenming Yu, Liang Shu, Yilun Zhao, Haojie Zhang, and Kun Xu
Opt. Express 27(8) 11281-11291 (2019)