Rapid quantitative analysis of calcium in infant formula powder assisted by long short-term memory with variable importance using laser-induced breakdown spectroscopy

Abstract

Calcium is the main mineral responsible for healthy bone growth in infants. Laser-induced breakdown spectroscopy (LIBS) was combined with a variable importance-based long short-term memory (VI-LSTM) for the quantitative analysis of calcium in infant formula powder. First, the full spectra were used to establish PLS (partial least squares) and LSTM models. The R2 and root-mean-square error (RMSE) of the test set (R P 2 and RMSE P ) were 0.1460 and 0.0093 in the PLS method, respectively, and 0.1454 and 0.0091 in the LSTM model, respectively. To improve the quantitative performance, variable selection based on variable importance was introduced to evaluate the contribution of input variables. The variable importance-based PLS (VI-PLS) model had R P 2 and RMSE P of 0.1454 and 0.0091, respectively, whereas the VI-LSTM model had R P 2 and RMSE P of 0.9845 and 0.0037, respectively. Compared with the LSTM model, the number of input variables in the VI-LSTM model was reduced to 276, R P 2 was improved by 114.63%, and RMSE P was reduced by 46.38%. The mean relative error of the VI-LSTM model was 3.33%. We confirm the predictive ability of the VI-LSTM model for the calcium element in infant formula powder. Thus, combining VI-LSTM modeling and LIBS has great potential for the quantitative elemental analysis of dairy products.

NIRS-XRF fusion spectroscopy for coal calorific value prediction using data deficient learning

“…However, this approach is associated with radioactive hazards, necessitating signicant nancial investments in equipment procurement and ongoing maintenance, thereby rendering it a costly endeavor. Recently, the spectral sensors laser-induced breakdown spectroscopy (LIBS), 2,3,[8][9][10][11][12][13][14][15][16][17] near-infrared spectroscopy (NIRS), 16,[18][19][20][21] and X-ray uorescence spectroscopy (XRF) [21][22][23][24] are utilized for evaluating coal properties. LIBS leverages a high-energy laser beam to ablate coal samples that generate plasma exhibiting a unique radiation spectrum.…”

Energy value measurement of milk powder using laser-induced breakdown spectroscopy (LIBS) combined with long short-term memory (LSTM)

“…17 Several scholars have utilized LIBS technology to study milk powder and have obtained promising results. For instance, Motto-Ros et al 18 used ICP-OES and LIBS to detect Ca, Mg and K concentrations in milk powder, and compared the results of the two analytical techniques, which showed that LIBS technology could be applied to the analysis of mineral elements in organic matter (such as milk powder); Khan et al 19 detected trace metal elements such as Cd, Cr, Cu, Ni and Mn in milk powder samples using LIBS technology; the content of N in the selected samples was between 41 000 and 51 000 ppm, indicating that LIBS can be used to monitor the nutrient composition and heavy metal content in food; Cama-Moncunill et al 20 combined LIBS with a partial least squares regression model (PLSR) for the detection of Ca in milk powder, and their R P 2 reached 0.91; Markiewicz-Keszycka et al 21 used LIBS for the quantication of Mg in milk powder with a detection limit of 150 mg kg; Ding et al 22 established the VI-LSTM (long short-term memory) model based on LIBS technology for the quantitative analysis of calcium in milk powder, and their R P 2 reached 0.9845, which increased the guarantee of the quality and safety of the milk powder; and Y. Ding et al 23 employed LIBS and an ELM algorithm combined with CARS and GA to conduct quantitative analysis of the energy value of milk powder, and the study showed that the GA-CARS-ELM corrected model could obtain the best predictive performance, with an R P 2 of 0.9962.…”